bot: update weekly RSS feed
This commit is contained in:
github-actions[bot]
706
feed_weekly.xml
706
feed_weekly.xml
@@ -7,342 +7,566 @@
|
|||||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||||
<generator>python-feedgen</generator>
|
<generator>python-feedgen</generator>
|
||||||
<language>en</language>
|
<language>en</language>
|
||||||
<lastBuildDate>Mon, 29 Dec 2025 00:13:44 +0000</lastBuildDate>
|
<lastBuildDate>Mon, 05 Jan 2026 00:13:53 +0000</lastBuildDate>
|
||||||
<item>
|
<item>
|
||||||
<title>Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey</title>
|
<title>GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models</title>
|
||||||
<link>https://arxiv.org/abs/2412.18619</link>
|
<link>https://arxiv.org/abs/2512.15560</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.18619.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liang Chen, Zekun Wang, Shuhuai Ren, Lei Li, Haozhe Zhao, Yunshui Li, Zefan Cai, Hongcheng Guo, Lei Zhang, Yizhe Xiong, Yichi Zhang, Ruoyu Wu, Qingxiu Dong, Ge Zhang, Jian Yang, Lingwei Meng, Shujie Hu, Yulong Chen, Junyang Lin, Shuai Bai, Andreas Vlachos, Xu Tan, Minjia Zhang, Wen Xiao, Aaron Yee, Tianyu Liu, Baobao Chang</p><p><b>Upvotes:</b> 58</p><p><b>Summary:</b> Building on the foundations of language modeling in natural language processing, Next Token Prediction (NTP) has evolved into a versatile training objective for machine learning tasks across various modalities, achieving considerable success. As Large Language Models (LLMs) have advanced to unify understanding and generation tasks within the textual modality, recent research has shown that tasks from different modalities can also be effectively encapsulated within the NTP framework, transforming the multimodal information into tokens and predict the next one given the context. This survey introduces a comprehensive taxonomy that unifies both understanding and generation within multimodal learning through the lens of NTP. The proposed taxonomy covers five key aspects: Multimodal tokenization, MMNTP model architectures, unified task representation, datasets \& evaluation, and open challenges. This new taxonomy aims to aid researchers in their exploration of multimodal intelligence. An associated GitHub repository collecting the latest papers and repos is available at https://github.com/LMM101/Awesome-Multimodal-Next-Token-Prediction</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.15560.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bozhou Li, Sihan Yang, Yushuo Guan, Ruichuan An, Xinlong Chen, Yang Shi, Pengfei Wan, Wentao Zhang, Yuanxing zhang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> The text encoder is a critical component of text-to-image and text-to-video diffusion models, fundamentally determining the semantic fidelity of the generated content. However, its development has been hindered by two major challenges: the lack of an efficient evaluation framework that reliably predicts downstream generation performance, and the difficulty of effectively adapting pretrained language models for visual synthesis. To address these issues, we introduce GRAN-TED, a paradigm to Generate Robust, Aligned, and Nuanced Text Embeddings for Diffusion models. Our contribution is twofold. First, we propose TED-6K, a novel text-only benchmark that enables efficient and robust assessment of an encoder's representational quality without requiring costly end-to-end model training. We demonstrate that performance on TED-6K, standardized via a lightweight, unified adapter, strongly correlates with an encoder's effectiveness in downstream generation tasks. Notably, under our experimental setup, compared with training a diffusion model from scratch, evaluating with TED-6K is about 750times faster. Second, guided by this validated framework, we develop a superior text encoder using a novel two-stage training paradigm. This process involves an initial fine-tuning stage on a Multimodal Large Language Model for better visual representation, followed by a layer-wise weighting method to extract more nuanced and potent text features. Our experiments show that the resulting GRAN-TED encoder not only achieves state-of-the-art performance on TED-6K but also leads to demonstrable performance gains in text-to-image and text-to-video generation. Our TED-6K dataset and evaluation code are available at the following link: https://anonymous.4open.science/r/GRAN-TED-4FCC/.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.18619</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.15560</guid>
|
||||||
<pubDate>Mon, 16 Dec 2024 05:02:25 +0000</pubDate>
|
<pubDate>Wed, 17 Dec 2025 16:09:43 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images</title>
|
<title>Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding</title>
|
||||||
<link>https://arxiv.org/abs/2412.17606</link>
|
<link>https://arxiv.org/abs/2512.17220</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.17606.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Risa Shinoda, Kuniaki Saito, Shohei Tanaka, Tosho Hirasawa, Yoshitaka Ushiku</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Building a large-scale figure QA dataset requires a considerable amount of work, from gathering and selecting figures to extracting attributes like text, numbers, and colors, and generating QAs. Although recent developments in LLMs have led to efforts to synthesize figures, most of these focus primarily on QA generation. Additionally, creating figures directly using LLMs often encounters issues such as code errors, similar-looking figures, and repetitive content in figures. To address this issue, we present SBSFigures (Stage-by-Stage Synthetic Figures), a dataset for pre-training figure QA. Our proposed pipeline enables the creation of chart figures with complete annotations of the visualized data and dense QA annotations without any manual annotation process. Our stage-by-stage pipeline makes it possible to create diverse topic and appearance figures efficiently while minimizing code errors. Our SBSFigures demonstrate a strong pre-training effect, making it possible to achieve efficient training with a limited amount of real-world chart data starting from our pre-trained weights.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqing Li, Jiangnan Li, Zheng Lin, Ziyan Zhou, Junjie Wu, Weiping Wang, Jie Zhou, Mo Yu</p><p><b>Upvotes:</b> 105</p><p><b>Summary:</b> Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first approach that equips LLM-based RAG systems with explicit global context awareness. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.17606</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.17220</guid>
|
||||||
<pubDate>Mon, 23 Dec 2024 14:25:33 +0000</pubDate>
|
<pubDate>Fri, 19 Dec 2025 04:08:29 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>The Superposition of Diffusion Models Using the Itô Density Estimator</title>
|
<title>InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion</title>
|
||||||
<link>https://arxiv.org/abs/2412.17762</link>
|
<link>https://arxiv.org/abs/2512.17504</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.17762.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Marta Skreta, Lazar Atanackovic, Avishek Joey Bose, Alexander Tong, Kirill Neklyudov</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant computational burden of re-training a larger combined model. In this paper, we cast the problem of combining multiple pre-trained diffusion models at the generation stage under a novel proposed framework termed superposition. Theoretically, we derive superposition from rigorous first principles stemming from the celebrated continuity equation and design two novel algorithms tailor-made for combining diffusion models in SuperDiff. SuperDiff leverages a new scalable It\^o density estimator for the log likelihood of the diffusion SDE which incurs no additional overhead compared to the well-known Hutchinson's estimator needed for divergence calculations. We demonstrate that SuperDiff is scalable to large pre-trained diffusion models as superposition is performed solely through composition during inference, and also enjoys painless implementation as it combines different pre-trained vector fields through an automated re-weighting scheme. Notably, we show that SuperDiff is efficient during inference time, and mimics traditional composition operators such as the logical OR and the logical AND. We empirically demonstrate the utility of using SuperDiff for generating more diverse images on CIFAR-10, more faithful prompt conditioned image editing using Stable Diffusion, and improved unconditional de novo structure design of proteins. https://github.com/necludov/super-diffusion</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.17504.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hoiyeong Jin, Hyojin Jang, Jeongho Kim, Junha Hyung, Kinam Kim, Dongjin Kim, Huijin Choi, Hyeonji Kim, Jaegul Choo</p><p><b>Upvotes:</b> 95</p><p><b>Summary:</b> Recent advances in diffusion-based video generation have opened new possibilities for controllable video editing, yet realistic video object insertion (VOI) remains challenging due to limited 4D scene understanding and inadequate handling of occlusion and lighting effects. We present InsertAnywhere, a new VOI framework that achieves geometrically consistent object placement and appearance-faithful video synthesis. Our method begins with a 4D aware mask generation module that reconstructs the scene geometry and propagates user specified object placement across frames while maintaining temporal coherence and occlusion consistency. Building upon this spatial foundation, we extend a diffusion based video generation model to jointly synthesize the inserted object and its surrounding local variations such as illumination and shading. To enable supervised training, we introduce ROSE++, an illumination aware synthetic dataset constructed by transforming the ROSE object removal dataset into triplets of object removed video, object present video, and a VLM generated reference image. Through extensive experiments, we demonstrate that our framework produces geometrically plausible and visually coherent object insertions across diverse real world scenarios, significantly outperforming existing research and commercial models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.17762</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.17504</guid>
|
||||||
<pubDate>Mon, 23 Dec 2024 18:18:07 +0000</pubDate>
|
<pubDate>Fri, 19 Dec 2025 12:14:36 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization</title>
|
<title>InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search</title>
|
||||||
<link>https://arxiv.org/abs/2412.18525</link>
|
<link>https://arxiv.org/abs/2512.18745</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.18525.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Shen, Xiu-Shen Wei, Yifan Sun, Yuxin Song, Tao Yuan, Jian Jin, Heyang Xu, Yazhou Yao, Errui Ding</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Computer Vision (CV) has yet to fully achieve the zero-shot task generalization observed in Natural Language Processing (NLP), despite following many of the milestones established in NLP, such as large transformer models, extensive pre-training, and the auto-regression paradigm, among others. In this paper, we explore the idea that CV adopts discrete and terminological task definitions (\eg, ``image segmentation''), which may be a key barrier to zero-shot task generalization. Our hypothesis is that without truly understanding previously-seen tasks--due to these terminological definitions--deep models struggle to generalize to novel tasks. To verify this, we introduce Explanatory Instructions, which provide an intuitive way to define CV task objectives through detailed linguistic transformations from input images to outputs. We create a large-scale dataset comprising 12 million ``image input to explanatory instruction to output'' triplets, and train an auto-regressive-based vision-language model (AR-based VLM) that takes both images and explanatory instructions as input. By learning to follow these instructions, the AR-based VLM achieves instruction-level zero-shot capabilities for previously-seen tasks and demonstrates strong zero-shot generalization for unseen CV tasks. Code and dataset will be openly available on our GitHub repository.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.18745.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaican Li, Lewei Yao, Jiannan Wu, Tiezheng Yu, Jierun Chen, Haoli Bai, Lu Hou, Lanqing Hong, Wei Zhang, Nevin L. Zhang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> The ability for AI agents to "think with images" requires a sophisticated blend of reasoning and perception. However, current open multimodal agents still largely fall short on the reasoning aspect crucial for real-world tasks like analyzing documents with dense charts/diagrams and navigating maps. To address this gap, we introduce O3-Bench, a new benchmark designed to evaluate multimodal reasoning with interleaved attention to visual details. O3-Bench features challenging problems that require agents to piece together subtle visual information from distinct image areas through multi-step reasoning. The problems are highly challenging even for frontier systems like OpenAI o3, which only obtains 40.8% accuracy on O3-Bench. To make progress, we propose InSight-o3, a multi-agent framework consisting of a visual reasoning agent (vReasoner) and a visual search agent (vSearcher) for which we introduce the task of generalized visual search -- locating relational, fuzzy, or conceptual regions described in free-form language, beyond just simple objects or figures in natural images. We then present a multimodal LLM purpose-trained for this task via reinforcement learning. As a plug-and-play agent, our vSearcher empowers frontier multimodal models (as vReasoners), significantly improving their performance on a wide range of benchmarks. This marks a concrete step towards powerful o3-like open systems. Our code and dataset can be found at https://github.com/m-Just/InSight-o3 .</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.18525</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.18745</guid>
|
||||||
<pubDate>Tue, 24 Dec 2024 16:08:25 +0000</pubDate>
|
<pubDate>Sun, 21 Dec 2025 14:23:07 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models</title>
|
<title>CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks</title>
|
||||||
<link>https://arxiv.org/abs/2412.18605</link>
|
<link>https://arxiv.org/abs/2512.22206</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.18605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zehan Wang, Ziang Zhang, Tianyu Pang, Chao Du, Hengshuang Zhao, Zhou Zhao</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Orientation is a key attribute of objects, crucial for understanding their spatial pose and arrangement in images. However, practical solutions for accurate orientation estimation from a single image remain underexplored. In this work, we introduce Orient Anything, the first expert and foundational model designed to estimate object orientation in a single- and free-view image. Due to the scarcity of labeled data, we propose extracting knowledge from the 3D world. By developing a pipeline to annotate the front face of 3D objects and render images from random views, we collect 2M images with precise orientation annotations. To fully leverage the dataset, we design a robust training objective that models the 3D orientation as probability distributions of three angles and predicts the object orientation by fitting these distributions. Besides, we employ several strategies to improve synthetic-to-real transfer. Our model achieves state-of-the-art orientation estimation accuracy in both rendered and real images and exhibits impressive zero-shot ability in various scenarios. More importantly, our model enhances many applications, such as comprehension and generation of complex spatial concepts and 3D object pose adjustment.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22206.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yogeswar Reddy Thota</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Modern deep residual networks perform substantial redundant computation by evaluating all residual blocks for every input, even when identity mappings suffice. We introduce CosineGate, an end-to-end differentiable architecture for dynamic routing in residual networks that uses cosine incompatibility between identity and residual feature representations as a self-supervised skip signal. CosineGate measures semantic redundancy through the Cosine Incompatibility Ratio (CIR), defined as 1 - cos(x, F(x)), and uses Gumbel-Softmax relaxation to enable per-sample, per-block gating during training. A progressive FLOPs regularization term controls average compute usage without destabilizing optimization. On CIFAR-10, CosineGate spans the accuracy-efficiency Pareto frontier: an aggressive configuration achieves 89.9 percent accuracy with 24.1 percent FLOPs savings, a balanced configuration achieves 91.3 percent accuracy with 28.5 percent savings at epoch 160, and a conservative configuration reaches a peak of 93.2 percent accuracy with minimal compute reduction. These results match or exceed ResNet-20 (91.3 percent) while reducing computation, without auxiliary supervision, distillation, or task-specific heuristics. Our results demonstrate that simple geometric measures of feature incompatibility provide a principled and effective signal for dynamic residual routing.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.18605</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22206</guid>
|
||||||
<pubDate>Tue, 24 Dec 2024 18:58:43 +0000</pubDate>
|
<pubDate>Sun, 21 Dec 2025 18:26:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>1.58-bit FLUX</title>
|
<title>DiRL: An Efficient Post-Training Framework for Diffusion Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2412.18653</link>
|
<link>https://arxiv.org/abs/2512.22234</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.18653.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenglin Yang, Celong Liu, Xueqing Deng, Dongwon Kim, Xing Mei, Xiaohui Shen, Liang-Chieh Chen</p><p><b>Upvotes:</b> 85</p><p><b>Summary:</b> We present 1.58-bit FLUX, the first successful approach to quantizing the state-of-the-art text-to-image generation model, FLUX.1-dev, using 1.58-bit weights (i.e., values in {-1, 0, +1}) while maintaining comparable performance for generating 1024 x 1024 images. Notably, our quantization method operates without access to image data, relying solely on self-supervision from the FLUX.1-dev model. Additionally, we develop a custom kernel optimized for 1.58-bit operations, achieving a 7.7x reduction in model storage, a 5.1x reduction in inference memory, and improved inference latency. Extensive evaluations on the GenEval and T2I Compbench benchmarks demonstrate the effectiveness of 1.58-bit FLUX in maintaining generation quality while significantly enhancing computational efficiency.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22234.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ying Zhu, Jiaxin Wan, Xiaoran Liu, Siyanag He, Qiqi Wang, Xu Guo, Tianyi Liang, Zengfeng Huang, Ziwei He, Xipeng Qiu</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accelerated inference speeds, the post-training landscape for dLLMs remains underdeveloped. Existing methods suffer from computational inefficiency and objective mismatches between training and inference, severely limiting performance on complex reasoning tasks such as mathematics. To address this, we introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference. This architecture enables a streamlined online model update loop, facilitating efficient two-stage post-training (Supervised Fine-Tuning followed by Reinforcement Learning). Building on this framework, we propose DiPO, the first unbiased Group Relative Policy Optimization (GRPO) implementation tailored for dLLMs. We validate our approach by training DiRL-8B-Instruct on high-quality math data. Our model achieves state-of-the-art math performance among dLLMs and surpasses comparable models in the Qwen2.5 series on several benchmarks.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.18653</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22234</guid>
|
||||||
<pubDate>Tue, 24 Dec 2024 19:00:02 +0000</pubDate>
|
<pubDate>Tue, 23 Dec 2025 08:33:19 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era</title>
|
<title>SlideTailor: Personalized Presentation Slide Generation for Scientific Papers</title>
|
||||||
<link>https://arxiv.org/abs/2412.18702</link>
|
<link>https://arxiv.org/abs/2512.20292</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.18702.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanlin Feng, Simone Papicchio, Sajjadur Rahman</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Retrieval from graph data is crucial for augmenting large language models (LLM) with both open-domain knowledge and private enterprise data, and it is also a key component in the recent GraphRAG system (edge et al., 2024). Despite decades of research on knowledge graphs and knowledge base question answering, leading LLM frameworks (e.g. Langchain and LlamaIndex) have only minimal support for retrieval from modern encyclopedic knowledge graphs like Wikidata. In this paper, we analyze the root cause and suggest that modern RDF knowledge graphs (e.g. Wikidata, Freebase) are less efficient for LLMs due to overly large schemas that far exceed the typical LLM context window, use of resource identifiers, overlapping relation types and lack of normalization. As a solution, we propose property graph views on top of the underlying RDF graph that can be efficiently queried by LLMs using Cypher. We instantiated this idea on Wikidata and introduced CypherBench, the first benchmark with 11 large-scale, multi-domain property graphs with 7.8 million entities and over 10,000 questions. To achieve this, we tackled several key challenges, including developing an RDF-to-property graph conversion engine, creating a systematic pipeline for text-to-Cypher task generation, and designing new evaluation metrics.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.20292.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenzheng Zeng, Mingyu Ouyang, Langyuan Cui, Hwee Tou Ng</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Automatic presentation slide generation can greatly streamline content creation. However, since preferences of each user may vary, existing under-specified formulations often lead to suboptimal results that fail to align with individual user needs. We introduce a novel task that conditions paper-to-slides generation on user-specified preferences. We propose a human behavior-inspired agentic framework, SlideTailor, that progressively generates editable slides in a user-aligned manner. Instead of requiring users to write their preferences in detailed textual form, our system only asks for a paper-slides example pair and a visual template - natural and easy-to-provide artifacts that implicitly encode rich user preferences across content and visual style. Despite the implicit and unlabeled nature of these inputs, our framework effectively distills and generalizes the preferences to guide customized slide generation. We also introduce a novel chain-of-speech mechanism to align slide content with planned oral narration. Such a design significantly enhances the quality of generated slides and enables downstream applications like video presentations. To support this new task, we construct a benchmark dataset that captures diverse user preferences, with carefully designed interpretable metrics for robust evaluation. Extensive experiments demonstrate the effectiveness of our framework.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.18702</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.20292</guid>
|
||||||
<pubDate>Tue, 24 Dec 2024 23:22:04 +0000</pubDate>
|
<pubDate>Tue, 23 Dec 2025 12:01:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs</title>
|
<title>Masking Teacher and Reinforcing Student for Distilling Vision-Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2412.18925</link>
|
<link>https://arxiv.org/abs/2512.22238</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.18925.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, Benyou Wang</p><p><b>Upvotes:</b> 103</p><p><b>Summary:</b> The breakthrough of OpenAI o1 highlights the potential of enhancing reasoning to improve LLM. Yet, most research in reasoning has focused on mathematical tasks, leaving domains like medicine underexplored. The medical domain, though distinct from mathematics, also demands robust reasoning to provide reliable answers, given the high standards of healthcare. However, verifying medical reasoning is challenging, unlike those in mathematics. To address this, we propose verifiable medical problems with a medical verifier to check the correctness of model outputs. This verifiable nature enables advancements in medical reasoning through a two-stage approach: (1) using the verifier to guide the search for a complex reasoning trajectory for fine-tuning LLMs, (2) applying reinforcement learning (RL) with verifier-based rewards to enhance complex reasoning further. Finally, we introduce HuatuoGPT-o1, a medical LLM capable of complex reasoning, which outperforms general and medical-specific baselines using only 40K verifiable problems. Experiments show complex reasoning improves medical problem-solving and benefits more from RL. We hope our approach inspires advancements in reasoning across medical and other specialized domains.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22238.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Byung-Kwan Lee, Yu-Chiang Frank Wang, Ryo Hachiuma</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Large-scale vision-language models (VLMs) have recently achieved remarkable multimodal understanding, but their massive size makes them impractical for deployment on mobile or edge devices. This raises the need for compact yet capable VLMs that can efficiently learn from powerful large teachers. However, distilling knowledge from a large teacher to a small student remains challenging due to their large size gap: the student often fails to reproduce the teacher's complex, high-dimensional representations, leading to unstable learning and degraded performance. To address this, we propose Masters (Masking Teacher and Reinforcing Student), a mask-progressive reinforcement learning (RL) distillation framework. Masters first masks non-dominant weights of the teacher to reduce unnecessary complexity, then progressively restores the teacher by gradually increasing its capacity during training. This strategy allows the student to learn richer representations from the teacher in a smooth and stable manner. To further refine knowledge transfer, Masters integrates an offline RL stage with two complementary rewards: an accuracy reward that measures the correctness of the generated responses, and a distillation reward that quantifies the ease of transferring responses from teacher to student. Unlike online think-answer RL paradigms that are computationally expensive and generate lengthy responses, our offline RL leverages pre-generated responses from masked teachers. These provide rich yet efficient guidance, enabling students to achieve strong performance without requiring the think-answer process.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.18925</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22238</guid>
|
||||||
<pubDate>Wed, 25 Dec 2024 15:12:34 +0000</pubDate>
|
<pubDate>Tue, 23 Dec 2025 14:40:38 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment</title>
|
<title>Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting</title>
|
||||||
<link>https://arxiv.org/abs/2412.19326</link>
|
<link>https://arxiv.org/abs/2512.20927</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.19326.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziang Yan, Zhilin Li, Yinan He, Chenting Wang, Kunchang Li, Xinhao Li, Xiangyu Zeng, Zilei Wang, Yali Wang, Yu Qiao, Limin Wang, Yi Wang</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals though they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop tool-using or unify specific visual tasks into the autoregressive framework, often at the expense of overall multimodal performance. To address this issue and enhance MLLMs with visual tasks in a scalable fashion, we propose Task Preference Optimization (TPO), a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks. TPO introduces learnable task tokens that establish connections between multiple task-specific heads and the MLLM. By leveraging rich visual labels during training, TPO significantly enhances the MLLM's multimodal capabilities and task-specific performance. Through multi-task co-training within TPO, we observe synergistic benefits that elevate individual task performance beyond what is achievable through single-task training methodologies. Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models. Additionally, MLLM-TPO demonstrates robust zero-shot capabilities across various tasks, performing comparably to state-of-the-art supervised models. The code will be released at https://github.com/OpenGVLab/TPO</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.20927.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoonwoo Jeong, Cheng Sun, Frank Wang, Minsu Cho, Jaesung Choe</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Recent advancements in computer vision have successfully extended Open-vocabulary segmentation (OVS) to the 3D domain by leveraging 3D Gaussian Splatting (3D-GS). Despite this progress, efficiently rendering the high-dimensional features required for open-vocabulary queries poses a significant challenge. Existing methods employ codebooks or feature compression, causing information loss, thereby degrading segmentation quality. To address this limitation, we introduce Quantile Rendering (Q-Render), a novel rendering strategy for 3D Gaussians that efficiently handles high-dimensional features while maintaining high fidelity. Unlike conventional volume rendering, which densely samples all 3D Gaussians intersecting each ray, Q-Render sparsely samples only those with dominant influence along the ray. By integrating Q-Render into a generalizable 3D neural network, we also propose Gaussian Splatting Network (GS-Net), which predicts Gaussian features in a generalizable manner. Extensive experiments on ScanNet and LeRF demonstrate that our framework outperforms state-of-the-art methods, while enabling real-time rendering with an approximate ~43.7x speedup on 512-D feature maps. Code will be made publicly available.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.19326</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.20927</guid>
|
||||||
<pubDate>Thu, 26 Dec 2024 18:56:05 +0000</pubDate>
|
<pubDate>Wed, 24 Dec 2025 04:16:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging</title>
|
<title>GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2412.19512</link>
|
<link>https://arxiv.org/abs/2512.21008</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.19512.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hua Farn, Hsuan Su, Shachi H Kumar, Saurav Sahay, Shang-Tse Chen, Hung-yi Lee</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Fine-tuning large language models (LLMs) for downstream tasks is a widely adopted approach, but it often leads to safety degradation in safety-aligned LLMs. Currently, many solutions address this issue by incorporating additional safety data, which can be impractical in many cases. In this paper, we address the question: How can we improve downstream task performance while preserving safety in LLMs without relying on additional safety data? We propose a simple and effective method that maintains the inherent safety of LLMs while enhancing their downstream task performance: merging the weights of pre- and post-fine-tuned safety-aligned models. Experimental results across various downstream tasks, models, and merging methods demonstrate that this approach effectively mitigates safety degradation while improving downstream task performance, offering a practical solution for adapting safety-aligned LLMs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lichao Wu, Sasha Behrouzi, Mohamadreza Rostami, Stjepan Picek, Ahmad-Reza Sadeghi</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Mixture-of-Experts (MoE) architectures have advanced the scaling of Large Language Models (LLMs) by activating only a sparse subset of parameters per input, enabling state-of-the-art performance with reduced computational cost. As these models are increasingly deployed in critical domains, understanding and strengthening their alignment mechanisms is essential to prevent harmful outputs. However, existing LLM safety research has focused almost exclusively on dense architectures, leaving the unique safety properties of MoEs largely unexamined. The modular, sparsely-activated design of MoEs suggests that safety mechanisms may operate differently than in dense models, raising questions about their robustness. In this paper, we present GateBreaker, the first training-free, lightweight, and architecture-agnostic attack framework that compromises the safety alignment of modern MoE LLMs at inference time. GateBreaker operates in three stages: (i) gate-level profiling, which identifies safety experts disproportionately routed on harmful inputs, (ii) expert-level localization, which localizes the safety structure within safety experts, and (iii) targeted safety removal, which disables the identified safety structure to compromise the safety alignment. Our study shows that MoE safety concentrates within a small subset of neurons coordinated by sparse routing. Selective disabling of these neurons, approximately 3% of neurons in the targeted expert layers, significantly increases the averaged attack success rate (ASR) from 7.4% to 64.9% against the eight latest aligned MoE LLMs with limited utility degradation. These safety neurons transfer across models within the same family, raising ASR from 17.9% to 67.7% with one-shot transfer attack. Furthermore, GateBreaker generalizes to five MoE vision language models (VLMs) with 60.9% ASR on unsafe image inputs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.19512</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21008</guid>
|
||||||
<pubDate>Fri, 27 Dec 2024 08:03:22 +0000</pubDate>
|
<pubDate>Wed, 24 Dec 2025 07:13:24 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Xmodel-2 Technical Report</title>
|
<title>Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks</title>
|
||||||
<link>https://arxiv.org/abs/2412.19638</link>
|
<link>https://arxiv.org/abs/2512.22255</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.19638.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wang Qun, Liu Yang, Lin Qingquan, Qu Zhijiu, Jiang Ling</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Xmodel-2 is a 1.2-billion-parameter large language model designed specifically for reasoning tasks. Its architecture enables different model scales to share a unified set of hyperparameters, allowing for extensive experimentation on smaller models and seamless transfer of optimal configurations to larger models. To maximize training efficiency and stability, Xmodel-2 employs the WSD learning rate scheduler from MiniCPM. Pretrained on 1.5 trillion tokens from diverse sources, Xmodel-2 achieves state-of-the-art performance in complex reasoning and agent-based tasks, while maintaining low training costs. These results highlight the potential of efficient model design and training strategies in advancing reasoning capabilities. Model checkpoints and code are publicly available on GitHub at https://github.com/XiaoduoAILab/Xmodel-2</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22255.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Abhranil Chandra, Ayush Agrawal, Arian Hosseini, Sebastian Fischmeister, Rishabh Agarwal, Navin Goyal, Aaron Courville</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect final answer. Our experiments show this approach can yield better performance on reasoning tasks than training on human-annotated datasets. We hypothesize that two key factors explain this phenomenon: first, the distribution of synthetic data is inherently closer to the language model's own distribution, making it more amenable to learning. Second, these `incorrect' traces are often only partially flawed and contain valid reasoning steps from which the model can learn. To further test the first hypothesis, we use a language model to paraphrase human-annotated traces -- shifting their distribution closer to the model's own distribution -- and show that this improves performance. For the second hypothesis, we introduce increasingly flawed CoT traces and study to what extent models are tolerant to these flaws. We demonstrate our findings across various reasoning domains like math, algorithmic reasoning and code generation using MATH, GSM8K, Countdown and MBPP datasets on various language models ranging from 1.5B to 9B across Qwen, Llama, and Gemma models. Our study shows that curating datasets that are closer to the model's distribution is a critical aspect to consider. We also show that a correct final answer is not always a reliable indicator of a faithful reasoning process.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.19638</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22255</guid>
|
||||||
<pubDate>Fri, 27 Dec 2024 13:32:10 +0000</pubDate>
|
<pubDate>Wed, 24 Dec 2025 07:35:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models</title>
|
<title>UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement</title>
|
||||||
<link>https://arxiv.org/abs/2412.19645</link>
|
<link>https://arxiv.org/abs/2512.21185</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.19645.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tao Wu, Yong Zhang, Xiaodong Cun, Zhongang Qi, Junfu Pu, Huanzhang Dou, Guangcong Zheng, Ying Shan, Xi Li</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Zero-shot customized video generation has gained significant attention due to its substantial application potential. Existing methods rely on additional models to extract and inject reference subject features, assuming that the Video Diffusion Model (VDM) alone is insufficient for zero-shot customized video generation. However, these methods often struggle to maintain consistent subject appearance due to suboptimal feature extraction and injection techniques. In this paper, we reveal that VDM inherently possesses the force to extract and inject subject features. Departing from previous heuristic approaches, we introduce a novel framework that leverages VDM's inherent force to enable high-quality zero-shot customized video generation. Specifically, for feature extraction, we directly input reference images into VDM and use its intrinsic feature extraction process, which not only provides fine-grained features but also significantly aligns with VDM's pre-trained knowledge. For feature injection, we devise an innovative bidirectional interaction between subject features and generated content through spatial self-attention within VDM, ensuring that VDM has better subject fidelity while maintaining the diversity of the generated video.Experiments on both customized human and object video generation validate the effectiveness of our framework.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21185.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tanghui Jia, Dongyu Yan, Dehao Hao, Yang Li, Kaiyi Zhang, Xianyi He, Lanjiong Li, Jinnan Chen, Lutao Jiang, Qishen Yin, Long Quan, Ying-Cong Chen, Li Yuan</p><p><b>Upvotes:</b> 25</p><p><b>Summary:</b> In this report, we introduce UltraShape 1.0, a scalable 3D diffusion framework for high-fidelity 3D geometry generation. The proposed approach adopts a two-stage generation pipeline: a coarse global structure is first synthesized and then refined to produce detailed, high-quality geometry. To support reliable 3D generation, we develop a comprehensive data processing pipeline that includes a novel watertight processing method and high-quality data filtering. This pipeline improves the geometric quality of publicly available 3D datasets by removing low-quality samples, filling holes, and thickening thin structures, while preserving fine-grained geometric details. To enable fine-grained geometry refinement, we decouple spatial localization from geometric detail synthesis in the diffusion process. We achieve this by performing voxel-based refinement at fixed spatial locations, where voxel queries derived from coarse geometry provide explicit positional anchors encoded via RoPE, allowing the diffusion model to focus on synthesizing local geometric details within a reduced, structured solution space. Our model is trained exclusively on publicly available 3D datasets, achieving strong geometric quality despite limited training resources. Extensive evaluations demonstrate that UltraShape 1.0 performs competitively with existing open-source methods in both data processing quality and geometry generation. All code and trained models will be released to support future research.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.19645</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21185</guid>
|
||||||
<pubDate>Fri, 27 Dec 2024 13:49:25 +0000</pubDate>
|
<pubDate>Wed, 24 Dec 2025 14:08:38 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>From Elements to Design: A Layered Approach for Automatic Graphic Design Composition</title>
|
<title>SVBench: Evaluation of Video Generation Models on Social Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2412.19712</link>
|
<link>https://arxiv.org/abs/2512.21507</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.19712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiawei Lin, Shizhao Sun, Danqing Huang, Ting Liu, Ji Li, Jiang Bian</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> In this work, we investigate automatic design composition from multimodal graphic elements. Although recent studies have developed various generative models for graphic design, they usually face the following limitations: they only focus on certain subtasks and are far from achieving the design composition task; they do not consider the hierarchical information of graphic designs during the generation process. To tackle these issues, we introduce the layered design principle into Large Multimodal Models (LMMs) and propose a novel approach, called LaDeCo, to accomplish this challenging task. Specifically, LaDeCo first performs layer planning for a given element set, dividing the input elements into different semantic layers according to their contents. Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context. With this insightful design, LaDeCo decomposes the difficult task into smaller manageable steps, making the generation process smoother and clearer. The experimental results demonstrate the effectiveness of LaDeCo in design composition. Furthermore, we show that LaDeCo enables some interesting applications in graphic design, such as resolution adjustment, element filling, design variation, etc. In addition, it even outperforms the specialized models in some design subtasks without any task-specific training.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21507.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenshuo Peng, Gongxuan Wang, Tianmeng Yang, Chuanhao Li, Xiaojie Xu, Hui He, Kaipeng Zhang</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Recent text-to-video generation models exhibit remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they remain fundamentally limited in their ability to generate socially coherent behavior. Unlike humans, who effortlessly infer intentions, beliefs, emotions, and social norms from brief visual cues, current models tend to render literal scenes without capturing the underlying causal or psychological logic. To systematically evaluate this gap, we introduce the first benchmark for social reasoning in video generation. Grounded in findings from developmental and social psychology, our benchmark organizes thirty classic social cognition paradigms into seven core dimensions, including mental-state inference, goal-directed action, joint attention, social coordination, prosocial behavior, social norms, and multi-agent strategy. To operationalize these paradigms, we develop a fully training-free agent-based pipeline that (i) distills the reasoning mechanism of each experiment, (ii) synthesizes diverse video-ready scenarios, (iii) enforces conceptual neutrality and difficulty control through cue-based critique, and (iv) evaluates generated videos using a high-capacity VLM judge across five interpretable dimensions of social reasoning. Using this framework, we conduct the first large-scale study across seven state-of-the-art video generation systems. Our results reveal substantial performance gaps: while modern models excel in surface-level plausibility, they systematically fail in intention recognition, belief reasoning, joint attention, and prosocial inference.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.19712</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21507</guid>
|
||||||
<pubDate>Fri, 27 Dec 2024 16:13:08 +0000</pubDate>
|
<pubDate>Thu, 25 Dec 2025 04:44:59 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis</title>
|
<title>Valori: A Deterministic Memory Substrate for AI Systems</title>
|
||||||
<link>https://arxiv.org/abs/2412.19723</link>
|
<link>https://arxiv.org/abs/2512.22280</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.19723.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu</p><p><b>Upvotes:</b> 87</p><p><b>Summary:</b> Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. Despite their utility in advancing digital automation, a critical bottleneck persists: collecting high-quality trajectory data for training. Common practices for collecting such data rely on human supervision or synthetic data generation through executing pre-defined tasks, which are either resource-intensive or unable to guarantee data quality. Moreover, these methods suffer from limited data diversity and significant gaps between synthetic data and real-world environments. To address these challenges, we propose OS-Genesis, a novel GUI data synthesis pipeline that reverses the conventional trajectory collection process. Instead of relying on pre-defined tasks, OS-Genesis enables agents first to perceive environments and perform step-wise interactions, then retrospectively derive high-quality tasks to enable trajectory-level exploration. A trajectory reward model is then employed to ensure the quality of the generated trajectories. We demonstrate that training GUI agents with OS-Genesis significantly improves their performance on highly challenging online benchmarks. In-depth analysis further validates OS-Genesis's efficiency and its superior data quality and diversity compared to existing synthesis methods. Our codes, data, and checkpoints are available at https://qiushisun.github.io/OS-Genesis-Home/{OS-Genesis Homepage}.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22280.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Varshith Gudur</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Modern AI systems rely on vector embeddings stored and searched using floating-point arithmetic. While effective for approximate similarity search, this design introduces fundamental non-determinism: identical models, inputs, and code can produce different memory states and retrieval results across hardware architectures (e.g., x86 vs. ARM). This prevents replayability and safe deployment, leading to silent data divergence that prevents post-hoc verification and compromises audit trails in regulated sectors. We present Valori, a deterministic AI memory substrate that replaces floating-point memory operations with fixed-point arithmetic (Q16.16) and models memory as a replayable state machine. Valori guarantees bit-identical memory states, snapshots, and search results across platforms. We demonstrate that non-determinism arises before indexing or retrieval and show how Valori enforces determinism at the memory boundary. Our results suggest that deterministic memory is a necessary primitive for trustworthy AI systems. The reference implementation is open-source and available at https://github.com/varshith-Git/Valori-Kernel (archived at https://zenodo.org/records/18022660).</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.19723</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22280</guid>
|
||||||
<pubDate>Fri, 27 Dec 2024 16:21:58 +0000</pubDate>
|
<pubDate>Thu, 25 Dec 2025 06:04:04 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System</title>
|
<title>Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards</title>
|
||||||
<link>https://arxiv.org/abs/2412.20005</link>
|
<link>https://arxiv.org/abs/2512.21625</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20005.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yujie Luo, Xiangyuan Ru, Kangwei Liu, Lin Yuan, Mengshu Sun, Ningyu Zhang, Lei Liang, Zhiqiang Zhang, Jun Zhou, Lanning Wei, Da Zheng, Haofen Wang, Huajun Chen</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We introduce OneKE, a dockerized schema-guided knowledge extraction system, which can extract knowledge from the Web and raw PDF Books, and support various domains (science, news, etc.). Specifically, we design OneKE with multiple agents and a configure knowledge base. Different agents perform their respective roles, enabling support for various extraction scenarios. The configure knowledge base facilitates schema configuration, error case debugging and correction, further improving the performance. Empirical evaluations on benchmark datasets demonstrate OneKE's efficacy, while case studies further elucidate its adaptability to diverse tasks across multiple domains, highlighting its potential for broad applications. We have open-sourced the Code at https://github.com/zjunlp/OneKE and released a Video at http://oneke.openkg.cn/demo.mp4.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21625.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xinyu Tang, Yuliang Zhan, Zhixun Li, Wayne Xin Zhao, Zhenduo Zhang, Zujie Wen, Zhiqiang Zhang, Jun Zhou</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large reasoning models (LRMs) are typically trained using reinforcement learning with verifiable reward (RLVR) to enhance their reasoning abilities. In this paradigm, policies are updated using both positive and negative self-generated rollouts, which correspond to distinct sample polarities. In this paper, we provide a systematic investigation into how these sample polarities affect RLVR training dynamics and behaviors. We find that positive samples sharpen existing correct reasoning patterns, while negative samples encourage exploration of new reasoning paths. We further explore how adjusting the advantage values of positive and negative samples at both the sample level and the token level affects RLVR training. Based on these insights, we propose an Adaptive and Asymmetric token-level Advantage shaping method for Policy Optimization, namely A3PO, that more precisely allocates advantage signals to key tokens across different polarities. Experiments across five reasoning benchmarks demonstrate the effectiveness of our approach.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20005</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21625</guid>
|
||||||
<pubDate>Sat, 28 Dec 2024 04:01:30 +0000</pubDate>
|
<pubDate>Thu, 25 Dec 2025 11:15:46 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>On the Compositional Generalization of Multimodal LLMs for Medical Imaging</title>
|
<title>Omni-Weather: Unified Multimodal Foundation Model for Weather Generation and Understanding</title>
|
||||||
<link>https://arxiv.org/abs/2412.20070</link>
|
<link>https://arxiv.org/abs/2512.21643</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20070.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenyang Cai, Junying Chen, Rongsheng Wang, Weihong Wang, Yonglin Deng, Dingjie Song, Yize Chen, Zixu Zhang, Benyou Wang</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Multimodal large language models (MLLMs) hold significant potential in the medical field, but their capabilities are often limited by insufficient data in certain medical domains, highlighting the need for understanding what kinds of images can be used by MLLMs for generalization. Current research suggests that multi-task training outperforms single-task as different tasks can benefit each other, but they often overlook the internal relationships within these tasks, providing limited guidance on selecting datasets to enhance specific tasks. To analyze this phenomenon, we attempted to employ compositional generalization (CG)-the ability of models to understand novel combinations by recombining learned elements-as a guiding framework. Since medical images can be precisely defined by Modality, Anatomical area, and Task, naturally providing an environment for exploring CG. Therefore, we assembled 106 medical datasets to create Med-MAT for comprehensive experiments. The experiments confirmed that MLLMs can use CG to understand unseen medical images and identified CG as one of the main drivers of the generalization observed in multi-task training. Additionally, further studies demonstrated that CG effectively supports datasets with limited data and delivers consistent performance across different backbones, highlighting its versatility and broad applicability. Med-MAT is publicly available at https://github.com/FreedomIntelligence/Med-MAT.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21643.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiwang Zhou, Yuandong Pu, Xuming He, Yidi Liu, Yixin Chen, Junchao Gong, Xiang Zhuang, Wanghan Xu, Qinglong Cao, Shixiang Tang, Yihao Liu, Wenlong Zhang, Lei Bai</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a single architecture. Omni-Weather integrates a radar encoder for weather generation tasks, followed by unified processing using a shared self-attention mechanism. Moreover, we construct a Chain-of-Thought dataset for causal reasoning in weather generation, enabling interpretable outputs and improved perceptual quality. Extensive experiments show Omni-Weather achieves state-of-the-art performance in both weather generation and understanding. Our findings further indicate that generative and understanding tasks in the weather domain can mutually enhance each other. Omni-Weather also demonstrates the feasibility and value of unifying weather generation and understanding.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20070</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21643</guid>
|
||||||
<pubDate>Sat, 28 Dec 2024 07:50:00 +0000</pubDate>
|
<pubDate>Thu, 25 Dec 2025 12:08:09 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Bringing Objects to Life: 4D generation from 3D objects</title>
|
<title>UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture</title>
|
||||||
<link>https://arxiv.org/abs/2412.20422</link>
|
<link>https://arxiv.org/abs/2512.21675</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20422.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ohad Rahamim, Ori Malca, Dvir Samuel, Gal Chechik</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Recent advancements in generative modeling now enable the creation of 4D content (moving 3D objects) controlled with text prompts. 4D generation has large potential in applications like virtual worlds, media, and gaming, but existing methods provide limited control over the appearance and geometry of generated content. In this work, we introduce a method for animating user-provided 3D objects by conditioning on textual prompts to guide 4D generation, enabling custom animations while maintaining the identity of the original object. We first convert a 3D mesh into a ``static" 4D Neural Radiance Field (NeRF) that preserves the visual attributes of the input object. Then, we animate the object using an Image-to-Video diffusion model driven by text. To improve motion realism, we introduce an incremental viewpoint selection protocol for sampling perspectives to promote lifelike movement and a masked Score Distillation Sampling (SDS) loss, which leverages attention maps to focus optimization on relevant regions. We evaluate our model in terms of temporal coherence, prompt adherence, and visual fidelity and find that our method outperforms baselines that are based on other approaches, achieving up to threefold improvements in identity preservation measured using LPIPS scores, and effectively balancing visual quality with dynamic content.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21675.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo Cao, Jiayang Li, Xiaohui Li, Yuandong Pu, Kaiwen Zhu, Yuanting Gao, Siqi Luo, Yi Xin, Qi Qin, Yu Zhou, Xiangyu Chen, Wenlong Zhang, Bin Fu, Yu Qiao, Yihao Liu</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their ability to perceive perceptual-level image features remains limited. In this work, we present UniPercept-Bench, a unified framework for perceptual-level image understanding across three key domains: Aesthetics, Quality, Structure and Texture. We establish a hierarchical definition system and construct large-scale datasets to evaluate perceptual-level image understanding. Based on this foundation, we develop a strong baseline UniPercept trained via Domain-Adaptive Pre-Training and Task-Aligned RL, enabling robust generalization across both Visual Rating (VR) and Visual Question Answering (VQA) tasks. UniPercept outperforms existing MLLMs on perceptual-level image understanding and can serve as a plug-and-play reward model for text-to-image generation. This work defines Perceptual-Level Image Understanding in the era of MLLMs and, through the introduction of a comprehensive benchmark together with a strong baseline, provides a solid foundation for advancing perceptual-level multimodal image understanding.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20422</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21675</guid>
|
||||||
<pubDate>Sun, 29 Dec 2024 10:12:01 +0000</pubDate>
|
<pubDate>Thu, 25 Dec 2025 13:35:52 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Slow Perception: Let's Perceive Geometric Figures Step-by-step</title>
|
<title>An Information Theoretic Perspective on Agentic System Design</title>
|
||||||
<link>https://arxiv.org/abs/2412.20631</link>
|
<link>https://arxiv.org/abs/2512.21720</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20631.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoran Wei, Youyang Yin, Yumeng Li, Jia Wang, Liang Zhao, Jianjian Sun, Zheng Ge, Xiangyu Zhang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Recently, "visual o1" began to enter people's vision, with expectations that this slow-thinking design can solve visual reasoning tasks, especially geometric math problems. However, the reality is that current LVLMs (Large Vision Language Models) can hardly even accurately copy a geometric figure, let alone truly understand the complex inherent logic and spatial relationships within geometric shapes. We believe accurate copying (strong perception) is the first step to visual o1. Accordingly, we introduce the concept of "slow perception" (SP), which guides the model to gradually perceive basic point-line combinations, as our humans, reconstruct complex geometric structures progressively. There are two-fold stages in SP: a) perception decomposition. Perception is not instantaneous. In this stage, complex geometric figures are broken down into basic simple units to unify geometry representation. b) perception flow, which acknowledges that accurately tracing a line is not an easy task. This stage aims to avoid "long visual jumps" in regressing line segments by using a proposed "perceptual ruler" to trace each line stroke-by-stroke. Surprisingly, such a human-like perception manner enjoys an inference time scaling law -- the slower, the better. Researchers strive to speed up the model's perception in the past, but we slow it down again, allowing the model to read the image step-by-step and carefully.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21720.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shizhe He, Avanika Narayan, Ishan S. Khare, Scott W. Linderman, Christopher Ré, Dan Biderman</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath their apparent diversity lies a recurring pattern: smaller "compressor" LMs (that can even run locally) distill raw context into compact text that is then consumed by larger "predictor" LMs. Despite their popularity, the design of compressor-predictor systems remains largely ad hoc, with little guidance on how compressor and predictor choices shape downstream performance. In practice, attributing gains to compression versus prediction requires costly, task-specific pairwise sweeps. We argue that these agentic system design questions are, at root, information-theoretic. Viewing the compressor LM as a noisy channel, we introduce a simple estimator of mutual information between the context and its compression to quantify compression quality in a task-independent way. We show that mutual information strongly predicts downstream performance, independent of any specific task. Through an information-theoretic framework, we perform a comprehensive empirical analysis across five datasets and three model families. Results reveal that larger compressors not only are more accurate, but also more token-efficient, conveying more bits of information per token. A 7B Qwen-2.5 compressor, for instance, is 1.6times more accurate, 4.6times more concise, and conveys 5.5times more bits of mutual information per token than its 1.5B sibling. Across datasets, scaling compressors is substantially more effective than scaling predictors, enabling larger on-device compressors to pair with smaller cloud predictors. Applied to a Deep Research system, these principles enable local compressors as small as 3B parameters to recover 99% of frontier-LM accuracy at 26% of API costs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20631</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21720</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 00:40:35 +0000</pubDate>
|
<pubDate>Thu, 25 Dec 2025 15:45:31 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving</title>
|
<title>Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation</title>
|
||||||
<link>https://arxiv.org/abs/2412.20735</link>
|
<link>https://arxiv.org/abs/2512.21734</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20735.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Li, Dong Du, Linfeng Song, Chen Li, Weikang Wang, Tao Yang, Haitao Mi</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We introduce HunyuanProver, an language model finetuned from the Hunyuan 7B for interactive automatic theorem proving with LEAN4. To alleviate the data sparsity issue, we design a scalable framework to iterative synthesize data with low cost. Besides, guided tree search algorithms are designed to enable effective ``system 2 thinking`` of the prover. HunyuanProver achieves state-of-the-art (SOTA) performances on major benchmarks. Specifically, it achieves a pass of 68.4% on the miniF2F-test compared to 65.9%, the current SOTA results. It proves 4 IMO statements (imo_1960_p2, imo_1962_p2}, imo_1964_p2 and imo_1983_p6) in miniF2F-test. To benefit the community, we will open-source a dataset of 30k synthesized instances, where each instance contains the original question in natural language, the converted statement by autoformalization, and the proof by HunyuanProver.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21734.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Steven Xiao, Xindi Zhang, Dechao Meng, Qi Wang, Peng Zhang, Bang Zhang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Real-time portrait animation is essential for interactive applications such as virtual assistants and live avatars, requiring high visual fidelity, temporal coherence, ultra-low latency, and responsive control from dynamic inputs like reference images and driving signals. While diffusion-based models achieve strong quality, their non-causal nature hinders streaming deployment. Causal autoregressive video generation approaches enable efficient frame-by-frame generation but suffer from error accumulation, motion discontinuities at chunk boundaries, and degraded long-term consistency. In this work, we present a novel streaming framework named Knot Forcing for real-time portrait animation that addresses these challenges through three key designs: (1) a chunk-wise generation strategy with global identity preservation via cached KV states of the reference image and local temporal modeling using sliding window attention; (2) a temporal knot module that overlaps adjacent chunks and propagates spatio-temporal cues via image-to-video conditioning to smooth inter-chunk motion transitions; and (3) A "running ahead" mechanism that dynamically updates the reference frame's temporal coordinate during inference, keeping its semantic context ahead of the current rollout frame to support long-term coherence. Knot Forcing enables high-fidelity, temporally consistent, and interactive portrait animation over infinite sequences, achieving real-time performance with strong visual stability on consumer-grade GPUs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20735</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21734</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 06:18:33 +0000</pubDate>
|
<pubDate>Thu, 25 Dec 2025 16:34:56 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Are Vision-Language Models Truly Understanding Multi-vision Sensor?</title>
|
<title>TimeBill: Time-Budgeted Inference for Large Language Models</title>
|
||||||
<link>https://arxiv.org/abs/2412.20750</link>
|
<link>https://arxiv.org/abs/2512.21859</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20750.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sangyun Chung, Youngjoon Yu, Youngchae Chee, Se Yeon Kim, Byung-Kwan Lee, Yong Man Ro</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Large-scale Vision-Language Models (VLMs) have advanced by aligning vision inputs with text, significantly improving performance in computer vision tasks. Moreover, for VLMs to be effectively utilized in real-world applications, an understanding of diverse multi-vision sensor data, such as thermal, depth, and X-ray information, is essential. However, we find that current VLMs process multi-vision sensor images without deep understanding of sensor information, disregarding each sensor's unique physical properties. This limitation restricts their capacity to interpret and respond to complex questions requiring multi-vision sensor reasoning. To address this, we propose a novel Multi-vision Sensor Perception and Reasoning (MS-PR) benchmark, assessing VLMs on their capacity for sensor-specific reasoning. Moreover, we introduce Diverse Negative Attributes (DNA) optimization to enable VLMs to perform deep reasoning on multi-vision sensor tasks, helping to bridge the core information gap between images and sensor data. Extensive experimental results validate that the proposed DNA method can significantly improve the multi-vision sensor reasoning for VLMs.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21859.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qi Fan, An Zou, Yehan Ma</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Large Language Models (LLMs) are increasingly deployed in time-critical systems, such as robotics, autonomous driving, embodied intelligence, and industrial automation, where generating accurate responses within a given time budget is crucial for decision-making, control, or safety-critical tasks. However, the auto-regressive generation process of LLMs makes it challenging to model and estimate the end-to-end execution time. Furthermore, existing efficient inference methods based on a fixed key-value (KV) cache eviction ratio struggle to adapt to varying tasks with diverse time budgets, where an improper eviction ratio may lead to incomplete inference or a drop in response performance. In this paper, we propose TimeBill, a novel time-budgeted inference framework for LLMs that balances the inference efficiency and response performance. To be more specific, we propose a fine-grained response length predictor (RLP) and an execution time estimator (ETE) to accurately predict the end-to-end execution time of LLMs. Following this, we develop a time-budgeted efficient inference approach that adaptively adjusts the KV cache eviction ratio based on execution time prediction and the given time budget. Finally, through extensive experiments, we demonstrate the advantages of TimeBill in improving task completion rate and maintaining response performance under various overrun strategies.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20750</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21859</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 06:44:25 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 04:49:35 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control</title>
|
<title>SWE-RM: Execution-free Feedback For Software Engineering Agents</title>
|
||||||
<link>https://arxiv.org/abs/2412.20800</link>
|
<link>https://arxiv.org/abs/2512.21919</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20800.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaojin Wu, Fei Ding, Mengqi Huang, Wei Liu, Qian He</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> While diffusion models show extraordinary talents in text-to-image generation, they may still fail to generate highly aesthetic images. More specifically, there is still a gap between the generated images and the real-world aesthetic images in finer-grained dimensions including color, lighting, composition, etc. In this paper, we propose Cross-Attention Value Mixing Control (VMix) Adapter, a plug-and-play aesthetics adapter, to upgrade the quality of generated images while maintaining generality across visual concepts by (1) disentangling the input text prompt into the content description and aesthetic description by the initialization of aesthetic embedding, and (2) integrating aesthetic conditions into the denoising process through value-mixed cross-attention, with the network connected by zero-initialized linear layers. Our key insight is to enhance the aesthetic presentation of existing diffusion models by designing a superior condition control method, all while preserving the image-text alignment. Through our meticulous design, VMix is flexible enough to be applied to community models for better visual performance without retraining. To validate the effectiveness of our method, we conducted extensive experiments, showing that VMix outperforms other state-of-the-art methods and is compatible with other community modules (e.g., LoRA, ControlNet, and IPAdapter) for image generation. The project page is https://vmix-diffusion.github.io/VMix/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21919.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> KaShun Shum, Binyuan Hui, Jiawei Chen, Lei Zhang, X. W., Jiaxi Yang, Yuzhen Huang, Junyang Lin, Junxian He</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to provide accurate feedback, and the resulting feedback is often sparse and cannot effectively distinguish between trajectories that are both successful or both unsuccessful. In contrast, execution-free feedback from reward models can provide more fine-grained signals without depending on unit test cases. Despite this potential, execution-free feedback for realistic software engineering (SWE) agents remains underexplored. Aiming to develop versatile reward models that are effective across TTS and RL, however, we observe that two verifiers with nearly identical TTS performance can nevertheless yield very different results in RL. Intuitively, TTS primarily reflects the model's ability to select the best trajectory, but this ability does not necessarily generalize to RL. To address this limitation, we identify two additional aspects that are crucial for RL training: classification accuracy and calibration. We then conduct comprehensive controlled experiments to investigate how to train a robust reward model that performs well across these metrics. In particular, we analyze the impact of various factors such as training data scale, policy mixtures, and data source composition. Guided by these investigations, we introduce SWE-RM, an accurate and robust reward model adopting a mixture-of-experts architecture with 30B total parameters and 3B activated during inference. SWE-RM substantially improves SWE agents on both TTS and RL performance. For example, it increases the accuracy of Qwen3-Coder-Flash from 51.6% to 62.0%, and Qwen3-Coder-Max from 67.0% to 74.6% on SWE-Bench Verified using TTS, achieving new state-of-the-art performance among open-source models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20800</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21919</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 08:47:25 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 08:26:18 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Efficiently Serving LLM Reasoning Programs with Certaindex</title>
|
<title>A 58-Addition, Rank-23 Scheme for General 3x3 Matrix Multiplication</title>
|
||||||
<link>https://arxiv.org/abs/2412.20993</link>
|
<link>https://arxiv.org/abs/2512.21980</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.20993.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yichao Fu, Junda Chen, Siqi Zhu, Zheyu Fu, Zhongdongming Dai, Aurick Qiao, Hao Zhang</p><p><b>Upvotes:</b> 36</p><p><b>Summary:</b> The rapid evolution of large language models (LLMs) has unlocked their capabilities in advanced reasoning tasks like mathematical problem-solving, code generation, and legal analysis. Central to this progress are inference-time reasoning algorithms, which refine outputs by exploring multiple solution paths, at the cost of increasing compute demands and response latencies. Existing serving systems fail to adapt to the scaling behaviors of these algorithms or the varying difficulty of queries, leading to inefficient resource use and unmet latency targets. We present Dynasor, a system that optimizes inference-time compute for LLM reasoning queries. Unlike traditional engines, Dynasor tracks and schedules requests within reasoning queries and uses Certaindex, a proxy that measures statistical reasoning progress based on model certainty, to guide compute allocation dynamically. Dynasor co-adapts scheduling with reasoning progress: it allocates more compute to hard queries, reduces compute for simpler ones, and terminates unpromising queries early, balancing accuracy, latency, and cost. On diverse datasets and algorithms, Dynasor reduces compute by up to 50% in batch processing and sustaining 3.3x higher query rates or 4.7x tighter latency SLOs in online serving.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.21980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> A. I. Perminov</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> This paper presents a new state-of-the-art algorithm for exact 3times3 matrix multiplication over general non-commutative rings, achieving a rank-23 scheme with only 58 scalar additions. This improves the previous best additive complexity of 60 additions without a change of basis. The result was discovered through an automated search combining ternary-restricted flip-graph exploration with greedy intersection reduction for common subexpression elimination. The resulting scheme uses only coefficients from {-1, 0, 1}, ensuring both efficiency and portability across arbitrary fields. The total scalar operation count is reduced from 83 to 81.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.20993</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.21980</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 14:57:53 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 10:58:54 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MapQaTor: A System for Efficient Annotation of Map Query Datasets</title>
|
<title>SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents</title>
|
||||||
<link>https://arxiv.org/abs/2412.21015</link>
|
<link>https://arxiv.org/abs/2512.22322</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21015.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mahir Labib Dihan, Mohammed Eunus Ali, Md Rizwan Parvez</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Mapping and navigation services like Google Maps, Apple Maps, Openstreet Maps, are essential for accessing various location-based data, yet they often struggle to handle natural language geospatial queries. Recent advancements in Large Language Models (LLMs) show promise in question answering (QA), but creating reliable geospatial QA datasets from map services remains challenging. We introduce MapQaTor, a web application that streamlines the creation of reproducible, traceable map-based QA datasets. With its plug-and-play architecture, MapQaTor enables seamless integration with any maps API, allowing users to gather and visualize data from diverse sources with minimal setup. By caching API responses, the platform ensures consistent ground truth, enhancing the reliability of the data even as real-world information evolves. MapQaTor centralizes data retrieval, annotation, and visualization within a single platform, offering a unique opportunity to evaluate the current state of LLM-based geospatial reasoning while advancing their capabilities for improved geospatial understanding. Evaluation metrics show that, MapQaTor speeds up the annotation process by at least 30 times compared to manual methods, underscoring its potential for developing geospatial resources, such as complex map reasoning datasets. The website is live at: https://mapqator.github.io/ and a demo video is available at: https://youtu.be/7_aV9Wmhs6Q.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22322.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaofei Cai, Yulei Qin, Haojia Lin, Zihan Xu, Gang Li, Yuchen Shi, Zongyi Li, Yong Mao, Siqi Cai, Xiaoyu Tan, Yitao Liang, Ke Li, Xing Sun</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verification of task completion. Existing task verification is treated as a passive, post-hoc process: a verifier (i.e., rule-based scoring script, reward or critic model, and LLM-as-a-Judge) analyzes the agent's entire interaction trajectory to determine if the agent succeeds. Such processing of verbose context that contains irrelevant, noisy history poses challenges to the verification protocols and therefore leads to prohibitive cost and low reliability. To overcome this bottleneck, we propose SmartSnap, a paradigm shift from this passive, post-hoc verification to proactive, in-situ self-verification by the agent itself. We introduce the Self-Verifying Agent, a new type of agent designed with dual missions: to not only complete a task but also to prove its accomplishment with curated snapshot evidences. Guided by our proposed 3C Principles (Completeness, Conciseness, and Creativity), the agent leverages its accessibility to the online environment to perform self-verification on a minimal, decisive set of snapshots. Such evidences are provided as the sole materials for a general LLM-as-a-Judge verifier to determine their validity and relevance. Experiments on mobile tasks across model families and scales demonstrate that our SmartSnap paradigm allows training LLM-driven agents in a scalable manner, bringing performance gains up to 26.08% and 16.66% respectively to 8B and 30B models. The synergizing between solution finding and evidence seeking facilitates the cultivation of efficient, self-verifying agents with competitive performance against DeepSeek V3.1 and Qwen3-235B-A22B.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21015</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22322</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 15:33:19 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 14:51:39 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization</title>
|
<title>MAI-UI Technical Report: Real-World Centric Foundation GUI Agents</title>
|
||||||
<link>https://arxiv.org/abs/2412.21037</link>
|
<link>https://arxiv.org/abs/2512.22047</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21037.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chia-Yu Hung, Navonil Majumder, Zhifeng Kong, Ambuj Mehrish, Rafael Valle, Bryan Catanzaro, Soujanya Poria</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> We introduce TangoFlux, an efficient Text-to-Audio (TTA) generative model with 515M parameters, capable of generating up to 30 seconds of 44.1kHz audio in just 3.7 seconds on a single A40 GPU. A key challenge in aligning TTA models lies in the difficulty of creating preference pairs, as TTA lacks structured mechanisms like verifiable rewards or gold-standard answers available for Large Language Models (LLMs). To address this, we propose CLAP-Ranked Preference Optimization (CRPO), a novel framework that iteratively generates and optimizes preference data to enhance TTA alignment. We demonstrate that the audio preference dataset generated using CRPO outperforms existing alternatives. With this framework, TangoFlux achieves state-of-the-art performance across both objective and subjective benchmarks. We open source all code and models to support further research in TTA generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22047.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hanzhang Zhou, Xu Zhang, Panrong Tong, Jianan Zhang, Liangyu Chen, Quyu Kong, Chenglin Cai, Chen Liu, Yue Wang, Jingren Zhou, Steven Hoi</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B, and 235B-A22B variants. We identify four key challenges to realistic deployment: the lack of native agent-user interaction, the limits of UI-only operation, the absence of a practical deployment architecture, and brittleness in dynamic environments. MAI-UI addresses these issues with a unified methodology: a self-evolving data pipeline that expands the navigation data to include user interaction and MCP tool calls, a native device-cloud collaboration system routes execution by task state, and an online RL framework with advanced optimizations to scale parallel environments and context length. MAI-UI establishes new state-of-the-art across GUI grounding and mobile navigation. On grounding benchmarks, it reaches 73.5% on ScreenSpot-Pro, 91.3% on MMBench GUI L2, 70.9% on OSWorld-G, and 49.2% on UI-Vision, surpassing Gemini-3-Pro and Seed1.8 on ScreenSpot-Pro. On mobile GUI navigation, it sets a new SOTA of 76.7% on AndroidWorld, surpassing UI-Tars-2, Gemini-2.5-Pro and Seed1.8. On MobileWorld, MAI-UI obtains 41.7% success rate, significantly outperforming end-to-end GUI models and competitive with Gemini-3-Pro based agentic frameworks. Our online RL experiments show significant gains from scaling parallel environments from 32 to 512 (+5.2 points) and increasing environment step budget from 15 to 50 (+4.3 points). Finally, the native device-cloud collaboration system improves on-device performance by 33%, reduces cloud model calls by over 40%, and preserves user privacy.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21037</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22047</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 16:02:44 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 14:51:52 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Edicho: Consistent Image Editing in the Wild</title>
|
<title>SpotEdit: Selective Region Editing in Diffusion Transformers</title>
|
||||||
<link>https://arxiv.org/abs/2412.21079</link>
|
<link>https://arxiv.org/abs/2512.22323</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21079.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyan Bai, Hao Ouyang, Yinghao Xu, Qiuyu Wang, Ceyuan Yang, Ka Leong Cheng, Yujun Shen, Qifeng Chen</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22323.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhibin Qin, Zhenxiong Tan, Zeqing Wang, Songhua Liu, Xinchao Wang</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Diffusion Transformer models have significantly advanced image editing by encoding conditional images and integrating them into transformer layers. However, most edits involve modifying only small regions, while current methods uniformly process and denoise all tokens at every timestep, causing redundant computation and potentially degrading unchanged areas. This raises a fundamental question: Is it truly necessary to regenerate every region during editing? To address this, we propose SpotEdit, a training-free diffusion editing framework that selectively updates only the modified regions. SpotEdit comprises two key components: SpotSelector identifies stable regions via perceptual similarity and skips their computation by reusing conditional image features; SpotFusion adaptively blends these features with edited tokens through a dynamic fusion mechanism, preserving contextual coherence and editing quality. By reducing unnecessary computation and maintaining high fidelity in unmodified areas, SpotEdit achieves efficient and precise image editing.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21079</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22323</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 16:56:44 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 14:59:41 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Training Software Engineering Agents and Verifiers with SWE-Gym</title>
|
<title>Yume-1.5: A Text-Controlled Interactive World Generation Model</title>
|
||||||
<link>https://arxiv.org/abs/2412.21139</link>
|
<link>https://arxiv.org/abs/2512.22096</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21139.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiayi Pan, Xingyao Wang, Graham Neubig, Navdeep Jaitly, Heng Ji, Alane Suhr, Yizhe Zhang</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> We present SWE-Gym, the first environment for training real-world software engineering (SWE) agents. SWE-Gym contains 2,438 real-world Python task instances, each comprising a codebase with an executable runtime environment, unit tests, and a task specified in natural language. We use SWE-Gym to train language model based SWE agents , achieving up to 19% absolute gains in resolve rate on the popular SWE-Bench Verified and Lite test sets. We also experiment with inference-time scaling through verifiers trained on agent trajectories sampled from SWE-Gym. When combined with our fine-tuned SWE agents, we achieve 32.0% and 26.0% on SWE-Bench Verified and Lite, respectively, reflecting a new state-of-the-art for open-weight SWE agents. To facilitate further research, we publicly release SWE-Gym, models, and agent trajectories.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22096.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaofeng Mao, Zhen Li, Chuanhao Li, Xiaojie Xu, Kaining Ying, Tong He, Jiangmiao Pang, Yu Qiao, Kaipeng Zhang</p><p><b>Upvotes:</b> 56</p><p><b>Summary:</b> Recent approaches have demonstrated the promise of using diffusion models to generate interactive and explorable worlds. However, most of these methods face critical challenges such as excessively large parameter sizes, reliance on lengthy inference steps, and rapidly growing historical context, which severely limit real-time performance and lack text-controlled generation capabilities. To address these challenges, we propose \method, a novel framework designed to generate realistic, interactive, and continuous worlds from a single image or text prompt. \method achieves this through a carefully designed framework that supports keyboard-based exploration of the generated worlds. The framework comprises three core components: (1) a long-video generation framework integrating unified context compression with linear attention; (2) a real-time streaming acceleration strategy powered by bidirectional attention distillation and an enhanced text embedding scheme; (3) a text-controlled method for generating world events. We have provided the codebase in the supplementary material.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21139</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22096</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 18:15:39 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 17:52:49 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Facilitating large language model Russian adaptation with Learned Embedding Propagation</title>
|
<title>Introducing TrGLUE and SentiTurca: A Comprehensive Benchmark for Turkish General Language Understanding and Sentiment Analysis</title>
|
||||||
<link>https://arxiv.org/abs/2412.21140</link>
|
<link>https://arxiv.org/abs/2512.22100</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21140.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mikhail Tikhomirov, Daniil Chernyshev</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Rapid advancements of large language model (LLM) technologies led to the introduction of powerful open-source instruction-tuned LLMs that have the same text generation quality as the state-of-the-art counterparts such as GPT-4. While the emergence of such models accelerates the adoption of LLM technologies in sensitive-information environments the authors of such models don not disclose the training data necessary for replication of the results thus making the achievements model-exclusive. Since those open-source models are also multilingual this in turn reduces the benefits of training a language specific LLMs as improved inference computation efficiency becomes the only guaranteed advantage of such costly procedure. More cost-efficient options such as vocabulary extension and subsequent continued pre-training are also inhibited by the lack of access to high-quality instruction-tuning data since it is the major factor behind the resulting LLM task-solving capabilities. To address the limitations and cut the costs of the language adaptation pipeline we propose Learned Embedding Propagation (LEP). Unlike existing approaches our method has lower training data size requirements due to minimal impact on existing LLM knowledge which we reinforce using novel ad-hoc embedding propagation procedure that allows to skip the instruction-tuning step and instead implant the new language knowledge directly into any existing instruct-tuned variant. We evaluated four Russian vocabulary adaptations for LLaMa-3-8B and Mistral-7B, showing that LEP is competitive with traditional instruction-tuning methods, achieving performance comparable to OpenChat 3.5 and LLaMa-3-8B-Instruct, with further improvements via self-calibration and continued tuning enhancing task-solving capabilities.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22100.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Duygu Altinok</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Evaluating the performance of various model architectures, such as transformers, large language models (LLMs), and other NLP systems, requires comprehensive benchmarks that measure performance across multiple dimensions. Among these, the evaluation of natural language understanding (NLU) is particularly critical as it serves as a fundamental criterion for assessing model capabilities. Thus, it is essential to establish benchmarks that enable thorough evaluation and analysis of NLU abilities from diverse perspectives. While the GLUE benchmark has set a standard for evaluating English NLU, similar benchmarks have been developed for other languages, such as CLUE for Chinese, FLUE for French, and JGLUE for Japanese. However, no comparable benchmark currently exists for the Turkish language. To address this gap, we introduce TrGLUE, a comprehensive benchmark encompassing a variety of NLU tasks for Turkish. In addition, we present SentiTurca, a specialized benchmark for sentiment analysis. To support researchers, we also provide fine-tuning and evaluation code for transformer-based models, facilitating the effective use of these benchmarks. TrGLUE comprises Turkish-native corpora curated to mirror the domains and task formulations of GLUE-style evaluations, with labels obtained through a semi-automated pipeline that combines strong LLM-based annotation, cross-model agreement checks, and subsequent human validation. This design prioritizes linguistic naturalness, minimizes direct translation artifacts, and yields a scalable, reproducible workflow. With TrGLUE, our goal is to establish a robust evaluation framework for Turkish NLU, empower researchers with valuable resources, and provide insights into generating high-quality semi-automated datasets.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21140</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22100</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 18:15:45 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 18:02:09 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs</title>
|
<title>ProEdit: Inversion-based Editing From Prompts Done Right</title>
|
||||||
<link>https://arxiv.org/abs/2412.21187</link>
|
<link>https://arxiv.org/abs/2512.22118</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21187.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended chain-of-thought (CoT) processes, exploring multiple strategies to enhance problem-solving capabilities. However, a critical question remains: How to intelligently and efficiently scale computational resources during testing. This paper presents the first comprehensive study on the prevalent issue of overthinking in these models, where excessive computational resources are allocated for simple problems with minimal benefit. We introduce novel efficiency metrics from both outcome and process perspectives to evaluate the rational use of computational resources by o1-like models. Using a self-training paradigm, we propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy. Experimental results show that our approach successfully reduces computational overhead while preserving model performance across a range of testsets with varying difficulty levels, such as GSM8K, MATH500, GPQA, and AIME.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22118.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhi Ouyang, Dian Zheng, Xiao-Ming Wu, Jian-Jian Jiang, Kun-Yu Lin, Jingke Meng, Wei-Shi Zheng</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Inversion-based visual editing provides an effective and training-free way to edit an image or a video based on user instructions. Existing methods typically inject source image information during the sampling process to maintain editing consistency. However, this sampling strategy overly relies on source information, which negatively affects the edits in the target image (e.g., failing to change the subject's atributes like pose, number, or color as instructed). In this work, we propose ProEdit to address this issue both in the attention and the latent aspects. In the attention aspect, we introduce KV-mix, which mixes KV features of the source and the target in the edited region, mitigating the influence of the source image on the editing region while maintaining background consistency. In the latent aspect, we propose Latents-Shift, which perturbs the edited region of the source latent, eliminating the influence of the inverted latent on the sampling. Extensive experiments on several image and video editing benchmarks demonstrate that our method achieves SOTA performance. In addition, our design is plug-and-play, which can be seamlessly integrated into existing inversion and editing methods, such as RF-Solver, FireFlow and UniEdit.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21187</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22118</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 18:55:12 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 18:59:14 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation</title>
|
<title>See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning</title>
|
||||||
<link>https://arxiv.org/abs/2412.21199</link>
|
<link>https://arxiv.org/abs/2512.22120</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21199.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhaojian Yu, Yilun Zhao, Arman Cohan, Xiao-Ping Zhang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They must solve the base problem and then utilize its solution to address the more complex one. This work features three key contributions. First, we propose a general recipe for generating more challenging versions of existing benchmarks, resulting in three new benchmarks: HumanEval Pro, MBPP Pro, and BigCodeBench-Lite Pro, specifically designed to assess LLMs on self-invoking code generation. Second, from the analysis of experimental results over twenty LLMs on our benchmarks, we have two important observations: (i) Most LLMs excel in traditional code generation benchmarks like HumanEval and MBPP, but their performance declines on self-invoking tasks. For example, o1-mini achieves 96.2% pass@1 on HumanEval but only 76.2% on HumanEval Pro. (ii) On self-invoking code generation task, the instruction-tuned models demonstrate only marginal improvements compared to the base models. Third, we disclose the types of failure modes that exist in our evaluation results. All these results underscore the need for further advancements in self-invoking code generation tasks and provide a new direction for future research on enhancing LLMs' code reasoning capabilities.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22120.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuoshuo Zhang, Yizhen Zhang, Jingjing Fu, Lei Song, Jiang Bian, Yujiu Yang, Rui Wang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Large vision-language models (VLMs) often benefit from intermediate visual cues, either injected via external tools or generated as latent visual tokens during reasoning, but these mechanisms still overlook fine-grained visual evidence (e.g., polylines in charts), generalize poorly across domains, and incur high inference-time cost. In this paper, we propose Bi-directional Perceptual Shaping (BiPS), which transforms question-conditioned masked views into bidirectional where-to-look signals that shape perception during training. BiPS first applies a KL-consistency constraint between the original image and an evidence-preserving view that keeps only question-relevant regions, encouraging coarse but complete coverage of supporting pixels. It then applies a KL-separation constraint between the original and an evidence-ablated view where critical pixels are masked so the image no longer supports the original answer, discouraging text-only shortcuts (i.e., answering from text alone) and enforcing fine-grained visual reliance. Across eight benchmarks, BiPS boosts Qwen2.5-VL-7B by 8.2% on average and shows strong out-of-domain generalization to unseen datasets and image types.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21199</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22120</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 18:58:58 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 18:59:47 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>PERSE: Personalized 3D Generative Avatars from A Single Portrait</title>
|
<title>VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs</title>
|
||||||
<link>https://arxiv.org/abs/2412.21206</link>
|
<link>https://arxiv.org/abs/2512.22342</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2412.21206.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hyunsoo Cha, Inhee Lee, Hanbyul Joo</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> We present PERSE, a method for building an animatable personalized generative avatar from a reference portrait. Our avatar model enables facial attribute editing in a continuous and disentangled latent space to control each facial attribute, while preserving the individual's identity. To achieve this, our method begins by synthesizing large-scale synthetic 2D video datasets, where each video contains consistent changes in the facial expression and viewpoint, combined with a variation in a specific facial attribute from the original input. We propose a novel pipeline to produce high-quality, photorealistic 2D videos with facial attribute editing. Leveraging this synthetic attribute dataset, we present a personalized avatar creation method based on the 3D Gaussian Splatting, learning a continuous and disentangled latent space for intuitive facial attribute manipulation. To enforce smooth transitions in this latent space, we introduce a latent space regularization technique by using interpolated 2D faces as supervision. Compared to previous approaches, we demonstrate that PERSE generates high-quality avatars with interpolated attributes while preserving identity of reference person.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wensi Huang, Shaohao Zhu, Meng Wei, Jinming Xu, Xihui Liu, Hanqing Wang, Tai Wang, Feng Zhao, Jiangmiao Pang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> In most existing embodied navigation tasks, instructions are well-defined and unambiguous, such as instruction following and object searching. Under this idealized setting, agents are required solely to produce effective navigation outputs conditioned on vision and language inputs. However, real-world navigation instructions are often vague and ambiguous, requiring the agent to resolve uncertainty and infer user intent through active dialog. To address this gap, we propose Interactive Instance Object Navigation (IION), a task that requires agents not only to generate navigation actions but also to produce language outputs via active dialog, thereby aligning more closely with practical settings. IION extends Instance Object Navigation (ION) by allowing agents to freely consult an oracle in natural language while navigating. Building on this task, we present the Vision Language-Language Navigation (VL-LN) benchmark, which provides a large-scale, automatically generated dataset and a comprehensive evaluation protocol for training and assessing dialog-enabled navigation models. VL-LN comprises over 41k long-horizon dialog-augmented trajectories for training and an automatic evaluation protocol with an oracle capable of responding to agent queries. Using this benchmark, we train a navigation model equipped with dialog capabilities and show that it achieves significant improvements over the baselines. Extensive experiments and analyses further demonstrate the effectiveness and reliability of VL-LN for advancing research on dialog-enabled embodied navigation. Code and dataset: https://0309hws.github.io/VL-LN.github.io/</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2412.21206</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22342</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 18:59:58 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 19:00:12 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>LTX-Video: Realtime Video Latent Diffusion</title>
|
<title>Self-Evaluation Unlocks Any-Step Text-to-Image Generation</title>
|
||||||
<link>https://arxiv.org/abs/2501.00103</link>
|
<link>https://arxiv.org/abs/2512.22374</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yoav HaCohen, Nisan Chiprut, Benny Brazowski, Daniel Shalem, Dudu Moshe, Eitan Richardson, Eran Levin, Guy Shiran, Nir Zabari, Ori Gordon, Poriya Panet, Sapir Weissbuch, Victor Kulikov, Yaki Bitterman, Zeev Melumian, Ofir Bibi</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> We introduce LTX-Video, a transformer-based latent diffusion model that adopts a holistic approach to video generation by seamlessly integrating the responsibilities of the Video-VAE and the denoising transformer. Unlike existing methods, which treat these components as independent, LTX-Video aims to optimize their interaction for improved efficiency and quality. At its core is a carefully designed Video-VAE that achieves a high compression ratio of 1:192, with spatiotemporal downscaling of 32 x 32 x 8 pixels per token, enabled by relocating the patchifying operation from the transformer's input to the VAE's input. Operating in this highly compressed latent space enables the transformer to efficiently perform full spatiotemporal self-attention, which is essential for generating high-resolution videos with temporal consistency. However, the high compression inherently limits the representation of fine details. To address this, our VAE decoder is tasked with both latent-to-pixel conversion and the final denoising step, producing the clean result directly in pixel space. This approach preserves the ability to generate fine details without incurring the runtime cost of a separate upsampling module. Our model supports diverse use cases, including text-to-video and image-to-video generation, with both capabilities trained simultaneously. It achieves faster-than-real-time generation, producing 5 seconds of 24 fps video at 768x512 resolution in just 2 seconds on an Nvidia H100 GPU, outperforming all existing models of similar scale. The source code and pre-trained models are publicly available, setting a new benchmark for accessible and scalable video generation.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22374.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xin Yu, Xiaojuan Qi, Zhengqi Li, Kai Zhang, Richard Zhang, Zhe Lin, Eli Shechtman, Tianyu Wang, Yotam Nitzan</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We introduce the Self-Evaluating Model (Self-E), a novel, from-scratch training approach for text-to-image generation that supports any-step inference. Self-E learns from data similarly to a Flow Matching model, while simultaneously employing a novel self-evaluation mechanism: it evaluates its own generated samples using its current score estimates, effectively serving as a dynamic self-teacher. Unlike traditional diffusion or flow models, it does not rely solely on local supervision, which typically necessitates many inference steps. Unlike distillation-based approaches, it does not require a pretrained teacher. This combination of instantaneous local learning and self-driven global matching bridges the gap between the two paradigms, enabling the training of a high-quality text-to-image model from scratch that excels even at very low step counts. Extensive experiments on large-scale text-to-image benchmarks show that Self-E not only excels in few-step generation, but is also competitive with state-of-the-art Flow Matching models at 50 steps. We further find that its performance improves monotonically as inference steps increase, enabling both ultra-fast few-step generation and high-quality long-trajectory sampling within a single unified model. To our knowledge, Self-E is the first from-scratch, any-step text-to-image model, offering a unified framework for efficient and scalable generation.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00103</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22374</guid>
|
||||||
<pubDate>Mon, 30 Dec 2024 19:00:25 +0000</pubDate>
|
<pubDate>Fri, 26 Dec 2025 20:42:11 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MLLM-as-a-Judge for Image Safety without Human Labeling</title>
|
<title>Monadic Context Engineering</title>
|
||||||
<link>https://arxiv.org/abs/2501.00192</link>
|
<link>https://arxiv.org/abs/2512.22431</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenting Wang, Shuming Hu, Shiyu Zhao, Xiaowen Lin, Felix Juefei-Xu, Zhuowei Li, Ligong Han, Harihar Subramanyam, Li Chen, Jianfa Chen, Nan Jiang, Lingjuan Lyu, Shiqing Ma, Dimitris N. Metaxas, Ankit Jain</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Image content safety has become a significant challenge with the rise of visual media on online platforms. Meanwhile, in the age of AI-generated content (AIGC), many image generation models are capable of producing harmful content, such as images containing sexual or violent material. Thus, it becomes crucial to identify such unsafe images based on established safety rules. Pre-trained Multimodal Large Language Models (MLLMs) offer potential in this regard, given their strong pattern recognition abilities. Existing approaches typically fine-tune MLLMs with human-labeled datasets, which however brings a series of drawbacks. First, relying on human annotators to label data following intricate and detailed guidelines is both expensive and labor-intensive. Furthermore, users of safety judgment systems may need to frequently update safety rules, making fine-tuning on human-based annotation more challenging. This raises the research question: Can we detect unsafe images by querying MLLMs in a zero-shot setting using a predefined safety constitution (a set of safety rules)? Our research showed that simply querying pre-trained MLLMs does not yield satisfactory results. This lack of effectiveness stems from factors such as the subjectivity of safety rules, the complexity of lengthy constitutions, and the inherent biases in the models. To address these challenges, we propose a MLLM-based method includes objectifying safety rules, assessing the relevance between rules and images, making quick judgments based on debiased token probabilities with logically complete yet simplified precondition chains for safety rules, and conducting more in-depth reasoning with cascaded chain-of-thought processes if necessary. Experiment results demonstrate that our method is highly effective for zero-shot image safety judgment tasks.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22431.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Zhang, Mengdi Wang</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> The proliferation of Large Language Models (LLMs) has catalyzed a shift towards autonomous agents capable of complex reasoning and tool use. However, current agent architectures are frequently constructed using imperative, ad hoc patterns. This results in brittle systems plagued by difficulties in state management, error handling, and concurrency. This paper introduces Monadic Context Engineering (MCE), a novel architectural paradigm leveraging the algebraic structures of Functors, Applicative Functors, and Monads to provide a formal foundation for agent design. MCE treats agent workflows as computational contexts where cross-cutting concerns, such as state propagation, short-circuiting error handling, and asynchronous execution, are managed intrinsically by the algebraic properties of the abstraction. We demonstrate how Monads enable robust sequential composition, how Applicatives provide a principled structure for parallel execution, and crucially, how Monad Transformers allow for the systematic composition of these capabilities. This layered approach enables developers to construct complex, resilient, and efficient AI agents from simple, independently verifiable components. We further extend this framework to describe Meta-Agents, which leverage MCE for generative orchestration, dynamically creating and managing sub-agent workflows through metaprogramming. Project Page: https://github.com/yifanzhang-pro/monadic-context-engineering.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00192</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22431</guid>
|
||||||
<pubDate>Tue, 31 Dec 2024 00:06:04 +0000</pubDate>
|
<pubDate>Sat, 27 Dec 2025 01:52:06 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models</title>
|
<title>GraphLocator: Graph-guided Causal Reasoning for Issue Localization</title>
|
||||||
<link>https://arxiv.org/abs/2501.00316</link>
|
<link>https://arxiv.org/abs/2512.22469</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00316.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mahir Labib Dihan, Md Tanvir Hassan, Md Tanvir Parvez, Md Hasebul Hasan, Md Almash Alam, Muhammad Aamir Cheema, Mohammed Eunus Ali, Md Rizwan Parvez</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Recent advancements in foundation models have enhanced AI systems' capabilities in autonomous tool usage and reasoning. However, their ability in location or map-based reasoning - which improves daily life by optimizing navigation, facilitating resource discovery, and streamlining logistics - has not been systematically studied. To bridge this gap, we introduce MapEval, a benchmark designed to assess diverse and complex map-based user queries with geo-spatial reasoning. MapEval features three task types (textual, API-based, and visual) that require collecting world information via map tools, processing heterogeneous geo-spatial contexts (e.g., named entities, travel distances, user reviews or ratings, images), and compositional reasoning, which all state-of-the-art foundation models find challenging. Comprising 700 unique multiple-choice questions about locations across 180 cities and 54 countries, MapEval evaluates foundation models' ability to handle spatial relationships, map infographics, travel planning, and navigation challenges. Using MapEval, we conducted a comprehensive evaluation of 28 prominent foundation models. While no single model excelled across all tasks, Claude-3.5-Sonnet, GPT-4o, and Gemini-1.5-Pro achieved competitive performance overall. However, substantial performance gaps emerged, particularly in MapEval, where agents with Claude-3.5-Sonnet outperformed GPT-4o and Gemini-1.5-Pro by 16% and 21%, respectively, and the gaps became even more amplified when compared to open-source LLMs. Our detailed analyses provide insights into the strengths and weaknesses of current models, though all models still fall short of human performance by more than 20% on average, struggling with complex map images and rigorous geo-spatial reasoning. This gap highlights MapEval's critical role in advancing general-purpose foundation models with stronger geo-spatial understanding.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22469.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Liu, Chao Peng, Pengfei Gao, Aofan Liu, Wei Zhang, Haiyan Zhao, Zhi Jin</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> The issue localization task aims to identify the locations in a software repository that requires modification given a natural language issue description. This task is fundamental yet challenging in automated software engineering due to the semantic gap between issue description and source code implementation. This gap manifests as two mismatches:(1) symptom-to-cause mismatches, where descriptions do not explicitly reveal underlying root causes; (2) one-to-many mismatches, where a single issue corresponds to multiple interdependent code entities. To address these two mismatches, we propose GraphLocator, an approach that mitigates symptom-to-cause mismatches through causal structure discovering and resolves one-to-many mismatches via dynamic issue disentangling. The key artifact is the causal issue graph (CIG), in which vertices represent discovered sub-issues along with their associated code entities, and edges encode the causal dependencies between them. The workflow of GraphLocator consists of two phases: symptom vertices locating and dynamic CIG discovering; it first identifies symptom locations on the repository graph, then dynamically expands the CIG by iteratively reasoning over neighboring vertices. Experiments on three real-world datasets demonstrates the effectiveness of GraphLocator: (1) Compared with baselines, GraphLocator achieves more accurate localization with average improvements of +19.49% in function-level recall and +11.89% in precision. (2) GraphLocator outperforms baselines on both symptom-to-cause and one-to-many mismatch scenarios, achieving recall improvement of +16.44% and +19.18%, precision improvement of +7.78% and +13.23%, respectively. (3) The CIG generated by GraphLocator yields the highest relative improvement, resulting in a 28.74% increase in performance on downstream resolving task.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00316</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22469</guid>
|
||||||
<pubDate>Tue, 31 Dec 2024 07:20:32 +0000</pubDate>
|
<pubDate>Sat, 27 Dec 2025 05:02:53 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM</title>
|
<title>DreamOmni3: Scribble-based Editing and Generation</title>
|
||||||
<link>https://arxiv.org/abs/2501.00599</link>
|
<link>https://arxiv.org/abs/2512.22525</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00599.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuqian Yuan, Hang Zhang, Wentong Li, Zesen Cheng, Boqiang Zhang, Long Li, Xin Li, Deli Zhao, Wenqiao Zhang, Yueting Zhuang, Jianke Zhu, Lidong Bing</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal details. Besides, the lack of high-quality object-level video instruction data and a comprehensive benchmark further hinders their advancements. To tackle these challenges, we introduce the VideoRefer Suite to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video. Specially, we thoroughly develop VideoRefer Suite across three essential aspects: dataset, model, and benchmark. Firstly, we introduce a multi-agent data engine to meticulously curate a large-scale, high-quality object-level video instruction dataset, termed VideoRefer-700K. Next, we present the VideoRefer model, which equips a versatile spatial-temporal object encoder to capture precise regional and sequential representations. Finally, we meticulously create a VideoRefer-Bench to comprehensively assess the spatial-temporal understanding capability of a Video LLM, evaluating it across various aspects. Extensive experiments and analyses demonstrate that our VideoRefer model not only achieves promising performance on video referring benchmarks but also facilitates general video understanding capabilities.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22525.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bin Xia, Bohao Peng, Jiyang Liu, Sitong Wu, Jingyao Li, Junjia Huang, Xu Zhao, Yitong Wang, Ruihang Chu, Bei Yu, Jiaya Jia</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Recently unified generation and editing models have achieved remarkable success with their impressive performance. These models rely mainly on text prompts for instruction-based editing and generation, but language often fails to capture users intended edit locations and fine-grained visual details. To this end, we propose two tasks: scribble-based editing and generation, that enables more flexible creation on graphical user interface (GUI) combining user textual, images, and freehand sketches. We introduce DreamOmni3, tackling two challenges: data creation and framework design. Our data synthesis pipeline includes two parts: scribble-based editing and generation. For scribble-based editing, we define four tasks: scribble and instruction-based editing, scribble and multimodal instruction-based editing, image fusion, and doodle editing. Based on DreamOmni2 dataset, we extract editable regions and overlay hand-drawn boxes, circles, doodles or cropped image to construct training data. For scribble-based generation, we define three tasks: scribble and instruction-based generation, scribble and multimodal instruction-based generation, and doodle generation, following similar data creation pipelines. For the framework, instead of using binary masks, which struggle with complex edits involving multiple scribbles, images, and instructions, we propose a joint input scheme that feeds both the original and scribbled source images into the model, using different colors to distinguish regions and simplify processing. By applying the same index and position encodings to both images, the model can precisely localize scribbled regions while maintaining accurate editing. Finally, we establish comprehensive benchmarks for these tasks to promote further research. Experimental results demonstrate that DreamOmni3 achieves outstanding performance, and models and code will be publicly released.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00599</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22525</guid>
|
||||||
<pubDate>Tue, 31 Dec 2024 18:56:46 +0000</pubDate>
|
<pubDate>Sat, 27 Dec 2025 09:07:12 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing</title>
|
<title>Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformers</title>
|
||||||
<link>https://arxiv.org/abs/2501.00658</link>
|
<link>https://arxiv.org/abs/2512.22564</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00658.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peihao Wang, Ruisi Cai, Yuehao Wang, Jiajun Zhu, Pragya Srivastava, Zhangyang Wang, Pan Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Structured State Space Models (SSMs) have emerged as alternatives to transformers. While SSMs are often regarded as effective in capturing long-sequence dependencies, we rigorously demonstrate that they are inherently limited by strong recency bias. Our empirical studies also reveal that this bias impairs the models' ability to recall distant information and introduces robustness issues. Our scaling experiments then discovered that deeper structures in SSMs can facilitate the learning of long contexts. However, subsequent theoretical analysis reveals that as SSMs increase in depth, they exhibit another inevitable tendency toward over-smoothing, e.g., token representations becoming increasingly indistinguishable. This fundamental dilemma between recency and over-smoothing hinders the scalability of existing SSMs. Inspired by our theoretical findings, we propose to polarize two channels of the state transition matrices in SSMs, setting them to zero and one, respectively, simultaneously addressing recency bias and over-smoothing. Experiments demonstrate that our polarization technique consistently enhances the associative recall accuracy of long-range tokens and unlocks SSMs to benefit further from deeper architectures. All source codes are released at https://github.com/VITA-Group/SSM-Bottleneck.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22564.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Atakan Işık, Selin Vulga Işık, Ahmet Feridun Işık, Mahşuk Taylan</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Respiratory sound classification is hindered by the limited size, high noise levels, and severe class imbalance of benchmark datasets like ICBHI 2017. While Transformer-based models offer powerful feature extraction capabilities, they are prone to overfitting and often converge to sharp minima in the loss landscape when trained on such constrained medical data. To address this, we introduce a framework that enhances the Audio Spectrogram Transformer (AST) using Sharpness-Aware Minimization (SAM). Instead of merely minimizing the training loss, our approach optimizes the geometry of the loss surface, guiding the model toward flatter minima that generalize better to unseen patients. We also implement a weighted sampling strategy to handle class imbalance effectively. Our method achieves a state-of-the-art score of 68.10% on the ICBHI 2017 dataset, outperforming existing CNN and hybrid baselines. More importantly, it reaches a sensitivity of 68.31%, a crucial improvement for reliable clinical screening. Further analysis using t-SNE and attention maps confirms that the model learns robust, discriminative features rather than memorizing background noise.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00658</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22564</guid>
|
||||||
<pubDate>Tue, 31 Dec 2024 22:06:39 +0000</pubDate>
|
<pubDate>Sat, 27 Dec 2025 11:39:36 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding</title>
|
<title>Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone</title>
|
||||||
<link>https://arxiv.org/abs/2501.00712</link>
|
<link>https://arxiv.org/abs/2512.22615</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00712.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many current methods enforce rigid patterns in attention maps, limiting the ability to model long-range dependencies and adapt to diverse tasks. Additionally, most positional encodings are learned as general biases, lacking the specialization required for different instances within a dataset. To address this, we propose conTextualized equivariAnt Position Embedding (TAPE), a novel framework that enhances positional embeddings by incorporating sequence content across layers. TAPE introduces dynamic, context-aware positional encodings, overcoming the constraints of traditional fixed patterns. By enforcing permutation and orthogonal equivariance, TAPE ensures the stability of positional encodings during updates, improving robustness and adaptability. Our method can be easily integrated into pre-trained transformers, offering parameter-efficient fine-tuning with minimal overhead. Extensive experiments shows that TAPE achieves superior performance in language modeling, arithmetic reasoning, and long-context retrieval tasks compared to existing positional embedding techniques.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22615.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiacheng Ye, Shansan Gong, Jiahui Gao, Junming Fan, Shuang Wu, Wei Bi, Haoli Bai, Lifeng Shang, Lingpeng Kong</p><p><b>Upvotes:</b> 43</p><p><b>Summary:</b> While autoregressive Large Vision-Language Models (VLMs) have achieved remarkable success, their sequential generation often limits their efficacy in complex visual planning and dynamic robotic control. In this work, we investigate the potential of constructing Vision-Language Models upon diffusion-based large language models (dLLMs) to overcome these limitations. We introduce Dream-VL, an open diffusion-based VLM (dVLM) that achieves state-of-the-art performance among previous dVLMs. Dream-VL is comparable to top-tier AR-based VLMs trained on open data on various benchmarks but exhibits superior potential when applied to visual planning tasks. Building upon Dream-VL, we introduce Dream-VLA, a dLLM-based Vision-Language-Action model (dVLA) developed through continuous pre-training on open robotic datasets. We demonstrate that the natively bidirectional nature of this diffusion backbone serves as a superior foundation for VLA tasks, inherently suited for action chunking and parallel generation, leading to significantly faster convergence in downstream fine-tuning. Dream-VLA achieves top-tier performance of 97.2% average success rate on LIBERO, 71.4% overall average on SimplerEnv-Bridge, and 60.5% overall average on SimplerEnv-Fractal, surpassing leading models such as π_0 and GR00T-N1. We also validate that dVLMs surpass AR baselines on downstream tasks across different training objectives. We release both Dream-VL and Dream-VLA to facilitate further research in the community.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00712</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22615</guid>
|
||||||
<pubDate>Wed, 01 Jan 2025 03:23:00 +0000</pubDate>
|
<pubDate>Sat, 27 Dec 2025 14:46:24 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Population Aware Diffusion for Time Series Generation</title>
|
<title>On the Role of Discreteness in Diffusion LLMs</title>
|
||||||
<link>https://arxiv.org/abs/2501.00910</link>
|
<link>https://arxiv.org/abs/2512.22630</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00910.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Li, Han Meng, Zhenyu Bi, Ingolv T. Urnes, Haipeng Chen</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Diffusion models have shown promising ability in generating high-quality time series (TS) data. Despite the initial success, existing works mostly focus on the authenticity of data at the individual level, but pay less attention to preserving the population-level properties on the entire dataset. Such population-level properties include value distributions for each dimension and distributions of certain functional dependencies (e.g., cross-correlation, CC) between different dimensions. For instance, when generating house energy consumption TS data, the value distributions of the outside temperature and the kitchen temperature should be preserved, as well as the distribution of CC between them. Preserving such TS population-level properties is critical in maintaining the statistical insights of the datasets, mitigating model bias, and augmenting downstream tasks like TS prediction. Yet, it is often overlooked by existing models. Hence, data generated by existing models often bear distribution shifts from the original data. We propose Population-aware Diffusion for Time Series (PaD-TS), a new TS generation model that better preserves the population-level properties. The key novelties of PaD-TS include 1) a new training method explicitly incorporating TS population-level property preservation, and 2) a new dual-channel encoder model architecture that better captures the TS data structure. Empirical results in major benchmark datasets show that PaD-TS can improve the average CC distribution shift score between real and synthetic data by 5.9x while maintaining a performance comparable to state-of-the-art models on individual-level authenticity.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22630.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqi Jin, Bin Wang, Xiang Lin, Lidong Bing, Aixin Sun</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Diffusion models offer appealing properties for language generation, such as parallel decoding and iterative refinement, but the discrete and highly structured nature of text challenges the direct application of diffusion principles. In this paper, we revisit diffusion language modeling from the view of diffusion process and language modeling, and outline five properties that separate diffusion mechanics from language-specific requirements. We first categorize existing approaches into continuous diffusion in embedding space and discrete diffusion over tokens. We then show that each satisfies only part of the five essential properties and therefore reflects a structural trade-off. Through analyses of recent large diffusion language models, we identify two central issues: (i) uniform corruption does not respect how information is distributed across positions, and (ii) token-wise marginal training cannot capture multi-token dependencies during parallel decoding. These observations motivate diffusion processes that align more closely with the structure of text, and encourage future work toward more coherent diffusion language models.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00910</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22630</guid>
|
||||||
<pubDate>Wed, 01 Jan 2025 17:53:43 +0000</pubDate>
|
<pubDate>Sat, 27 Dec 2025 16:03:08 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining</title>
|
<title>JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation</title>
|
||||||
<link>https://arxiv.org/abs/2501.00958</link>
|
<link>https://arxiv.org/abs/2512.22905</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.00958.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqi Zhang, Hang Zhang, Xin Li, Jiashuo Sun, Yongliang Shen, Weiming Lu, Deli Zhao, Yueting Zhuang, Lidong Bing</p><p><b>Upvotes:</b> 106</p><p><b>Summary:</b> Compared to image-text pair data, interleaved corpora enable Vision-Language Models (VLMs) to understand the world more naturally like humans. However, such existing datasets are crawled from webpage, facing challenges like low knowledge density, loose image-text relations, and poor logical coherence between images. On the other hand, the internet hosts vast instructional videos (e.g., online geometry courses) that are widely used by humans to learn foundational subjects, yet these valuable resources remain underexplored in VLM training. In this paper, we introduce a high-quality multimodal textbook corpus with richer foundational knowledge for VLM pretraining. It collects over 2.5 years of instructional videos, totaling 22,000 class hours. We first use an LLM-proposed taxonomy to systematically gather instructional videos. Then we progressively extract and refine visual (keyframes), audio (ASR), and textual knowledge (OCR) from the videos, and organize as an image-text interleaved corpus based on temporal order. Compared to its counterparts, our video-centric textbook offers more coherent context, richer knowledge, and better image-text alignment. Experiments demonstrate its superb pretraining performance, particularly in knowledge- and reasoning-intensive tasks like ScienceQA and MathVista. Moreover, VLMs pre-trained on our textbook exhibit outstanding interleaved context awareness, leveraging visual and textual cues in their few-shot context for task solving~Our code are available at \url{https://github.com/DAMO-NLP-SG/multimodal_textbook}.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22905.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai Liu, Jungang Li, Yuchong Sun, Shengqiong Wu, Jianzhang Gao, Daoan Zhang, Wei Zhang, Sheng Jin, Sicheng Yu, Geng Zhan, Jiayi Ji, Fan Zhou, Liang Zheng, Shuicheng Yan, Hao Fei, Tat-Seng Chua</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> This paper presents JavisGPT, the first unified multimodal large language model (MLLM) for Joint Audio-Video (JAV) comprehension and generation. JavisGPT adopts a concise encoder-LLM-decoder architecture, featuring a SyncFusion module for spatio-temporal audio-video fusion and synchrony-aware learnable queries to bridge a pretrained JAV-DiT generator. This design enables temporally coherent video-audio understanding and generation from multimodal instructions. We design an effective three-stage training pipeline consisting of multimodal pretraining, audio-video fine-tuning, and large-scale instruction-tuning, to progressively build multimodal comprehension and generation from existing vision-language models. To support this, we further construct JavisInst-Omni, a high-quality instruction dataset with over 200K GPT-4o-curated audio-video-text dialogues that span diverse and multi-level comprehension and generation scenarios. Extensive experiments on JAV comprehension and generation benchmarks show that JavisGPT outperforms existing MLLMs, particularly in complex and temporally synchronized settings.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.00958</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22905</guid>
|
||||||
<pubDate>Wed, 01 Jan 2025 21:29:37 +0000</pubDate>
|
<pubDate>Sun, 28 Dec 2025 12:25:43 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Dynamic Scaling of Unit Tests for Code Reward Modeling</title>
|
<title>Reverse Personalization</title>
|
||||||
<link>https://arxiv.org/abs/2501.01054</link>
|
<link>https://arxiv.org/abs/2512.22984</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01054.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeyao Ma, Xiaokang Zhang, Jing Zhang, Jifan Yu, Sijia Luo, Jie Tang</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus).</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.22984.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han-Wei Kung, Tuomas Varanka, Nicu Sebe</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent text-to-image diffusion models have demonstrated remarkable generation of realistic facial images conditioned on textual prompts and human identities, enabling creating personalized facial imagery. However, existing prompt-based methods for removing or modifying identity-specific features rely either on the subject being well-represented in the pre-trained model or require model fine-tuning for specific identities. In this work, we analyze the identity generation process and introduce a reverse personalization framework for face anonymization. Our approach leverages conditional diffusion inversion, allowing direct manipulation of images without using text prompts. To generalize beyond subjects in the model's training data, we incorporate an identity-guided conditioning branch. Unlike prior anonymization methods, which lack control over facial attributes, our framework supports attribute-controllable anonymization. We demonstrate that our method achieves a state-of-the-art balance between identity removal, attribute preservation, and image quality. Source code and data are available at https://github.com/hanweikung/reverse-personalization .</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01054</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.22984</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 04:33:31 +0000</pubDate>
|
<pubDate>Sun, 28 Dec 2025 16:06:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>A3: Android Agent Arena for Mobile GUI Agents</title>
|
<title>Video-BrowseComp: Benchmarking Agentic Video Research on Open Web</title>
|
||||||
<link>https://arxiv.org/abs/2501.01149</link>
|
<link>https://arxiv.org/abs/2512.23044</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01149.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuxiang Chai, Hanhao Li, Jiayu Zhang, Liang Liu, Guozhi Wang, Shuai Ren, Siyuan Huang, Hongsheng Li</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> AI agents have become increasingly prevalent in recent years, driven by significant advancements in the field of large language models (LLMs). Mobile GUI agents, a subset of AI agents, are designed to autonomously perform tasks on mobile devices. While numerous studies have introduced agents, datasets, and benchmarks to advance mobile GUI agent research, many existing datasets focus on static frame evaluations and fail to provide a comprehensive platform for assessing performance on real-world, in-the-wild tasks. To address this gap, we present Android Agent Arena (A3), a novel evaluation platform. Unlike existing in-the-wild systems, A3 offers: (1) meaningful and practical tasks, such as real-time online information retrieval and operational instructions; (2) a larger, more flexible action space, enabling compatibility with agents trained on any dataset; and (3) automated business-level LLM-based evaluation process. A3 includes 21 widely used general third-party apps and 201 tasks representative of common user scenarios, providing a robust foundation for evaluating mobile GUI agents in real-world situations and a new autonomous evaluation process for less human labor and coding expertise. The project is available at https://yuxiangchai.github.io/Android-Agent-Arena/.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23044.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengyang Liang, Yan Shu, Xiangrui Liu, Minghao Qin, Kaixin Liang, Paolo Rota, Nicu Sebe, Zheng Liu, Lizi Liao</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> The evolution of autonomous agents is redefining information seeking, transitioning from passive retrieval to proactive, open-ended web research. However, while textual and static multimodal agents have seen rapid progress, a significant modality gap remains in processing the web's most dynamic modality: video. Existing video benchmarks predominantly focus on passive perception, feeding curated clips to models without requiring external retrieval. They fail to evaluate agentic video research, which necessitates actively interrogating video timelines, cross-referencing dispersed evidence, and verifying claims against the open web. To bridge this gap, we present Video-BrowseComp, a challenging benchmark comprising 210 questions tailored for open-web agentic video reasoning. Unlike prior benchmarks, Video-BrowseComp enforces a mandatory dependency on temporal visual evidence, ensuring that answers cannot be derived solely through text search but require navigating video timelines to verify external claims. Our evaluation of state-of-the-art models reveals a critical bottleneck: even advanced search-augmented models like GPT-5.1 (w/ Search) achieve only 15.24\% accuracy. Our analysis reveals that these models largely rely on textual proxies, excelling in metadata-rich domains (e.g., TV shows with plot summaries) but collapsing in metadata-sparse, dynamic environments (e.g., sports, gameplay) where visual grounding is essential. As the first open-web video research benchmark, Video-BrowseComp advances the field beyond passive perception toward proactive video reasoning.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01149</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23044</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 09:03:56 +0000</pubDate>
|
<pubDate>Sun, 28 Dec 2025 19:08:27 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization</title>
|
<title>SurgWorld: Learning Surgical Robot Policies from Videos via World Modeling</title>
|
||||||
<link>https://arxiv.org/abs/2501.01245</link>
|
<link>https://arxiv.org/abs/2512.23162</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01245.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yongle Huang, Haodong Chen, Zhenbang Xu, Zihan Jia, Haozhou Sun, Dian Shao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Human action understanding is crucial for the advancement of multimodal systems. While recent developments, driven by powerful large language models (LLMs), aim to be general enough to cover a wide range of categories, they often overlook the need for more specific capabilities. In this work, we address the more challenging task of Fine-grained Action Recognition (FAR), which focuses on detailed semantic labels within shorter temporal duration (e.g., "salto backward tucked with 1 turn"). Given the high costs of annotating fine-grained labels and the substantial data needed for fine-tuning LLMs, we propose to adopt semi-supervised learning (SSL). Our framework, SeFAR, incorporates several innovative designs to tackle these challenges. Specifically, to capture sufficient visual details, we construct Dual-level temporal elements as more effective representations, based on which we design a new strong augmentation strategy for the Teacher-Student learning paradigm through involving moderate temporal perturbation. Furthermore, to handle the high uncertainty within the teacher model's predictions for FAR, we propose the Adaptive Regulation to stabilize the learning process. Experiments show that SeFAR achieves state-of-the-art performance on two FAR datasets, FineGym and FineDiving, across various data scopes. It also outperforms other semi-supervised methods on two classical coarse-grained datasets, UCF101 and HMDB51. Further analysis and ablation studies validate the effectiveness of our designs. Additionally, we show that the features extracted by our SeFAR could largely promote the ability of multimodal foundation models to understand fine-grained and domain-specific semantics.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23162.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yufan He, Pengfei Guo, Mengya Xu, Zhaoshuo Li, Andriy Myronenko, Dillan Imans, Bingjie Liu, Dongren Yang, Mingxue Gu, Yongnan Ji, Yueming Jin, Ren Zhao, Baiyong Shen, Daguang Xu</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Data scarcity remains a fundamental barrier to achieving fully autonomous surgical robots. While large scale vision language action (VLA) models have shown impressive generalization in household and industrial manipulation by leveraging paired video action data from diverse domains, surgical robotics suffers from the paucity of datasets that include both visual observations and accurate robot kinematics. In contrast, vast corpora of surgical videos exist, but they lack corresponding action labels, preventing direct application of imitation learning or VLA training. In this work, we aim to alleviate this problem by learning policy models from SurgWorld, a world model designed for surgical physical AI. We curated the Surgical Action Text Alignment (SATA) dataset with detailed action description specifically for surgical robots. Then we built SurgeWorld based on the most advanced physical AI world model and SATA. It's able to generate diverse, generalizable and realistic surgery videos. We are also the first to use an inverse dynamics model to infer pseudokinematics from synthetic surgical videos, producing synthetic paired video action data. We demonstrate that a surgical VLA policy trained with these augmented data significantly outperforms models trained only on real demonstrations on a real surgical robot platform. Our approach offers a scalable path toward autonomous surgical skill acquisition by leveraging the abundance of unlabeled surgical video and generative world modeling, thus opening the door to generalizable and data efficient surgical robot policies.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01245</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23162</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 13:12:12 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 03:03:00 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings</title>
|
<title>Evaluating Parameter Efficient Methods for RLVR</title>
|
||||||
<link>https://arxiv.org/abs/2501.01257</link>
|
<link>https://arxiv.org/abs/2512.23165</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01257.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shanghaoran Quan, Jiaxi Yang, Bowen Yu, Bo Zheng, Dayiheng Liu, An Yang, Xuancheng Ren, Bofei Gao, Yibo Miao, Yunlong Feng, Zekun Wang, Jian Yang, Zeyu Cui, Yang Fan, Yichang Zhang, Binyuan Hui, Junyang Lin</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> With the increasing code reasoning capabilities of existing large language models (LLMs) and breakthroughs in reasoning models like OpenAI o1 and o3, there is a growing need to develop more challenging and comprehensive benchmarks that effectively test their sophisticated competition-level coding abilities. Existing benchmarks, like LiveCodeBench and USACO, fall short due to the unavailability of private test cases, lack of support for special judges, and misaligned execution environments. To bridge this gap, we introduce CodeElo, a standardized competition-level code generation benchmark that effectively addresses all these challenges for the first time. CodeElo benchmark is mainly based on the official CodeForces platform and tries to align with the platform as much as possible. We compile the recent six months of contest problems on CodeForces with detailed information such as contest divisions, problem difficulty ratings, and problem algorithm tags. We introduce a unique judging method in which problems are submitted directly to the platform and develop a reliable Elo rating calculation system that aligns with the platform and is comparable with human participants but has lower variance. By testing on our CodeElo, we provide the Elo ratings of 30 existing popular open-source and 3 proprietary LLMs for the first time. The results show that o1-mini and QwQ-32B-Preview stand out significantly, achieving Elo ratings of 1578 and 1261, respectively, while other models struggle even with the easiest problems, placing in the lowest 20 percent among all human participants. Detailed analysis experiments are also conducted to provide insights into performance across algorithms and comparisons between using C++ and Python, which can suggest directions for future studies.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23165.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Yin, Yulun Wu, Zhennan Shen, Sunbowen Li, Zhilin Wang, Yanshu Li, Chak Tou Leong, Jiale Kang, Jinjin Gu</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> We systematically evaluate Parameter-Efficient Fine-Tuning (PEFT) methods under the paradigm of Reinforcement Learning with Verifiable Rewards (RLVR). RLVR incentivizes language models to enhance their reasoning capabilities through verifiable feedback; however, while methods like LoRA are commonly used, the optimal PEFT architecture for RLVR remains unidentified. In this work, we conduct the first comprehensive evaluation of over 12 PEFT methodologies across the DeepSeek-R1-Distill families on mathematical reasoning benchmarks. Our empirical results challenge the default adoption of standard LoRA with three main findings. First, we demonstrate that structural variants, such as DoRA, AdaLoRA, and MiSS, consistently outperform LoRA. Second, we uncover a spectral collapse phenomenon in SVD-informed initialization strategies (e.g., PiSSA, MiLoRA), attributing their failure to a fundamental misalignment between principal-component updates and RL optimization. Furthermore, our ablations reveal that extreme parameter reduction (e.g., VeRA, Rank-1) severely bottlenecks reasoning capacity. We further conduct ablation studies and scaling experiments to validate our findings. This work provides a definitive guide for advocating for more exploration for parameter-efficient RL methods.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01257</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23165</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 13:49:00 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 03:13:08 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>ProgCo: Program Helps Self-Correction of Large Language Models</title>
|
<title>Bridging Your Imagination with Audio-Video Generation via a Unified Director</title>
|
||||||
<link>https://arxiv.org/abs/2501.01264</link>
|
<link>https://arxiv.org/abs/2512.23222</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01264.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoshuai Song, Yanan Wu, Weixun Wang, Jiaheng Liu, Wenbo Su, Bo Zheng</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectively self-verify and generate correct feedback, further misleading refinement and leading to the failure of self-correction, especially in complex reasoning tasks. In this paper, we propose Program-driven Self-Correction (ProgCo). First, program-driven verification (ProgVe) achieves complex verification logic and extensive validation through self-generated, self-executing verification pseudo-programs. Then, program-driven refinement (ProgRe) receives feedback from ProgVe, conducts dual reflection and refinement on both responses and verification programs to mitigate misleading of incorrect feedback in complex reasoning tasks. Experiments on three instruction-following and mathematical benchmarks indicate that ProgCo achieves effective self-correction, and can be further enhance performance when combined with real program tools.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23222.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaxu Zhang, Tianshu Hu, Yuan Zhang, Zenan Li, Linjie Luo, Guosheng Lin, Xin Chen</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Existing AI-driven video creation systems typically treat script drafting and key-shot design as two disjoint tasks: the former relies on large language models, while the latter depends on image generation models. We argue that these two tasks should be unified within a single framework, as logical reasoning and imaginative thinking are both fundamental qualities of a film director. In this work, we propose UniMAGE, a unified director model that bridges user prompts with well-structured scripts, thereby empowering non-experts to produce long-context, multi-shot films by leveraging existing audio-video generation models. To achieve this, we employ the Mixture-of-Transformers architecture that unifies text and image generation. To further enhance narrative logic and keyframe consistency, we introduce a ``first interleaving, then disentangling'' training paradigm. Specifically, we first perform Interleaved Concept Learning, which utilizes interleaved text-image data to foster the model's deeper understanding and imaginative interpretation of scripts. We then conduct Disentangled Expert Learning, which decouples script writing from keyframe generation, enabling greater flexibility and creativity in storytelling. Extensive experiments demonstrate that UniMAGE achieves state-of-the-art performance among open-source models, generating logically coherent video scripts and visually consistent keyframe images.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01264</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23222</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 13:59:20 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 05:56:22 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration</title>
|
<title>KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta</title>
|
||||||
<link>https://arxiv.org/abs/2501.01320</link>
|
<link>https://arxiv.org/abs/2512.23236</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01320.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianyi Wang, Zhijie Lin, Meng Wei, Yang Zhao, Ceyuan Yang, Chen Change Loy, Lu Jiang</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Video restoration poses non-trivial challenges in maintaining fidelity while recovering temporally consistent details from unknown degradations in the wild. Despite recent advances in diffusion-based restoration, these methods often face limitations in generation capability and sampling efficiency. In this work, we present SeedVR, a diffusion transformer designed to handle real-world video restoration with arbitrary length and resolution. The core design of SeedVR lies in the shifted window attention that facilitates effective restoration on long video sequences. SeedVR further supports variable-sized windows near the boundary of both spatial and temporal dimensions, overcoming the resolution constraints of traditional window attention. Equipped with contemporary practices, including causal video autoencoder, mixed image and video training, and progressive training, SeedVR achieves highly-competitive performance on both synthetic and real-world benchmarks, as well as AI-generated videos. Extensive experiments demonstrate SeedVR's superiority over existing methods for generic video restoration.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23236.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gang Liao, Hongsen Qin, Ying Wang, Alicia Golden, Michael Kuchnik, Yavuz Yetim, Jia Jiunn Ang, Chunli Fu, Yihan He, Samuel Hsia, Zewei Jiang, Dianshi Li, Uladzimir Pashkevich, Varna Puvvada, Feng Shi, Matt Steiner, Ruichao Xiao, Nathan Yan, Xiayu Yu, Zhou Fang, Abdul Zainul-Abedin, Ketan Singh, Hongtao Yu, Wenyuan Chi, Barney Huang, Sean Zhang, Noah Weller, Zach Marine, Wyatt Cook, Carole-Jean Wu, Gaoxiang Liu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Making deep learning recommendation model (DLRM) training and inference fast and efficient is important. However, this presents three key system challenges - model architecture diversity, kernel primitive diversity, and hardware generation and architecture heterogeneity. This paper presents KernelEvolve-an agentic kernel coding framework-to tackle heterogeneity at-scale for DLRM. KernelEvolve is designed to take kernel specifications as input and automate the process of kernel generation and optimization for recommendation model across heterogeneous hardware architectures. KernelEvolve does so by operating at multiple programming abstractions, from Triton and CuTe DSL to low-level hardware agnostic languages, spanning the full hardware-software optimization stack. The kernel optimization process is described as graph-based search with selection policy, universal operator, fitness function, and termination rule, dynamically adapts to runtime execution context through retrieval-augmented prompt synthesis. We designed, implemented, and deployed KernelEvolve to optimize a wide variety of production recommendation models across generations of NVIDIA and AMD GPUs, as well as Meta's AI accelerators. We validate KernelEvolve on the publicly-available KernelBench suite, achieving 100% pass rate on all 250 problems across three difficulty levels, and 160 PyTorch ATen operators across three heterogeneous hardware platforms, demonstrating 100% correctness. KernelEvolve reduces development time from weeks to hours and achieves substantial performance improvements over PyTorch baselines across diverse production use cases and for heterogeneous AI systems at-scale. Beyond performance efficiency improvements, KernelEvolve significantly mitigates the programmability barrier for new AI hardware by enabling automated kernel generation for in-house developed AI hardware.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01320</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23236</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 16:19:48 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 06:31:55 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Nested Attention: Semantic-aware Attention Values for Concept Personalization</title>
|
<title>YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection</title>
|
||||||
<link>https://arxiv.org/abs/2501.01407</link>
|
<link>https://arxiv.org/abs/2512.23273</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01407.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Or Patashnik, Rinon Gal, Daniil Ostashev, Sergey Tulyakov, Kfir Aberman, Daniel Cohen-Or</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Personalizing text-to-image models to generate images of specific subjects across diverse scenes and styles is a rapidly advancing field. Current approaches often face challenges in maintaining a balance between identity preservation and alignment with the input text prompt. Some methods rely on a single textual token to represent a subject, which limits expressiveness, while others employ richer representations but disrupt the model's prior, diminishing prompt alignment. In this work, we introduce Nested Attention, a novel mechanism that injects a rich and expressive image representation into the model's existing cross-attention layers. Our key idea is to generate query-dependent subject values, derived from nested attention layers that learn to select relevant subject features for each region in the generated image. We integrate these nested layers into an encoder-based personalization method, and show that they enable high identity preservation while adhering to input text prompts. Our approach is general and can be trained on various domains. Additionally, its prior preservation allows us to combine multiple personalized subjects from different domains in a single image.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xu Lin, Jinlong Peng, Zhenye Gan, Jiawen Zhu, Jun Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to all inputs, misallocating representational capacity and computational resources such as over-allocating on trivial scenes while under-serving complex ones. This mismatch results in both computational redundancy and suboptimal detection performance. To overcome this limitation, we propose YOLO-Master, a novel YOLO-like framework that introduces instance-conditional adaptive computation for RTOD. This is achieved through a Efficient Sparse Mixture-of-Experts (ES-MoE) block that dynamically allocates computational resources to each input according to its scene complexity. At its core, a lightweight dynamic routing network guides expert specialization during training through a diversity enhancing objective, encouraging complementary expertise among experts. Additionally, the routing network adaptively learns to activate only the most relevant experts, thereby improving detection performance while minimizing computational overhead during inference. Comprehensive experiments on five large-scale benchmarks demonstrate the superiority of YOLO-Master. On MS COCO, our model achieves 42.4% AP with 1.62ms latency, outperforming YOLOv13-N by +0.8% mAP and 17.8% faster inference. Notably, the gains are most pronounced on challenging dense scenes, while the model preserves efficiency on typical inputs and maintains real-time inference speed. Code will be available.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01407</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23273</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 18:52:11 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 07:54:49 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models</title>
|
<title>AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents</title>
|
||||||
<link>https://arxiv.org/abs/2501.01423</link>
|
<link>https://arxiv.org/abs/2512.23343</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01423.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingfeng Yao, Xinggang Wang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual tokenizers improves reconstruction quality, it requires substantially larger diffusion models and more training iterations to achieve comparable generation performance. Consequently, existing systems often settle for sub-optimal solutions, either producing visual artifacts due to information loss within tokenizers or failing to converge fully due to expensive computation costs. We argue that this dilemma stems from the inherent difficulty in learning unconstrained high-dimensional latent spaces. To address this, we propose aligning the latent space with pre-trained vision foundation models when training the visual tokenizers. Our proposed VA-VAE (Vision foundation model Aligned Variational AutoEncoder) significantly expands the reconstruction-generation frontier of latent diffusion models, enabling faster convergence of Diffusion Transformers (DiT) in high-dimensional latent spaces. To exploit the full potential of VA-VAE, we build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT. The integrated system achieves state-of-the-art (SOTA) performance on ImageNet 256x256 generation with an FID score of 1.35 while demonstrating remarkable training efficiency by reaching an FID score of 2.11 in just 64 epochs--representing an over 21 times convergence speedup compared to the original DiT. Models and codes are available at: https://github.com/hustvl/LightningDiT.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23343.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiafeng Liang, Hao Li, Chang Li, Jiaqi Zhou, Shixin Jiang, Zekun Wang, Changkai Ji, Zhihao Zhu, Runxuan Liu, Tao Ren, Jinlan Fu, See-Kiong Ng, Xia Liang, Ming Liu, Bing Qin</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Memory serves as the pivotal nexus bridging past and future, providing both humans and AI systems with invaluable concepts and experience to navigate complex tasks. Recent research on autonomous agents has increasingly focused on designing efficient memory workflows by drawing on cognitive neuroscience. However, constrained by interdisciplinary barriers, existing works struggle to assimilate the essence of human memory mechanisms. To bridge this gap, we systematically synthesizes interdisciplinary knowledge of memory, connecting insights from cognitive neuroscience with LLM-driven agents. Specifically, we first elucidate the definition and function of memory along a progressive trajectory from cognitive neuroscience through LLMs to agents. We then provide a comparative analysis of memory taxonomy, storage mechanisms, and the complete management lifecycle from both biological and artificial perspectives. Subsequently, we review the mainstream benchmarks for evaluating agent memory. Additionally, we explore memory security from dual perspectives of attack and defense. Finally, we envision future research directions, with a focus on multimodal memory systems and skill acquisition.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01423</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23343</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 18:59:40 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 10:01:32 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>Unifying Specialized Visual Encoders for Video Language Models</title>
|
<title>A unified framework for detecting point and collective anomalies in operating system logs via collaborative transformers</title>
|
||||||
<link>https://arxiv.org/abs/2501.01426</link>
|
<link>https://arxiv.org/abs/2512.23380</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01426.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jihoon Chung, Tyler Zhu, Max Gonzalez Saez-Diez, Juan Carlos Niebles, Honglu Zhou, Olga Russakovsky</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all of their visual processing, which limits the amount and type of visual information that can be conveyed to the LLM. Our method, MERV, Multi-Encoder Representation of Videos, instead leverages multiple frozen visual encoders to create a unified representation of a video, providing the VideoLLM with a comprehensive set of specialized visual knowledge. Spatio-temporally aligning the features from each encoder allows us to tackle a wider range of open-ended and multiple-choice video understanding questions and outperform prior state-of-the-art works. MERV is up to 3.7% better in accuracy than Video-LLaVA across the standard suite video understanding benchmarks, while also having a better Video-ChatGPT score. We also improve upon SeViLA, the previous best on zero-shot Perception Test accuracy, by 2.2%. MERV introduces minimal extra parameters and trains faster than equivalent single-encoder methods while parallelizing the visual processing. Finally, we provide qualitative evidence that MERV successfully captures domain knowledge from each of its encoders. Our results offer promising directions in utilizing multiple vision encoders for comprehensive video understanding.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23380.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mohammad Nasirzadeh, Jafar Tahmoresnezhad, Parviz Rashidi-Khazaee</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> Log anomaly detection is crucial for preserving the security of operating systems. Depending on the source of log data collection, various information is recorded in logs that can be considered log modalities. In light of this intuition, unimodal methods often struggle by ignoring the different modalities of log data. Meanwhile, multimodal methods fail to handle the interactions between these modalities. Applying multimodal sentiment analysis to log anomaly detection, we propose CoLog, a framework that collaboratively encodes logs utilizing various modalities. CoLog utilizes collaborative transformers and multi-head impressed attention to learn interactions among several modalities, ensuring comprehensive anomaly detection. To handle the heterogeneity caused by these interactions, CoLog incorporates a modality adaptation layer, which adapts the representations from different log modalities. This methodology enables CoLog to learn nuanced patterns and dependencies within the data, enhancing its anomaly detection capabilities. Extensive experiments demonstrate CoLog's superiority over existing state-of-the-art methods. Furthermore, in detecting both point and collective anomalies, CoLog achieves a mean precision of 99.63%, a mean recall of 99.59%, and a mean F1 score of 99.61% across seven benchmark datasets for log-based anomaly detection. The comprehensive detection capabilities of CoLog make it highly suitable for cybersecurity, system monitoring, and operational efficiency. CoLog represents a significant advancement in log anomaly detection, providing a sophisticated and effective solution to point and collective anomaly detection through a unified framework and a solution to the complex challenges automatic log data analysis poses. We also provide the implementation of CoLog at https://github.com/NasirzadehMoh/CoLog.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01426</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23380</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 18:59:45 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 11:18:34 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
<item>
|
<item>
|
||||||
<title>VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control</title>
|
<title>Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss</title>
|
||||||
<link>https://arxiv.org/abs/2501.01427</link>
|
<link>https://arxiv.org/abs/2512.23447</link>
|
||||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2501.01427.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanpeng Tu, Hao Luo, Xi Chen, Sihui Ji, Xiang Bai, Hengshuang Zhao</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> Despite significant advancements in video generation, inserting a given object into videos remains a challenging task. The difficulty lies in preserving the appearance details of the reference object and accurately modeling coherent motions at the same time. In this paper, we propose VideoAnydoor, a zero-shot video object insertion framework with high-fidelity detail preservation and precise motion control. Starting from a text-to-video model, we utilize an ID extractor to inject the global identity and leverage a box sequence to control the overall motion. To preserve the detailed appearance and meanwhile support fine-grained motion control, we design a pixel warper. It takes the reference image with arbitrary key-points and the corresponding key-point trajectories as inputs. It warps the pixel details according to the trajectories and fuses the warped features with the diffusion U-Net, thus improving detail preservation and supporting users in manipulating the motion trajectories. In addition, we propose a training strategy involving both videos and static images with a reweight reconstruction loss to enhance insertion quality. VideoAnydoor demonstrates significant superiority over existing methods and naturally supports various downstream applications (e.g., talking head generation, video virtual try-on, multi-region editing) without task-specific fine-tuning.</p></description>
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23447.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ang Lv, Jin Ma, Yiyuan Ma, Siyuan Qiao</p><p><b>Upvotes:</b> 88</p><p><b>Summary:</b> Mixture-of-Experts (MoE) models lack explicit constraints to ensure the router's decisions align well with the experts' capabilities, which ultimately limits model performance. To address this, we propose expert-router coupling (ERC) loss, a lightweight auxiliary loss that tightly couples the router's decisions with expert capabilities. Our approach treats each expert's router embedding as a proxy token for the tokens assigned to that expert, and feeds perturbed router embeddings through the experts to obtain internal activations. The ERC loss enforces two constraints on these activations: (1) Each expert must exhibit higher activation for its own proxy token than for the proxy tokens of any other expert. (2) Each proxy token must elicit stronger activation from its corresponding expert than from any other expert. These constraints jointly ensure that each router embedding faithfully represents its corresponding expert's capability, while each expert specializes in processing the tokens actually routed to it. The ERC loss is computationally efficient, operating only on n^2 activations, where n is the number of experts. This represents a fixed cost independent of batch size, unlike prior coupling methods that scale with the number of tokens (often millions per batch). Through pre-training MoE-LLMs ranging from 3B to 15B parameters and extensive analysis on trillions of tokens, we demonstrate the effectiveness of the ERC loss. Moreover, the ERC loss offers flexible control and quantitative tracking of expert specialization levels during training, providing valuable insights into MoEs.</p></description>
|
||||||
<guid isPermaLink="false">https://arxiv.org/abs/2501.01427</guid>
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23447</guid>
|
||||||
<pubDate>Thu, 02 Jan 2025 18:59:54 +0000</pubDate>
|
<pubDate>Mon, 29 Dec 2025 13:03:18 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Act2Goal: From World Model To General Goal-conditioned Policy</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23541</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23541.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Pengfei Zhou, Liliang Chen, Shengcong Chen, Di Chen, Wenzhi Zhao, Rongjun Jin, Guanghui Ren, Jianlan Luo</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Specifying robotic manipulation tasks in a manner that is both expressive and precise remains a central challenge. While visual goals provide a compact and unambiguous task specification, existing goal-conditioned policies often struggle with long-horizon manipulation due to their reliance on single-step action prediction without explicit modeling of task progress. We propose Act2Goal, a general goal-conditioned manipulation policy that integrates a goal-conditioned visual world model with multi-scale temporal control. Given a current observation and a target visual goal, the world model generates a plausible sequence of intermediate visual states that captures long-horizon structure. To translate this visual plan into robust execution, we introduce Multi-Scale Temporal Hashing (MSTH), which decomposes the imagined trajectory into dense proximal frames for fine-grained closed-loop control and sparse distal frames that anchor global task consistency. The policy couples these representations with motor control through end-to-end cross-attention, enabling coherent long-horizon behavior while remaining reactive to local disturbances. Act2Goal achieves strong zero-shot generalization to novel objects, spatial layouts, and environments. We further enable reward-free online adaptation through hindsight goal relabeling with LoRA-based finetuning, allowing rapid autonomous improvement without external supervision. Real-robot experiments demonstrate that Act2Goal improves success rates from 30% to 90% on challenging out-of-distribution tasks within minutes of autonomous interaction, validating that goal-conditioned world models with multi-scale temporal control provide structured guidance necessary for robust long-horizon manipulation. Project page: https://act2goal.github.io/</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23541</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 15:28:42 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>ProGuard: Towards Proactive Multimodal Safeguard</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23573</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23573.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaohan Yu, Lijun Li, Chenyang Si, Lu Sheng, Jing Shao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> The rapid evolution of generative models has led to a continuous emergence of multimodal safety risks, exposing the limitations of existing defense methods. To address these challenges, we propose ProGuard, a vision-language proactive guard that identifies and describes out-of-distribution (OOD) safety risks without the need for model adjustments required by traditional reactive approaches. We first construct a modality-balanced dataset of 87K samples, each annotated with both binary safety labels and risk categories under a hierarchical multimodal safety taxonomy, effectively mitigating modality bias and ensuring consistent moderation across text, image, and text-image inputs. Based on this dataset, we train our vision-language base model purely through reinforcement learning (RL) to achieve efficient and concise reasoning. To approximate proactive safety scenarios in a controlled setting, we further introduce an OOD safety category inference task and augment the RL objective with a synonym-bank-based similarity reward that encourages the model to generate concise descriptions for unseen unsafe categories. Experimental results show that ProGuard achieves performance comparable to closed-source large models on binary safety classification, substantially outperforms existing open-source guard models on unsafe content categorization. Most notably, ProGuard delivers a strong proactive moderation ability, improving OOD risk detection by 52.6% and OOD risk description by 64.8%.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23573</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 16:13:23 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23576</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23576.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ethan Chern, Zhulin Hu, Bohao Tang, Jiadi Su, Steffi Chern, Zhijie Deng, Pengfei Liu</p><p><b>Upvotes:</b> 63</p><p><b>Summary:</b> Real-time video generation via diffusion is essential for building general-purpose multimodal interactive AI systems. However, the simultaneous denoising of all video frames with bidirectional attention via an iterative process in diffusion models prevents real-time interaction. While existing distillation methods can make the model autoregressive and reduce sampling steps to mitigate this, they focus primarily on text-to-video generation, leaving the human-AI interaction unnatural and less efficient. This paper targets real-time interactive video diffusion conditioned on a multimodal context, including text, image, and audio, to bridge the gap. Given the observation that the leading on-policy distillation approach Self Forcing encounters challenges (visual artifacts like flickering, black frames, and quality degradation) with multimodal conditioning, we investigate an improved distillation recipe with emphasis on the quality of condition inputs as well as the initialization and schedule for the on-policy optimization. On benchmarks for multimodal-conditioned (audio, image, and text) avatar video generation including HDTF, AVSpeech, and CelebV-HQ, our distilled model matches the visual quality of the full-step, bidirectional baselines of similar or larger size with 20x less inference cost and latency. Further, we integrate our model with audio language models and long-form video inference technique Anchor-Heavy Identity Sinks to build LiveTalk, a real-time multimodal interactive avatar system. System-level evaluation on our curated multi-turn interaction benchmark shows LiveTalk outperforms state-of-the-art models (Sora2, Veo3) in multi-turn video coherence and content quality, while reducing response latency from 1 to 2 minutes to real-time generation, enabling seamless human-AI multimodal interaction.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23576</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 16:17:36 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23646</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23646.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Keda Tao, Wenjie Du, Bohan Yu, Weiqiang Wang, Jian Liu, Huan Wang</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Omnimodal large language models have made significant strides in unifying audio and visual modalities; however, they often lack the fine-grained cross-modal understanding and have difficulty with multimodal alignment. To address these limitations, we introduce OmniAgent, a fully audio-guided active perception agent that dynamically orchestrates specialized tools to achieve more fine-grained audio-visual reasoning. Unlike previous works that rely on rigid, static workflows and dense frame-captioning, this paper demonstrates a paradigm shift from passive response generation to active multimodal inquiry. OmniAgent employs dynamic planning to autonomously orchestrate tool invocation on demand, strategically concentrating perceptual attention on task-relevant cues. Central to our approach is a novel coarse-to-fine audio-guided perception paradigm, which leverages audio cues to localize temporal events and guide subsequent reasoning. Extensive empirical evaluations on three audio-video understanding benchmarks demonstrate that OmniAgent achieves state-of-the-art performance, surpassing leading open-source and proprietary models by substantial margins of 10% - 20% accuracy.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23646</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 17:59:05 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Nested Browser-Use Learning for Agentic Information Seeking</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23647</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23647.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Baixuan Li, Jialong Wu, Wenbiao Yin, Kuan Li, Zhongwang Zhang, Huifeng Yin, Zhengwei Tao, Liwen Zhang, Pengjun Xie, Jingren Zhou, Yong Jiang</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Information-seeking (IS) agents have achieved strong performance across a range of wide and deep search tasks, yet their tool use remains largely restricted to API-level snippet retrieval and URL-based page fetching, limiting access to the richer information available through real browsing. While full browser interaction could unlock deeper capabilities, its fine-grained control and verbose page content returns introduce substantial complexity for ReAct-style function-calling agents. To bridge this gap, we propose Nested Browser-Use Learning (NestBrowse), which introduces a minimal and complete browser-action framework that decouples interaction control from page exploration through a nested structure. This design simplifies agentic reasoning while enabling effective deep-web information acquisition. Empirical results on challenging deep IS benchmarks demonstrate that NestBrowse offers clear benefits in practice. Further in-depth analyses underscore its efficiency and flexibility.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23647</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 17:59:14 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>End-to-End Test-Time Training for Long Context</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23675</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23675.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Arnuv Tandon, Karan Dalal, Xinhao Li, Daniel Koceja, Marcel Rød, Sam Buchanan, Xiaolong Wang, Jure Leskovec, Sanmi Koyejo, Tatsunori Hashimoto, Carlos Guestrin, Jed McCaleb, Yejin Choi, Yu Sun</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention. However, our model continues learning at test time via next-token prediction on the given context, compressing the context it reads into its weights. In addition, we improve the model's initialization for learning at test time via meta-learning at training time. Overall, our method, a form of Test-Time Training (TTT), is End-to-End (E2E) both at test time (via next-token prediction) and training time (via meta-learning), in contrast to previous forms. We conduct extensive experiments with a focus on scaling properties. In particular, for 3B models trained with 164B tokens, our method (TTT-E2E) scales with context length in the same way as Transformer with full attention, while others, such as Mamba 2 and Gated DeltaNet, do not. However, similar to RNNs, TTT-E2E has constant inference latency regardless of context length, making it 2.7 times faster than full attention for 128K context. Our code is publicly available.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23675</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 18:30:14 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Web World Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23676</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23676.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jichen Feng, Yifan Zhang, Chenggong Zhang, Yifu Lu, Shilong Liu, Mengdi Wang</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully generative world models aim for unlimited environments at the expense of controllability and practical engineering. In this work, we introduce the Web World Model (WWM), a middle ground where world state and ``physics'' are implemented in ordinary web code to ensure logical consistency, while large language models generate context, narratives, and high-level decisions on top of this structured latent state. We build a suite of WWMs on a realistic web stack, including an infinite travel atlas grounded in real geography, fictional galaxy explorers, web-scale encyclopedic and narrative worlds, and simulation- and game-like environments. Across these systems, we identify practical design principles for WWMs: separating code-defined rules from model-driven imagination, representing latent state as typed web interfaces, and utilizing deterministic generation to achieve unlimited but structured exploration. Our results suggest that web stacks themselves can serve as a scalable substrate for world models, enabling controllable yet open-ended environments. Project Page: https://github.com/Princeton-AI2-Lab/Web-World-Models.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23676</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 18:31:45 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23703</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huajie Tan, Sixiang Chen, Yijie Xu, Zixiao Wang, Yuheng Ji, Cheng Chi, Yaoxu Lyu, Zhongxia Zhao, Xiansheng Chen, Peterson Co, Shaoxuan Xie, Guocai Yao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The primary obstacle for applying reinforcement learning (RL) to real-world robotics is the design of effective reward functions. While recently learning-based Process Reward Models (PRMs) are a promising direction, they are often hindered by two fundamental limitations: their reward models lack step-aware understanding and rely on single-view perception, leading to unreliable assessments of fine-grained manipulation progress; and their reward shaping procedures are theoretically unsound, often inducing a semantic trap that misguides policy optimization. To address these, we introduce Dopamine-Reward, a novel reward modeling method for learning a general-purpose, step-aware process reward model from multi-view inputs. At its core is our General Reward Model (GRM), trained on a vast 3,400+ hour dataset, which leverages Step-wise Reward Discretization for structural understanding and Multi-Perspective Reward Fusion to overcome perceptual limitations. Building upon Dopamine-Reward, we propose Dopamine-RL, a robust policy learning framework that employs a theoretically-sound Policy-Invariant Reward Shaping method, which enables the agent to leverage dense rewards for efficient self-improvement without altering the optimal policy, thereby fundamentally avoiding the semantic trap. Extensive experiments across diverse simulated and real-world tasks validate our approach. GRM achieves state-of-the-art accuracy in reward assessment, and Dopamine-RL built on GRM significantly improves policy learning efficiency. For instance, after GRM is adapted to a new task in a one-shot manner from a single expert trajectory, the resulting reward model enables Dopamine-RL to improve the policy from near-zero to 95% success with only 150 online rollouts (approximately 1 hour of real robot interaction), while retaining strong generalization across tasks. Project website: https://robo-dopamine.github.io</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23703</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 18:57:44 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23705</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23705.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shaocong Xu, Songlin Wei, Qizhe Wei, Zheng Geng, Hong Li, Licheng Shen, Qianpu Sun, Shu Han, Bin Ma, Bohan Li, Chongjie Ye, Yuhang Zheng, Nan Wang, Saining Zhang, Hao Zhao</p><p><b>Upvotes:</b> 42</p><p><b>Summary:</b> Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monocular depth, causing holes and temporally unstable estimates. Our key observation is that modern video diffusion models already synthesize convincing transparent phenomena, suggesting they have internalized the optical rules. We build TransPhy3D, a synthetic video corpus of transparent/reflective scenes: 11k sequences rendered with Blender/Cycles. Scenes are assembled from a curated bank of category-rich static assets and shape-rich procedural assets paired with glass/plastic/metal materials. We render RGB + depth + normals with physically based ray tracing and OptiX denoising. Starting from a large video diffusion model, we learn a video-to-video translator for depth (and normals) via lightweight LoRA adapters. During training we concatenate RGB and (noisy) depth latents in the DiT backbone and co-train on TransPhy3D and existing frame-wise synthetic datasets, yielding temporally consistent predictions for arbitrary-length input videos. The resulting model, DKT, achieves zero-shot SOTA on real and synthetic video benchmarks involving transparency: ClearPose, DREDS (CatKnown/CatNovel), and TransPhy3D-Test. It improves accuracy and temporal consistency over strong image/video baselines, and a normal variant sets the best video normal estimation results on ClearPose. A compact 1.3B version runs at ~0.17 s/frame. Integrated into a grasping stack, DKT's depth boosts success rates across translucent, reflective and diffuse surfaces, outperforming prior estimators. Together, these results support a broader claim: "Diffusion knows transparency." Generative video priors can be repurposed, efficiently and label-free, into robust, temporally coherent perception for challenging real-world manipulation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23705</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 18:59:24 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Training AI Co-Scientists Using Rubric Rewards</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23707</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23707.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shashwat Goel, Rishi Hazra, Dulhan Jayalath, Timon Willi, Parag Jain, William F. Shen, Ilias Leontiadis, Francesco Barbieri, Yoram Bachrach, Jonas Geiping, Chenxi Whitehouse</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> AI co-scientists are emerging as a tool to assist human researchers in achieving their research goals. A crucial feature of these AI co-scientists is the ability to generate a research plan given a set of aims and constraints. The plan may be used by researchers for brainstorming, or may even be implemented after further refinement. However, language models currently struggle to generate research plans that follow all constraints and implicit requirements. In this work, we study how to leverage the vast corpus of existing research papers to train language models that generate better research plans. We build a scalable, diverse training corpus by automatically extracting research goals and goal-specific grading rubrics from papers across several domains. We then train models for research plan generation via reinforcement learning with self-grading. A frozen copy of the initial policy acts as the grader during training, with the rubrics creating a generator-verifier gap that enables improvements without external human supervision. To validate this approach, we conduct a study with human experts for machine learning research goals, spanning 225 hours. The experts prefer plans generated by our finetuned Qwen3-30B-A3B model over the initial model for 70% of research goals, and approve 84% of the automatically extracted goal-specific grading rubrics. To assess generality, we also extend our approach to research goals from medical papers, and new arXiv preprints, evaluating with a jury of frontier models. Our finetuning yields 12-22% relative improvements and significant cross-domain generalization, proving effective even in problem settings like medical research where execution feedback is infeasible. Together, these findings demonstrate the potential of a scalable, automated training recipe as a step towards improving general AI co-scientists.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23707</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 18:59:33 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23709</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23709.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hau-Shiang Shiu, Chin-Yang Lin, Zhixiang Wang, Chi-Wei Hsiao, Po-Fan Yu, Yu-Chih Chen, Yu-Lun Liu</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Diffusion-based video super-resolution (VSR) methods achieve strong perceptual quality but remain impractical for latency-sensitive settings due to reliance on future frames and expensive multi-step denoising. We propose Stream-DiffVSR, a causally conditioned diffusion framework for efficient online VSR. Operating strictly on past frames, it combines a four-step distilled denoiser for fast inference, an Auto-regressive Temporal Guidance (ARTG) module that injects motion-aligned cues during latent denoising, and a lightweight temporal-aware decoder with a Temporal Processor Module (TPM) that enhances detail and temporal coherence. Stream-DiffVSR processes 720p frames in 0.328 seconds on an RTX4090 GPU and significantly outperforms prior diffusion-based methods. Compared with the online SOTA TMP, it boosts perceptual quality (LPIPS +0.095) while reducing latency by over 130x. Stream-DiffVSR achieves the lowest latency reported for diffusion-based VSR, reducing initial delay from over 4600 seconds to 0.328 seconds, thereby making it the first diffusion VSR method suitable for low-latency online deployment. Project page: https://jamichss.github.io/stream-diffvsr-project-page/</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23709</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 18:59:57 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Pretraining Frame Preservation in Autoregressive Video Memory Compression</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23851</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23851.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lvmin Zhang, Shengqu Cai, Muyang Li, Chong Zeng, Beijia Lu, Anyi Rao, Song Han, Gordon Wetzstein, Maneesh Agrawala</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> We present PFP, a neural network structure to compress long videos into short contexts, with an explicit pretraining objective to preserve the high-frequency details of single frames at arbitrary temporal positions. The baseline model can compress a 20-second video into a context at about 5k length, where random frames can be retrieved with perceptually preserved appearances. Such pretrained models can be directly fine-tuned as memory encoders for autoregressive video models, enabling long history memory with low context cost and relatively low fidelity loss. We evaluate the framework with ablative settings and discuss the trade-offs of possible neural architecture designs.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23851</guid>
|
||||||
|
<pubDate>Mon, 29 Dec 2025 20:29:21 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23959</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23959.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chulun Zhou, Chunkang Zhang, Guoxin Yu, Fandong Meng, Jie Zhou, Wai Lam, Mo Yu</p><p><b>Upvotes:</b> 83</p><p><b>Summary:</b> Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Many RAG systems incorporate a working memory module to consolidate retrieved information. However, existing memory designs function primarily as passive storage that accumulates isolated facts for the purpose of condensing the lengthy inputs and generating new sub-queries through deduction. This static nature overlooks the crucial high-order correlations among primitive facts, the compositions of which can often provide stronger guidance for subsequent steps. Therefore, their representational strength and impact on multi-step reasoning and knowledge evolution are limited, resulting in fragmented reasoning and weak global sense-making capacity in extended contexts. We introduce HGMem, a hypergraph-based memory mechanism that extends the concept of memory beyond simple storage into a dynamic, expressive structure for complex reasoning and global understanding. In our approach, memory is represented as a hypergraph whose hyperedges correspond to distinct memory units, enabling the progressive formation of higher-order interactions within memory. This mechanism connects facts and thoughts around the focal problem, evolving into an integrated and situated knowledge structure that provides strong propositions for deeper reasoning in subsequent steps. We evaluate HGMem on several challenging datasets designed for global sense-making. Extensive experiments and in-depth analyses show that our method consistently improves multi-step RAG and substantially outperforms strong baseline systems across diverse tasks.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23959</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 03:13:10 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.23988</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.23988.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenyu Zhang, Shujian Zhang, John Lambert, Wenxuan Zhou, Zhangyang Wang, Mingqing Chen, Andrew Hard, Rajiv Mathews, Lun Wang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Despite the growing reasoning capabilities of recent large language models (LLMs), their internal mechanisms during the reasoning process remain underexplored. Prior approaches often rely on human-defined concepts (e.g., overthinking, reflection) at the word level to analyze reasoning in a supervised manner. However, such methods are limited, as it is infeasible to capture the full spectrum of potential reasoning behaviors, many of which are difficult to define in token space. In this work, we propose an unsupervised framework (namely, RISE: Reasoning behavior Interpretability via Sparse auto-Encoder) for discovering reasoning vectors, which we define as directions in the activation space that encode distinct reasoning behaviors. By segmenting chain-of-thought traces into sentence-level 'steps' and training sparse auto-encoders (SAEs) on step-level activations, we uncover disentangled features corresponding to interpretable behaviors such as reflection and backtracking. Visualization and clustering analyses show that these behaviors occupy separable regions in the decoder column space. Moreover, targeted interventions on SAE-derived vectors can controllably amplify or suppress specific reasoning behaviors, altering inference trajectories without retraining. Beyond behavior-specific disentanglement, SAEs capture structural properties such as response length, revealing clusters of long versus short reasoning traces. More interestingly, SAEs enable the discovery of novel behaviors beyond human supervision. We demonstrate the ability to control response confidence by identifying confidence-related vectors in the SAE decoder space. These findings underscore the potential of unsupervised latent discovery for both interpreting and controllably steering reasoning in LLMs.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.23988</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 05:09:11 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>TESO Tabu Enhanced Simulation Optimization for Noisy Black Box Problems</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24007</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24007.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bulent Soykan, Sean Mondesire, Ghaith Rabadi</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Simulation optimization (SO) is frequently challenged by noisy evaluations, high computational costs, and complex, multimodal search landscapes. This paper introduces Tabu-Enhanced Simulation Optimization (TESO), a novel metaheuristic framework integrating adaptive search with memory-based strategies. TESO leverages a short-term Tabu List to prevent cycling and encourage diversification, and a long-term Elite Memory to guide intensification by perturbing high-performing solutions. An aspiration criterion allows overriding tabu restrictions for exceptional candidates. This combination facilitates a dynamic balance between exploration and exploitation in stochastic environments. We demonstrate TESO's effectiveness and reliability using an queue optimization problem, showing improved performance compared to benchmarks and validating the contribution of its memory components. Source code and data are available at: https://github.com/bulentsoykan/TESO.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24007</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 06:03:37 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Factorized Learning for Temporally Grounded Video-Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24097</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24097.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenzheng Zeng, Difei Gao, Mike Zheng Shou, Hwee Tou Ng</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Recent video-language models have shown great potential for video understanding, but still struggle with accurate temporal grounding for event-level perception. We observe that two main factors in video understanding (i.e., temporal grounding and textual response) form a logical hierarchy: accurate temporal evidence grounding lays the foundation for reliable textual response. However, existing works typically handle these two tasks in a coupled manner without a clear logical structure, leading to sub-optimal objectives. We address this from a factorized learning perspective. We first propose D^2VLM, a framework that decouples the learning of these two tasks while also emphasizing their inherent dependency. We adopt a "grounding then answering with evidence referencing" paradigm and introduce evidence tokens for evidence grounding, which emphasize event-level visual semantic capture beyond the focus on timestamp representation in existing works. To further facilitate the learning of these two tasks, we introduce a novel factorized preference optimization (FPO) algorithm. Unlike standard preference optimization, FPO explicitly incorporates probabilistic temporal grounding modeling into the optimization objective, enabling preference learning for both temporal grounding and textual response. We also construct a synthetic dataset to address the lack of suitable datasets for factorized preference learning with explicit temporal grounding. Experiments on various tasks demonstrate the clear advantage of our approach. Our source code is available at https://github.com/nusnlp/d2vlm.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24097</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 09:13:20 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24165</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24165.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zefeng He, Xiaoye Qu, Yafu Li, Tong Zhu, Siyuan Huang, Yu Cheng</p><p><b>Upvotes:</b> 41</p><p><b>Summary:</b> While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leading to suboptimal performance in complex long-horizon, vision-centric tasks. In this paper, we establish a novel Generative Multimodal Reasoning paradigm and introduce DiffThinker, a diffusion-based reasoning framework. Conceptually, DiffThinker reformulates multimodal reasoning as a native generative image-to-image task, achieving superior logical consistency and spatial precision in vision-centric tasks. We perform a systematic comparison between DiffThinker and MLLMs, providing the first in-depth investigation into the intrinsic characteristics of this paradigm, revealing four core properties: efficiency, controllability, native parallelism, and collaboration. Extensive experiments across four domains (sequential planning, combinatorial optimization, constraint satisfaction, and spatial configuration) demonstrate that DiffThinker significantly outperforms leading closed source models including GPT-5 (+314.2\%) and Gemini-3-Flash (+111.6\%), as well as the fine-tuned Qwen3-VL-32B baseline (+39.0\%), highlighting generative multimodal reasoning as a promising approach for vision-centric reasoning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24165</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 11:51:18 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Guiding a Diffusion Transformer with the Internal Dynamics of Itself</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24176</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24176.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingyu Zhou, Qifan Li, Xiaobin Hu, Hai Chen, Shuhang Gu</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The diffusion model presents a powerful ability to capture the entire (conditional) data distribution. However, due to the lack of sufficient training and data to learn to cover low-probability areas, the model will be penalized for failing to generate high-quality images corresponding to these areas. To achieve better generation quality, guidance strategies such as classifier free guidance (CFG) can guide the samples to the high-probability areas during the sampling stage. However, the standard CFG often leads to over-simplified or distorted samples. On the other hand, the alternative line of guiding diffusion model with its bad version is limited by carefully designed degradation strategies, extra training and additional sampling steps. In this paper, we proposed a simple yet effective strategy Internal Guidance (IG), which introduces an auxiliary supervision on the intermediate layer during training process and extrapolates the intermediate and deep layer's outputs to obtain generative results during sampling process. This simple strategy yields significant improvements in both training efficiency and generation quality on various baselines. On ImageNet 256x256, SiT-XL/2+IG achieves FID=5.31 and FID=1.75 at 80 and 800 epochs. More impressively, LightningDiT-XL/1+IG achieves FID=1.34 which achieves a large margin between all of these methods. Combined with CFG, LightningDiT-XL/1+IG achieves the current state-of-the-art FID of 1.19.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24176</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 12:16:46 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>GR-Dexter Technical Report</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24210</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24210.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoshi Wen, Guangzeng Chen, Zhongren Cui, Min Du, Yang Gou, Zhigang Han, Liqun Huang, Mingyu Lei, Yunfei Li, Zhuohang Li, Wenlei Liu, Yuxiao Liu, Xiao Ma, Hao Niu, Yutao Ouyang, Zeyu Ren, Haixin Shi, Wei Xu, Haoxiang Zhang, Jiajun Zhang, Xiao Zhang, Liwei Zheng, Weiheng Zhong, Yifei Zhou, Zhengming Zhu, Hang Li</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Vision-language-action (VLA) models have enabled language-conditioned, long-horizon robot manipulation, but most existing systems are limited to grippers. Scaling VLA policies to bimanual robots with high degree-of-freedom (DoF) dexterous hands remains challenging due to the expanded action space, frequent hand-object occlusions, and the cost of collecting real-robot data. We present GR-Dexter, a holistic hardware-model-data framework for VLA-based generalist manipulation on a bimanual dexterous-hand robot. Our approach combines the design of a compact 21-DoF robotic hand, an intuitive bimanual teleoperation system for real-robot data collection, and a training recipe that leverages teleoperated robot trajectories together with large-scale vision-language and carefully curated cross-embodiment datasets. Across real-world evaluations spanning long-horizon everyday manipulation and generalizable pick-and-place, GR-Dexter achieves strong in-domain performance and improved robustness to unseen objects and unseen instructions. We hope GR-Dexter serves as a practical step toward generalist dexterous-hand robotic manipulation.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24210</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 13:22:16 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Figure It Out: Improving the Frontier of Reasoning with Active Visual Thinking</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24297</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24297.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Meiqi Chen, Fandong Meng, Jie Zhou</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Complex reasoning problems often involve implicit spatial, geometric, and structural relationships that are not explicitly encoded in text. While recent reasoning models have achieved strong performance across many domains, purely text-based reasoning struggles to represent global structural constraints in complex settings. In this paper, we introduce FIGR, which integrates active visual thinking into multi-turn reasoning via end-to-end reinforcement learning. FIGR externalizes intermediate structural hypotheses by constructing visual representations during problem solving. By adaptively regulating when and how visual reasoning should be invoked, FIGR enables more stable and coherent reasoning over global structural properties that are difficult to capture from text alone. Experiments on challenging mathematical reasoning benchmarks demonstrate that FIGR outperforms strong text-only chain-of-thought baselines. In particular, FIGR improves the base model by 13.12% on AIME 2025 and 11.00% on BeyondAIME, highlighting the effectiveness of figure-guided multimodal reasoning in enhancing the stability and reliability of complex reasoning.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24297</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 15:39:11 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24385</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24385.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Song Wang, Lingdong Kong, Xiaolu Liu, Hao Shi, Wentong Li, Jianke Zhu, Steven C. H. Hoi</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> The rapid advancement of autonomous systems, including self-driving vehicles and drones, has intensified the need to forge true Spatial Intelligence from multi-modal onboard sensor data. While foundation models excel in single-modal contexts, integrating their capabilities across diverse sensors like cameras and LiDAR to create a unified understanding remains a formidable challenge. This paper presents a comprehensive framework for multi-modal pre-training, identifying the core set of techniques driving progress toward this goal. We dissect the interplay between foundational sensor characteristics and learning strategies, evaluating the role of platform-specific datasets in enabling these advancements. Our central contribution is the formulation of a unified taxonomy for pre-training paradigms: ranging from single-modality baselines to sophisticated unified frameworks that learn holistic representations for advanced tasks like 3D object detection and semantic occupancy prediction. Furthermore, we investigate the integration of textual inputs and occupancy representations to facilitate open-world perception and planning. Finally, we identify critical bottlenecks, such as computational efficiency and model scalability, and propose a roadmap toward general-purpose multi-modal foundation models capable of achieving robust Spatial Intelligence for real-world deployment.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24385</guid>
|
||||||
|
<pubDate>Tue, 30 Dec 2025 17:58:01 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24551</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24551.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanhao Cai, Kunpeng Li, Menglin Jia, Jialiang Wang, Junzhe Sun, Feng Liang, Weifeng Chen, Felix Juefei-Xu, Chu Wang, Ali Thabet, Xiaoliang Dai, Xuan Ju, Alan Yuille, Ji Hou</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension struggle to generalize beyond simple simulated environments or learn implicit physical reasoning. The scarcity of training data with rich physics interactions and phenomena is also a problem. In this paper, we first introduce a Physics-Augmented video data construction Pipeline, PhyAugPipe, that leverages a vision-language model (VLM) with chain-of-thought reasoning to collect a large-scale training dataset, PhyVidGen-135K. Then we formulate a principled Physics-aware Groupwise Direct Preference Optimization, PhyGDPO, framework that builds upon the groupwise Plackett-Luce probabilistic model to capture holistic preferences beyond pairwise comparisons. In PhyGDPO, we design a Physics-Guided Rewarding (PGR) scheme that embeds VLM-based physics rewards to steer optimization toward physical consistency. We also propose a LoRA-Switch Reference (LoRA-SR) scheme that eliminates memory-heavy reference duplication for efficient training. Experiments show that our method significantly outperforms state-of-the-art open-source methods on PhyGenBench and VideoPhy2. Please check our project page at https://caiyuanhao1998.github.io/project/PhyGDPO for more video results. Our code, models, and data will be released at https://github.com/caiyuanhao1998/Open-PhyGDPO</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24551</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 01:19:14 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24617</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24617.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingwei Qu, Shaowen Wang, Zihao Huang, Kai Hua, Fan Yin, Rui-Jie Zhu, Jundong Zhou, Qiyang Min, Zihao Wang, Yizhi Li, Tianyu Zhang, He Xing, Zheng Zhang, Yuxuan Song, Tianyu Zheng, Zhiyuan Zeng, Chenghua Lin, Ge Zhang, Wenhao Huang</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating computation to semantically critical transitions. We propose Dynamic Large Concept Models (DLCM), a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts computation from tokens to a compressed concept space where reasoning is more efficient. DLCM discovers variable-length concepts end-to-end without relying on predefined linguistic units. Hierarchical compression fundamentally changes scaling behavior. We introduce the first compression-aware scaling law, which disentangles token-level capacity, concept-level reasoning capacity, and compression ratio, enabling principled compute allocation under fixed FLOPs. To stably train this heterogeneous architecture, we further develop a decoupled μP parametrization that supports zero-shot hyperparameter transfer across widths and compression regimes. At a practical setting (R=4, corresponding to an average of four tokens per concept), DLCM reallocates roughly one-third of inference compute into a higher-capacity reasoning backbone, achieving a +2.69\% average improvement across 12 zero-shot benchmarks under matched inference FLOPs.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24617</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 04:19:33 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24618</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24618.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junru Lu, Jiarui Qin, Lingfeng Qiao, Yinghui Li, Xinyi Dai, Bo Ke, Jianfeng He, Ruizhi Qiao, Di Yin, Xing Sun, Yunsheng Wu, Yinsong Liu, Shuangyin Liu, Mingkong Tang, Haodong Lin, Jiayi Kuang, Fanxu Meng, Xiaojuan Tang, Yunjia Xi, Junjie Huang, Haotong Yang, Zhenyi Shen, Yangning Li, Qianwen Zhang, Yifei Yu, Siyu An, Junnan Dong, Qiufeng Wang, Jie Wang, Keyu Chen, Wei Wen, Taian Guo, Zhifeng Shen, Daohai Yu, Jiahao Li, Ke Li, Zongyi Li, Xiaoyu Tan</p><p><b>Upvotes:</b> 104</p><p><b>Summary:</b> We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that rely on distillation, Youtu-LLM (1.96B) is pre-trained from scratch to systematically cultivate reasoning and planning capabilities. The key technical advancements are as follows: (1) Compact Architecture with Long-Context Support: Built on a dense Multi-Latent Attention (MLA) architecture with a novel STEM-oriented vocabulary, Youtu-LLM supports a 128k context window. This design enables robust long-context reasoning and state tracking within a minimal memory footprint, making it ideal for long-horizon agent and reasoning tasks. (2) Principled "Commonsense-STEM-Agent" Curriculum: We curated a massive corpus of approximately 11T tokens and implemented a multi-stage training strategy. By progressively shifting the pre-training data distribution from general commonsense to complex STEM and agentic tasks, we ensure the model acquires deep cognitive abilities rather than superficial alignment. (3) Scalable Agentic Mid-training: Specifically for the agentic mid-training, we employ diverse data construction schemes to synthesize rich and varied trajectories across math, coding, and tool-use domains. This high-quality data enables the model to internalize planning and reflection behaviors effectively. Extensive evaluations show that Youtu-LLM sets a new state-of-the-art for sub-2B LLMs. On general benchmarks, it achieves competitive performance against larger models, while on agent-specific tasks, it significantly surpasses existing SOTA baselines, demonstrating that lightweight models can possess strong intrinsic agentic capabilities.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24618</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 04:25:11 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24724</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24724.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jibin Song, Mingi Kwon, Jaeseok Jeong, Youngjung Uh</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> In this work, we show that the impact of model capacity varies across timesteps: it is crucial for the early and late stages but largely negligible during the intermediate stage. Accordingly, we propose FlowBlending, a stage-aware multi-model sampling strategy that employs a large model and a small model at capacity-sensitive stages and intermediate stages, respectively. We further introduce simple criteria to choose stage boundaries and provide a velocity-divergence analysis as an effective proxy for identifying capacity-sensitive regions. Across LTX-Video (2B/13B) and WAN 2.1 (1.3B/14B), FlowBlending achieves up to 1.65x faster inference with 57.35% fewer FLOPs, while maintaining the visual fidelity, temporal coherence, and semantic alignment of the large models. FlowBlending is also compatible with existing sampling-acceleration techniques, enabling up to 2x additional speedup. Project page is available at: https://jibin86.github.io/flowblending_project_page.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24724</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 08:41:27 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24766</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24766.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Karthik Dharmarajan, Wenlong Huang, Jiajun Wu, Li Fei-Fei, Ruohan Zhang</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Generative video modeling has emerged as a compelling tool to zero-shot reason about plausible physical interactions for open-world manipulation. Yet, it remains a challenge to translate such human-led motions into the low-level actions demanded by robotic systems. We observe that given an initial image and task instruction, these models excel at synthesizing sensible object motions. Thus, we introduce Dream2Flow, a framework that bridges video generation and robotic control through 3D object flow as an intermediate representation. Our method reconstructs 3D object motions from generated videos and formulates manipulation as object trajectory tracking. By separating the state changes from the actuators that realize those changes, Dream2Flow overcomes the embodiment gap and enables zero-shot guidance from pre-trained video models to manipulate objects of diverse categories-including rigid, articulated, deformable, and granular. Through trajectory optimization or reinforcement learning, Dream2Flow converts reconstructed 3D object flow into executable low-level commands without task-specific demonstrations. Simulation and real-world experiments highlight 3D object flow as a general and scalable interface for adapting video generation models to open-world robotic manipulation. Videos and visualizations are available at https://dream2flow.github.io/.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24766</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 10:25:24 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24873</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24873.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weixun Wang, XiaoXiao Xu, Wanhe An, Fangwen Dai, Wei Gao, Yancheng He, Ju Huang, Qiang Ji, Hanqi Jin, Xiaoyang Li, Yang Li, Zhongwen Li, Shirong Lin, Jiashun Liu, Zenan Liu, Tao Luo, Dilxat Muhtar, Yuanbin Qu, Jiaqiang Shi, Qinghui Sun, Yingshui Tan, Hao Tang, Runze Wang, Yi Wang, Zhaoguo Wang, Yanan Wu, Shaopan Xiong, Binchen Xu, Xander Xu, Yuchi Xu, Qipeng Zhang, Xixia Zhang, Haizhou Zhao, Jie Zhao, Shuaibing Zhao, Baihui Zheng, Jianhui Zheng, Suhang Zheng, Yanni Zhu, Mengze Cai, Kerui Cao, Xitong Chen, Yue Dai, Lifan Du, Tao Feng, Tao He, Jin Hu, Yijie Hu, Ziyu Jiang, Cheng Li, Xiang Li, Jing Liang, Chonghuan Liu, ZhenDong Liu, Haodong Mi, Yanhu Mo, Junjia Ni, Shixin Pei, Jingyu Shen, XiaoShuai Song, Cecilia Wang, Chaofan Wang, Kangyu Wang, Pei Wang, Tao Wang, Wei Wang, Ke Xiao, Mingyu Xu, Tiange Xu, Nan Ya, Siran Yang, Jianan Ye, Yaxing Zang, Duo Zhang, Junbo Zhang, Boren Zheng, Wanxi Deng, Ling Pan, Lin Qu, Wenbo Su, Jiamang Wang, Wei Wang, Hu Wei, Minggang Wu, Cheng Yu, Bing Zhao, Zhicheng Zheng, Bo Zheng</p><p><b>Upvotes:</b> 51</p><p><b>Summary:</b> Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agent LLMs. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME (ROME is Obviously an Agentic Model), an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-based Policy Alignment (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of the ALE infrastructure.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24873</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 14:03:39 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>mHC: Manifold-Constrained Hyper-Connections</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24880</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24880.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenda Xie, Yixuan Wei, Huanqi Cao, Chenggang Zhao, Chengqi Deng, Jiashi Li, Damai Dai, Huazuo Gao, Jiang Chang, Liang Zhao, Shangyan Zhou, Zhean Xu, Zhengyan Zhang, Wangding Zeng, Shengding Hu, Yuqing Wang, Jingyang Yuan, Lean Wang, Wenfeng Liang</p><p><b>Upvotes:</b> 178</p><p><b>Summary:</b> Recently, studies exemplified by Hyper-Connections (HC) have extended the ubiquitous residual connection paradigm established over the past decade by expanding the residual stream width and diversifying connectivity patterns. While yielding substantial performance gains, this diversification fundamentally compromises the identity mapping property intrinsic to the residual connection, which causes severe training instability and restricted scalability, and additionally incurs notable memory access overhead. To address these challenges, we propose Manifold-Constrained Hyper-Connections (mHC), a general framework that projects the residual connection space of HC onto a specific manifold to restore the identity mapping property, while incorporating rigorous infrastructure optimization to ensure efficiency. Empirical experiments demonstrate that mHC is effective for training at scale, offering tangible performance improvements and superior scalability. We anticipate that mHC, as a flexible and practical extension of HC, will contribute to a deeper understanding of topological architecture design and suggest promising directions for the evolution of foundational models.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24880</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 14:16:26 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.24885</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.24885.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hengli Li, Zhaoxin Yu, Qi Shen, Chenxi Li, Mengmeng Wang, Tinglang Wu, Yipeng Kang, Yuxuan Wang, Song-Chun Zhu, Zixia Jia, Zilong Zheng</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Strategic dialogue requires agents to execute distinct dialogue acts, for which belief estimation is essential. While prior work often estimates beliefs accurately, it lacks a principled mechanism to use those beliefs during generation. We bridge this gap by first formalizing two core acts Adversarial and Alignment, and by operationalizing them via probabilistic constraints on what an agent may generate. We instantiate this idea in BEDA, a framework that consists of the world set, the belief estimator for belief estimation, and the conditional generator that selects acts and realizes utterances consistent with the inferred beliefs. Across three settings, Conditional Keeper Burglar (CKBG, adversarial), Mutual Friends (MF, cooperative), and CaSiNo (negotiation), BEDA consistently outperforms strong baselines: on CKBG it improves success rate by at least 5.0 points across backbones and by 20.6 points with GPT-4.1-nano; on Mutual Friends it achieves an average improvement of 9.3 points; and on CaSiNo it achieves the optimal deal relative to all baselines. These results indicate that casting belief estimation as constraints provides a simple, general mechanism for reliable strategic dialogue.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.24885</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 14:26:55 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>Scaling Open-Ended Reasoning to Predict the Future</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.25070</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.25070.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended forecasting questions. To scale up training data, we synthesize novel forecasting questions from global events reported in daily news, using a fully automated, careful curation recipe. We train the Qwen3 thinking models on our dataset, OpenForesight. To prevent leakage of future information during training and evaluation, we use an offline news corpus, both for data generation and retrieval in our forecasting system. Guided by a small validation set, we show the benefits of retrieval, and an improved reward function for reinforcement learning (RL). Once we obtain our final forecasting system, we perform held-out testing between May to August 2025. Our specialized model, OpenForecaster 8B, matches much larger proprietary models, with our training improving the accuracy, calibration, and consistency of predictions. We find calibration improvements from forecasting training generalize across popular benchmarks. We open-source all our models, code, and data to make research on language model forecasting broadly accessible.</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.25070</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 18:59:51 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.25073</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.25073.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yi-Chuan Huang, Hao-Jen Chien, Chin-Yang Lin, Ying-Huan Chen, Yu-Lun Liu</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Recent advances in 3D reconstruction have achieved remarkable progress in high-quality scene capture from dense multi-view imagery, yet struggle when input views are limited. Various approaches, including regularization techniques, semantic priors, and geometric constraints, have been implemented to address this challenge. Latest diffusion-based methods have demonstrated substantial improvements by generating novel views from new camera poses to augment training data, surpassing earlier regularization and prior-based techniques. Despite this progress, we identify three critical limitations in these state-of-the-art approaches: inadequate coverage beyond known view peripheries, geometric inconsistencies across generated views, and computationally expensive pipelines. We introduce GaMO (Geometry-aware Multi-view Outpainter), a framework that reformulates sparse-view reconstruction through multi-view outpainting. Instead of generating new viewpoints, GaMO expands the field of view from existing camera poses, which inherently preserves geometric consistency while providing broader scene coverage. Our approach employs multi-view conditioning and geometry-aware denoising strategies in a zero-shot manner without training. Extensive experiments on Replica and ScanNet++ demonstrate state-of-the-art reconstruction quality across 3, 6, and 9 input views, outperforming prior methods in PSNR and LPIPS, while achieving a 25times speedup over SOTA diffusion-based methods with processing time under 10 minutes. Project page: https://yichuanh.github.io/GaMO/</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.25073</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 18:59:55 +0000</pubDate>
|
||||||
|
</item>
|
||||||
|
<item>
|
||||||
|
<title>SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time</title>
|
||||||
|
<link>https://arxiv.org/abs/2512.25075</link>
|
||||||
|
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.25075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhening Huang, Hyeonho Jeong, Xuelin Chen, Yulia Gryaditskaya, Tuanfeng Y. Wang, Joan Lasenby, Chun-Hao Huang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> We present SpaceTimePilot, a video diffusion model that disentangles space and time for controllable generative rendering. Given a monocular video, SpaceTimePilot can independently alter the camera viewpoint and the motion sequence within the generative process, re-rendering the scene for continuous and arbitrary exploration across space and time. To achieve this, we introduce an effective animation time-embedding mechanism in the diffusion process, allowing explicit control of the output video's motion sequence with respect to that of the source video. As no datasets provide paired videos of the same dynamic scene with continuous temporal variations, we propose a simple yet effective temporal-warping training scheme that repurposes existing multi-view datasets to mimic temporal differences. This strategy effectively supervises the model to learn temporal control and achieve robust space-time disentanglement. To further enhance the precision of dual control, we introduce two additional components: an improved camera-conditioning mechanism that allows altering the camera from the first frame, and CamxTime, the first synthetic space-and-time full-coverage rendering dataset that provides fully free space-time video trajectories within a scene. Joint training on the temporal-warping scheme and the CamxTime dataset yields more precise temporal control. We evaluate SpaceTimePilot on both real-world and synthetic data, demonstrating clear space-time disentanglement and strong results compared to prior work. Project page: https://zheninghuang.github.io/Space-Time-Pilot/ Code: https://github.com/ZheningHuang/spacetimepilot</p></description>
|
||||||
|
<guid isPermaLink="false">https://arxiv.org/abs/2512.25075</guid>
|
||||||
|
<pubDate>Wed, 31 Dec 2025 18:59:57 +0000</pubDate>
|
||||||
</item>
|
</item>
|
||||||
</channel>
|
</channel>
|
||||||
</rss>
|
</rss>
|
||||||
|
|||||||
Reference in New Issue
Block a user