bot: update RSS feed
This commit is contained in:
github-actions[bot]
396
feed.xml
396
feed.xml
@@ -7,286 +7,272 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Wed, 17 Dec 2025 00:02:42 +0000</lastBuildDate>
|
||||
<lastBuildDate>Thu, 18 Dec 2025 00:02:40 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>Inferring Compositional 4D Scenes without Ever Seeing One</title>
|
||||
<link>https://arxiv.org/abs/2512.05272</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05272.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ahmet Berke Gokmen, Ajad Chhatkuli, Luc Van Gool, Danda Pani Paudel</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Scenes in the real world are often composed of several static and dynamic objects. Capturing their 4-dimensional structures, composition and spatio-temporal configuration in-the-wild, though extremely interesting, is equally hard. Therefore, existing works often focus on one object at a time, while relying on some category-specific parametric shape model for dynamic objects. This can lead to inconsistent scene configurations, in addition to being limited to the modeled object categories. We propose COM4D (Compositional 4D), a method that consistently and jointly predicts the structure and spatio-temporal configuration of 4D/3D objects using only static multi-object or dynamic single object supervision. We achieve this by a carefully designed training of spatial and temporal attentions on 2D video input. The training is disentangled into learning from object compositions on the one hand, and single object dynamics throughout the video on the other, thus completely avoiding reliance on 4D compositional training data. At inference time, our proposed attention mixing mechanism combines these independently learned attentions, without requiring any 4D composition examples. By alternating between spatial and temporal reasoning, COM4D reconstructs complete and persistent 4D scenes with multiple interacting objects directly from monocular videos. Furthermore, COM4D provides state-of-the-art results in existing separate problems of 4D object and composed 3D reconstruction despite being purely data-driven.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.05272</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 21:51:47 +0000</pubDate>
|
||||
<title>ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.07328</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.07328.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyang Mai, Yu-Wing Tai</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Text-to-video (T2V) generation has advanced rapidly, yet maintaining consistent character identities across scenes remains a major challenge. Existing personalization methods often focus on facial identity but fail to preserve broader contextual cues such as hairstyle, outfit, and body shape, which are critical for visual coherence. We propose ContextAnyone, a context-aware diffusion framework that achieves character-consistent video generation from text and a single reference image. Our method jointly reconstructs the reference image and generates new video frames, enabling the model to fully perceive and utilize reference information. Reference information is effectively integrated into a DiT-based diffusion backbone through a novel Emphasize-Attention module that selectively reinforces reference-aware features and prevents identity drift across frames. A dual-guidance loss combines diffusion and reference reconstruction objectives to enhance appearance fidelity, while the proposed Gap-RoPE positional embedding separates reference and video tokens to stabilize temporal modeling. Experiments demonstrate that ContextAnyone outperforms existing reference-to-video methods in identity consistency and visual quality, generating coherent and context-preserving character videos across diverse motions and scenes. Project page: https://github.com/ziyang1106/ContextAnyone{https://github.com/ziyang1106/ContextAnyone}.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.07328</guid>
|
||||
<pubDate>Mon, 08 Dec 2025 09:12:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>START: Spatial and Textual Learning for Chart Understanding</title>
|
||||
<link>https://arxiv.org/abs/2512.07186</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.07186.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhuoming Liu, Xiaofeng Gao, Feiyang Niu, Qiaozi Gao, Liu Liu, Robinson Piramuthu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Chart understanding is crucial for deploying multimodal large language models (MLLMs) in real-world scenarios such as analyzing scientific papers and technical reports. Unlike natural images, charts pair a structured visual layout (spatial property) with an underlying data representation (textual property) -- grasping both is essential for precise, fine-grained chart reasoning. Motivated by this observation, we propose START, the Spatial and Textual learning for chART understanding. Specifically, we introduce (i) chart-element grounding and (ii) chart-to-code generation to strengthen an MLLM's understanding of both chart visual layout and data details. To facilitate spatial and textual learning, we propose the START-Dataset generated with a novel data-generation pipeline that first leverages an MLLM to translate real chart images into executable chart code, recovering the underlying data representation while preserving the visual distribution of real-world charts. We then evolve the code with a Large Language Model (LLM) to ascertain the positions of chart elements that capture the chart's visual structure, addressing challenges that existing methods cannot handle. To evaluate a model's ability to understand chart spatial structures, we propose the Chart Spatial understanding Benchmark (CS-Bench), filling a critical gap in comprehensive chart understanding evaluation. Leveraging spatial and textual learning, START delivers consistent gains across model sizes and benchmarks over the base models and surpasses prior state-of-the-art by a clear margin. Code, data and models will be publicly available.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.07186</guid>
|
||||
<pubDate>Mon, 08 Dec 2025 05:43:14 +0000</pubDate>
|
||||
<title>CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates</title>
|
||||
<link>https://arxiv.org/abs/2512.10342</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10342.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shresth Grover, Priyank Pathak, Akash Kumar, Vibhav Vineet, Yogesh S Rawat</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Large-scale Vision-Language Models (VLMs) exhibit impressive complex reasoning capabilities but remain largely unexplored in visual sequential planning, i.e., executing multi-step actions towards a goal. Additionally, practical sequential planning often involves non-optimal (erroneous) steps, challenging VLMs to detect and correct such steps. We propose Corrective Sequential Planning Benchmark (CoSPlan) to evaluate VLMs in error-prone, vision-based sequential planning tasks across 4 domains: maze navigation, block rearrangement, image reconstruction,and object reorganization. CoSPlan assesses two key abilities: Error Detection (identifying non-optimal action) and Step Completion (correcting and completing action sequences to reach the goal). Despite using state-of-the-art reasoning techniques such as Chain-of-Thought and Scene Graphs, VLMs (e.g. Intern-VLM and Qwen2) struggle on CoSPlan, failing to leverage contextual cues to reach goals. Addressing this, we propose a novel training-free method, Scene Graph Incremental updates (SGI), which introduces intermediate reasoning steps between the initial and goal states. SGI helps VLMs reason about sequences, yielding an average performance gain of 5.2%. In addition to enhancing reliability in corrective sequential planning, SGI generalizes to traditional planning tasks such as Plan-Bench and VQA.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.10342</guid>
|
||||
<pubDate>Thu, 11 Dec 2025 06:46:51 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Aesthetic Alignment Risks Assimilation: How Image Generation and Reward Models Reinforce Beauty Bias and Ideological "Censorship"</title>
|
||||
<link>https://arxiv.org/abs/2512.11883</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11883.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqi Marshall Guo, Qingyun Qian, Khalad Hasan, Shan Du</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when ``anti-aesthetic" outputs are requested for artistic or critical purposes. This adherence prioritizes developer-centered values, compromising user autonomy and aesthetic pluralism. We test this bias by constructing a wide-spectrum aesthetics dataset and evaluating state-of-the-art generation and reward models. We find that aesthetic-aligned generation models frequently default to conventionally beautiful outputs, failing to respect instructions for low-quality or negative imagery. Crucially, reward models penalize anti-aesthetic images even when they perfectly match the explicit user prompt. We confirm this systemic bias through image-to-image editing and evaluation against real abstract artworks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.11883</guid>
|
||||
<pubDate>Tue, 09 Dec 2025 00:24:29 +0000</pubDate>
|
||||
<title>MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation</title>
|
||||
<link>https://arxiv.org/abs/2512.10945</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10945.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Henghui Ding, Chang Liu, Shuting He, Kaining Ying, Xudong Jiang, Chen Change Loy, Yu-Gang Jiang</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> This paper proposes a large-scale multi-modal dataset for referring motion expression video segmentation, focusing on segmenting and tracking target objects in videos based on language description of objects' motions. Existing referring video segmentation datasets often focus on salient objects and use language expressions rich in static attributes, potentially allowing the target object to be identified in a single frame. Such datasets underemphasize the role of motion in both videos and languages. To explore the feasibility of using motion expressions and motion reasoning clues for pixel-level video understanding, we introduce MeViS, a dataset containing 33,072 human-annotated motion expressions in both text and audio, covering 8,171 objects in 2,006 videos of complex scenarios. We benchmark 15 existing methods across 4 tasks supported by MeViS, including 6 referring video object segmentation (RVOS) methods, 3 audio-guided video object segmentation (AVOS) methods, 2 referring multi-object tracking (RMOT) methods, and 4 video captioning methods for the newly introduced referring motion expression generation (RMEG) task. The results demonstrate weaknesses and limitations of existing methods in addressing motion expression-guided video understanding. We further analyze the challenges and propose an approach LMPM++ for RVOS/AVOS/RMOT that achieves new state-of-the-art results. Our dataset provides a platform that facilitates the development of motion expression-guided video understanding algorithms in complex video scenes. The proposed MeViS dataset and the method's source code are publicly available at https://henghuiding.com/MeViS/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.10945</guid>
|
||||
<pubDate>Thu, 11 Dec 2025 18:59:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries</title>
|
||||
<link>https://arxiv.org/abs/2512.08400</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.08400.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Samitha Nuwan Thilakarathna, Ercan Avsar, Martin Mathias Nielsen, Malte Pedersen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Accurate fisheries data are crucial for effective and sustainable marine resource management. With the recent adoption of Electronic Monitoring (EM) systems, more video data is now being collected than can be feasibly reviewed manually. This paper addresses this challenge by developing an optimized deep learning pipeline for automated fish re-identification (Re-ID) using the novel AutoFish dataset, which simulates EM systems with conveyor belts with six similarly looking fish species. We demonstrate that key Re-ID metrics (R1 and mAP@k) are substantially improved by using hard triplet mining in conjunction with a custom image transformation pipeline that includes dataset-specific normalization. By employing these strategies, we demonstrate that the Vision Transformer-based Swin-T architecture consistently outperforms the Convolutional Neural Network-based ResNet-50, achieving peak performance of 41.65% mAP@k and 90.43% Rank-1 accuracy. An in-depth analysis reveals that the primary challenge is distinguishing visually similar individuals of the same species (Intra-species errors), where viewpoint inconsistency proves significantly more detrimental than partial occlusion. The source code and documentation are available at: https://github.com/msamdk/Fish_Re_Identification.git</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.08400</guid>
|
||||
<pubDate>Tue, 09 Dec 2025 09:33:53 +0000</pubDate>
|
||||
<title>Hierarchical Dataset Selection for High-Quality Data Sharing</title>
|
||||
<link>https://arxiv.org/abs/2512.10952</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10952.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaona Zhou, Yingyan Zeng, Ran Jin, Ismini Lourentzou</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The success of modern machine learning hinges on access to high-quality training data. In many real-world scenarios, such as acquiring data from public repositories or sharing across institutions, data is naturally organized into discrete datasets that vary in relevance, quality, and utility. Selecting which repositories or institutions to search for useful datasets, and which datasets to incorporate into model training are therefore critical decisions, yet most existing methods select individual samples and treat all data as equally relevant, ignoring differences between datasets and their sources. In this work, we formalize the task of dataset selection: selecting entire datasets from a large, heterogeneous pool to improve downstream performance under resource constraints. We propose Dataset Selection via Hierarchies (DaSH), a dataset selection method that models utility at both dataset and group (e.g., collections, institutions) levels, enabling efficient generalization from limited observations. Across two public benchmarks (Digit-Five and DomainNet), DaSH outperforms state-of-the-art data selection baselines by up to 26.2% in accuracy, while requiring significantly fewer exploration steps. Ablations show DaSH is robust to low-resource settings and lack of relevant datasets, making it suitable for scalable and adaptive dataset selection in practical multi-source learning workflows.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.10952</guid>
|
||||
<pubDate>Thu, 11 Dec 2025 18:59:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Learning Robot Manipulation from Audio World Models</title>
|
||||
<link>https://arxiv.org/abs/2512.08405</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.08405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fan Zhang, Michael Gienger</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> World models have demonstrated impressive performance on robotic learning tasks. Many such tasks inherently demand multimodal reasoning; for example, filling a bottle with water will lead to visual information alone being ambiguous or incomplete, thereby requiring reasoning over the temporal evolution of audio, accounting for its underlying physical properties and pitch patterns. In this paper, we propose a generative latent flow matching model to anticipate future audio observations, enabling the system to reason about long-term consequences when integrated into a robot policy. We demonstrate the superior capabilities of our system through two manipulation tasks that require perceiving in-the-wild audio or music signals, compared to methods without future lookahead. We further emphasize that successful robot action learning for these tasks relies not merely on multi-modal input, but critically on the accurate prediction of future audio states that embody intrinsic rhythmic patterns.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.08405</guid>
|
||||
<pubDate>Tue, 09 Dec 2025 09:36:51 +0000</pubDate>
|
||||
<title>Unveiling User Perceptions in the Generative AI Era: A Sentiment-Driven Evaluation of AI Educational Apps' Role in Digital Transformation of e-Teaching</title>
|
||||
<link>https://arxiv.org/abs/2512.11934</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11934.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Adeleh Mazaherian, Erfan Nourbakhsh</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The rapid integration of generative artificial intelligence into education has driven digital transformation in e-teaching, yet user perceptions of AI educational apps remain underexplored. This study performs a sentiment-driven evaluation of user reviews from top AI ed-apps on the Google Play Store to assess efficacy, challenges, and pedagogical implications. Our pipeline involved scraping app data and reviews, RoBERTa for binary sentiment classification, GPT-4o for key point extraction, and GPT-5 for synthesizing top positive/negative themes. Apps were categorized into seven types (e.g., homework helpers, math solvers, language tools), with overlaps reflecting multifunctional designs. Results indicate predominantly positive sentiments, with homework apps like Edu AI (95.9% positive) and Answer.AI (92.7%) leading in accuracy, speed, and personalization, while language/LMS apps (e.g., Teacher AI at 21.8% positive) lag due to instability and limited features. Positives emphasize efficiency in brainstorming, problem-solving, and engagement; negatives center on paywalls, inaccuracies, ads, and glitches. Trends show that homework helpers outperform specialized tools, highlighting AI's democratizing potential amid risks of dependency and inequity. The discussion proposes future ecosystems with hybrid AI-human models, VR/AR for immersive learning, and a roadmap for developers (adaptive personalization) and policymakers (monetization regulation for inclusivity). This underscores generative AI's role in advancing e-teaching by enabling ethical refinements that foster equitable, innovative environments. The full dataset is available here(https://github.com/erfan-nourbakhsh/GenAI-EdSent).</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.11934</guid>
|
||||
<pubDate>Fri, 12 Dec 2025 06:24:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer</title>
|
||||
<link>https://arxiv.org/abs/2512.11891</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11891.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Songqiao Hu, Zeyi Liu, Shuang Liu, Jun Cen, Zihan Meng, Xiao He</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical need for simultaneous task compliance and safety assurance, particularly in preventing potential collisions during physical interactions. In this work, we introduce a Vision-Language-Safe Action (VLSA) architecture, named AEGIS, which contains a plug-and-play safety constraint (SC) layer formulated via control barrier functions. AEGIS integrates directly with existing VLA models to improve safety with theoretical guarantees, while maintaining their original instruction-following performance. To evaluate the efficacy of our architecture, we construct a comprehensive safety-critical benchmark SafeLIBERO, spanning distinct manipulation scenarios characterized by varying degrees of spatial complexity and obstacle intervention. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines. Notably, AEGIS achieves a 59.16% improvement in obstacle avoidance rate while substantially increasing the task execution success rate by 17.25%. To facilitate reproducibility and future research, we make our code, models, and the benchmark datasets publicly available at https://vlsa-aegis.github.io/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.11891</guid>
|
||||
<pubDate>Tue, 09 Dec 2025 16:53:44 +0000</pubDate>
|
||||
<title>Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling</title>
|
||||
<link>https://arxiv.org/abs/2512.12675</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12675.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuran Wang, Bohan Zeng, Chengzhuo Tong, Wenxuan Liu, Yang Shi, Xiaochen Ma, Hao Liang, Yuanxing Zhang, Wentao Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to identify and generate the correct subject when inputs contain multiple candidates. This limitation restricts effectiveness in complex, realistic visual settings. We propose Scone, a unified understanding-generation method that integrates composition and distinction. Scone enables the understanding expert to act as a semantic bridge, conveying semantic information and guiding the generation expert to preserve subject identity while minimizing interference. A two-stage training scheme first learns composition, then enhances distinction through semantic alignment and attention-based masking. We also introduce SconeEval, a benchmark for evaluating both composition and distinction across diverse scenarios. Experiments demonstrate that Scone outperforms existing open-source models in composition and distinction tasks on two benchmarks. Our model, benchmark, and training data are available at: https://github.com/Ryann-Ran/Scone.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12675</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 12:58:19 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>KD-OCT: Efficient Knowledge Distillation for Clinical-Grade Retinal OCT Classification</title>
|
||||
<link>https://arxiv.org/abs/2512.09069</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.09069.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Erfan Nourbakhsh, Nasrin Sanjari, Ali Nourbakhsh</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Age-related macular degeneration (AMD) and choroidal neovascularization (CNV)-related conditions are leading causes of vision loss worldwide, with optical coherence tomography (OCT) serving as a cornerstone for early detection and management. However, deploying state-of-the-art deep learning models like ConvNeXtV2-Large in clinical settings is hindered by their computational demands. Therefore, it is desirable to develop efficient models that maintain high diagnostic performance while enabling real-time deployment. In this study, a novel knowledge distillation framework, termed KD-OCT, is proposed to compress a high-performance ConvNeXtV2-Large teacher model, enhanced with advanced augmentations, stochastic weight averaging, and focal loss, into a lightweight EfficientNet-B2 student for classifying normal, drusen, and CNV cases. KD-OCT employs real-time distillation with a combined loss balancing soft teacher knowledge transfer and hard ground-truth supervision. The effectiveness of the proposed method is evaluated on the Noor Eye Hospital (NEH) dataset using patient-level cross-validation. Experimental results demonstrate that KD-OCT outperforms comparable multi-scale or feature-fusion OCT classifiers in efficiency- accuracy balance, achieving near-teacher performance with substantial reductions in model size and inference time. Despite the compression, the student model exceeds most existing frameworks, facilitating edge deployment for AMD screening. Code is available at https://github.com/erfan-nourbakhsh/KD- OCT.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.09069</guid>
|
||||
<pubDate>Tue, 09 Dec 2025 19:34:30 +0000</pubDate>
|
||||
<title>UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction</title>
|
||||
<link>https://arxiv.org/abs/2512.12941</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12941.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Yao, Dongxiu Liu, Taotao Li, Shengjie Li, Wenqi Ren, Xiaochun Cao</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Building extraction from remote sensing images is a challenging task due to the complex structure variations of the buildings. Existing methods employ convolutional or self-attention blocks to capture the multi-scale features in the segmentation models, while the inherent gap of the feature pyramids and insufficient global-local feature integration leads to inaccurate, ambiguous extraction results. To address this issue, in this paper, we present an Uncertainty-Aggregated Global-Local Fusion Network (UAGLNet), which is capable to exploit high-quality global-local visual semantics under the guidance of uncertainty modeling. Specifically, we propose a novel cooperative encoder, which adopts hybrid CNN and transformer layers at different stages to capture the local and global visual semantics, respectively. An intermediate cooperative interaction block (CIB) is designed to narrow the gap between the local and global features when the network becomes deeper. Afterwards, we propose a Global-Local Fusion (GLF) module to complementarily fuse the global and local representations. Moreover, to mitigate the segmentation ambiguity in uncertain regions, we propose an Uncertainty-Aggregated Decoder (UAD) to explicitly estimate the pixel-wise uncertainty to enhance the segmentation accuracy. Extensive experiments demonstrate that our method achieves superior performance to other state-of-the-art methods. Our code is available at https://github.com/Dstate/UAGLNet</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12941</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 02:59:16 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MentraSuite: Post-Training Large Language Models for Mental Health Reasoning and Assessment</title>
|
||||
<link>https://arxiv.org/abs/2512.09636</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.09636.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengxi Xiao, Kailai Yang, Pengde Zhao, Enze Zhang, Ziyan Kuang, Zhiwei Liu, Weiguang Han, Shu Liao, Lianting Huang, Jinpeng Hu, Min Peng, Qianqian Xie, Sophia Ananiadou</p><p><b>Upvotes:</b> 21</p><p><b>Summary:</b> Mental health disorders affect hundreds of millions globally, and the Web now serves as a primary medium for accessing support, information, and assessment. Large language models (LLMs) offer scalable and accessible assistance, yet their deployment in mental-health settings remains risky when their reasoning is incomplete, inconsistent, or ungrounded. Existing psychological LLMs emphasize emotional understanding or knowledge recall but overlook the step-wise, clinically aligned reasoning required for appraisal, diagnosis, intervention planning, abstraction, and verification. To address these issues, we introduce MentraSuite, a unified framework for advancing reliable mental-health reasoning. We propose MentraBench, a comprehensive benchmark spanning five core reasoning aspects, six tasks, and 13 datasets, evaluating both task performance and reasoning quality across five dimensions: conciseness, coherence, hallucination avoidance, task understanding, and internal consistency. We further present Mindora, a post-trained model optimized through a hybrid SFT-RL framework with an inconsistency-detection reward to enforce faithful and coherent reasoning. To support training, we construct high-quality trajectories using a novel reasoning trajectory generation strategy, that strategically filters difficult samples and applies a structured, consistency-oriented rewriting process to produce concise, readable, and well-balanced trajectories. Across 20 evaluated LLMs, Mindora achieves the highest average performance on MentraBench and shows remarkable performances in reasoning reliability, demonstrating its effectiveness for complex mental-health scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.09636</guid>
|
||||
<pubDate>Wed, 10 Dec 2025 13:26:22 +0000</pubDate>
|
||||
<title>Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views</title>
|
||||
<link>https://arxiv.org/abs/2512.12980</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12980.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tingyang Chen, Cong Fu, Jiahua Wu, Haotian Wu, Hua Fan, Xiangyu Ke, Yunjun Gao, Yabo Ni, Anxiang Zeng</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Vector Similarity Search (VSS) in high-dimensional spaces is rapidly emerging as core functionality in next-generation database systems for numerous data-intensive services -- from embedding lookups in large language models (LLMs), to semantic information retrieval and recommendation engines. Current benchmarks, however, evaluate VSS primarily on the recall-latency trade-off against a ground truth defined solely by distance metrics, neglecting how retrieval quality ultimately impacts downstream tasks. This disconnect can mislead both academic research and industrial practice. We present Iceberg, a holistic benchmark suite for end-to-end evaluation of VSS methods in realistic application contexts. From a task-centric view, Iceberg uncovers the Information Loss Funnel, which identifies three principal sources of end-to-end performance degradation: (1) Embedding Loss during feature extraction; (2) Metric Misuse, where distances poorly reflect task relevance; (3) Data Distribution Sensitivity, highlighting index robustness across skews and modalities. For a more comprehensive assessment, Iceberg spans eight diverse datasets across key domains such as image classification, face recognition, text retrieval, and recommendation systems. Each dataset, ranging from 1M to 100M vectors, includes rich, task-specific labels and evaluation metrics, enabling assessment of retrieval algorithms within the full application pipeline rather than in isolation. Iceberg benchmarks 13 state-of-the-art VSS methods and re-ranks them based on application-level metrics, revealing substantial deviations from traditional rankings derived purely from recall-latency evaluations. Building on these insights, we define a set of task-centric meta-features and derive an interpretable decision tree to guide practitioners in selecting and tuning VSS methods for their specific workloads.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12980</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 04:49:33 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge</title>
|
||||
<link>https://arxiv.org/abs/2512.10071</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10071.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junjie Bai, Yu-Wei Chao, Qizhi Chen, Jinwei Gu, Moo Jin Kim, Zhaoshuo Li, Xuan Li, Tsung-Yi Lin, Ming-Yu Liu, Nic Ma, Kaichun Mo, Delin Qu, Shangkun Sun, Hongchi Xia, Fangyin Wei, Xiaohui Zeng</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> The 2025 BEHAVIOR Challenge is designed to rigorously track progress toward solving long-horizon tasks by physical agents in simulated environments. BEHAVIOR-1K focuses on everyday household tasks that people most want robots to assist with and these tasks introduce long-horizon mobile manipulation challenges in realistic settings, bridging the gap between current research and real-world, human-centric applications. This report presents our solution to the 2025 BEHAVIOR Challenge in a very close 2nd place and substantially outperforms the rest of the submissions. Building on π_{0.5}, we focus on systematically building our solution by studying the effects of training techniques and data. Through careful ablations, we show the scaling power in pre-training and post-training phases for competitive performance. We summarize our practical lessons and design recommendations that we hope will provide actionable insights for the broader embodied AI community when adapting powerful foundation models to complex embodied scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.10071</guid>
|
||||
<pubDate>Wed, 10 Dec 2025 20:46:40 +0000</pubDate>
|
||||
<title>TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2512.13106</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shenzhi Yang, Guangcheng Zhu, Xing Zheng, Yingfan MA, Zhongqi Chen, Bowen Song, Weiqiang Wang, Junbo Zhao, Gang Chen, Haobo Wang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs) by leveraging answer-verifiable signals to guide policy optimization, which, however, suffers from high annotation costs. To alleviate this problem, recent work has explored unsupervised RLVR methods that derive rewards solely from the model's internal consistency, such as through entropy and majority voting. While seemingly promising, these methods often suffer from model collapse in the later stages of training, which may arise from the reinforcement of incorrect reasoning patterns in the absence of external supervision. In this work, we investigate a novel semi-supervised RLVR paradigm that utilizes a small labeled set to guide RLVR training on unlabeled samples. Our key insight is that supervised rewards are essential for stabilizing consistency-based training on unlabeled samples, ensuring that only reasoning patterns verified on labeled instances are incorporated into RL training. Technically, we propose an effective policy optimization algorithm, TraPO, that identifies reliable unlabeled samples by matching their learning trajectory similarity to labeled ones. Building on this, TraPO achieves remarkable data efficiency and strong generalization on six widely used mathematical reasoning benchmarks (AIME24/25, AMC, MATH-500, Minerva, and Olympiad) and three out-of-distribution tasks (ARC-c, GPQA-diamond, and MMLU-pro). With only 1K labeled and 3K unlabeled samples, TraPO reaches 42.6% average accuracy, surpassing the best unsupervised method trained on 45K unlabeled samples (38.3%). Notably, when using 4K labeled and 12K unlabeled samples, TraPO even outperforms the fully supervised model trained on the full 45K labeled samples on all benchmarks, while using only 10% of the labeled data. The code is available via https://github.com/ShenzhiYang2000/TRAPO.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13106</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 09:03:45 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models</title>
|
||||
<link>https://arxiv.org/abs/2512.10655</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10655.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tong Zhang, Carlos Hinojosa, Bernard Ghanem</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-time mitigation methods typically manipulate classifier-free guidance (CFG) or perturb prompt embeddings; however, they often struggle to reduce memorization without compromising alignment with the conditioning prompt. We introduce CAPTAIN, a training-free framework that mitigates memorization by directly modifying latent features during denoising. CAPTAIN first applies frequency-based noise initialization to reduce the tendency to replicate memorized patterns early in the denoising process. It then identifies the optimal denoising timesteps for feature injection and localizes memorized regions. Finally, CAPTAIN injects semantically aligned features from non-memorized reference images into localized latent regions, suppressing memorization while preserving prompt fidelity and visual quality. Our experiments show that CAPTAIN achieves substantial reductions in memorization compared to CFG-based baselines while maintaining strong alignment with the intended prompt.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.10655</guid>
|
||||
<pubDate>Thu, 11 Dec 2025 14:01:47 +0000</pubDate>
|
||||
<title>Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?</title>
|
||||
<link>https://arxiv.org/abs/2512.13281</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13281.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiaqi Wang, Weijia Wu, Yi Zhan, Rui Zhao, Ming Hu, James Cheng, Wei Liu, Philip Torr, Kevin Qinghong Lin</p><p><b>Upvotes:</b> 50</p><p><b>Summary:</b> Recent advances in video generation have produced vivid content that are often indistinguishable from real videos, making AI-generated video detection an emerging societal challenge. Prior AIGC detection benchmarks mostly evaluate video without audio, target broad narrative domains, and focus on classification solely. Yet it remains unclear whether state-of-the-art video generation models can produce immersive, audio-paired videos that reliably deceive humans and VLMs. To this end, we introduce Video Reality Test, an ASMR-sourced video benchmark suite for testing perceptual realism under tight audio-visual coupling, featuring the following dimensions: (i) Immersive ASMR video-audio sources. Built on carefully curated real ASMR videos, the benchmark targets fine-grained action-object interactions with diversity across objects, actions, and backgrounds. (ii) Peer-Review evaluation. An adversarial creator-reviewer protocol where video generation models act as creators aiming to fool reviewers, while VLMs serve as reviewers seeking to identify fakeness. Our experimental findings show: The best creator Veo3.1-Fast even fools most VLMs: the strongest reviewer (Gemini 2.5-Pro) achieves only 56\% accuracy (random 50\%), far below that of human experts (81.25\%). Adding audio improves real-fake discrimination, yet superficial cues such as watermarks can still significantly mislead models. These findings delineate the current boundary of video generation realism and expose limitations of VLMs in perceptual fidelity and audio-visual consistency. Our code is available at https://github.com/video-reality-test/video-reality-test.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13281</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 12:41:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>What matters for Representation Alignment: Global Information or Spatial Structure?</title>
|
||||
<link>https://arxiv.org/abs/2512.10794</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10794.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jaskirat Singh, Xingjian Leng, Zongze Wu, Liang Zheng, Richard Zhang, Eli Shechtman, Saining Xie</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target representation matters for generation, its global semantic information (e.g., measured by ImageNet-1K accuracy) or its spatial structure (i.e. pairwise cosine similarity between patch tokens)? Prevalent wisdom holds that stronger global semantic performance leads to better generation as a target representation. To study this, we first perform a large-scale empirical analysis across 27 different vision encoders and different model scales. The results are surprising; spatial structure, rather than global performance, drives the generation performance of a target representation. To further study this, we introduce two straightforward modifications, which specifically accentuate the transfer of spatial information. We replace the standard MLP projection layer in REPA with a simple convolution layer and introduce a spatial normalization layer for the external representation. Surprisingly, our simple method (implemented in <4 lines of code), termed iREPA, consistently improves convergence speed of REPA, across a diverse set of vision encoders, model sizes, and training variants (such as REPA, REPA-E, Meanflow, JiT etc). %, etc. Our work motivates revisiting the fundamental working mechanism of representational alignment and how it can be leveraged for improved training of generative models. The code and project page are available at https://end2end-diffusion.github.io/irepa</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.10794</guid>
|
||||
<pubDate>Thu, 11 Dec 2025 16:39:53 +0000</pubDate>
|
||||
<title>ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement</title>
|
||||
<link>https://arxiv.org/abs/2512.13303</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13303.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhihang Liu, Xiaoyi Bao, Pandeng Li, Junjie Zhou, Zhaohe Liao, Yefei He, Kaixun Jiang, Chen-Wei Xie, Yun Zheng, Hongtao Xie</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> While existing generation and unified models excel at general image generation, they struggle with tasks requiring deep reasoning, planning, and precise data-to-visual mapping abilities beyond general scenarios. To push beyond the existing limitations, we introduce a new and challenging task: creative table visualization, requiring the model to generate an infographic that faithfully and aesthetically visualizes the data from a given table. To address this challenge, we propose ShowTable, a pipeline that synergizes MLLMs with diffusion models via a progressive self-correcting process. The MLLM acts as the central orchestrator for reasoning the visual plan and judging visual errors to provide refined instructions, the diffusion execute the commands from MLLM, achieving high-fidelity results. To support this task and our pipeline, we introduce three automated data construction pipelines for training different modules. Furthermore, we introduce TableVisBench, a new benchmark with 800 challenging instances across 5 evaluation dimensions, to assess performance on this task. Experiments demonstrate that our pipeline, instantiated with different models, significantly outperforms baselines, highlighting its effective multi-modal reasoning, generation, and error correction capabilities.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13303</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 13:21:50 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos</title>
|
||||
<link>https://arxiv.org/abs/2512.10927</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.10927.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yulu Gan, Ligeng Zhu, Dandan Shan, Baifeng Shi, Hongxu Yin, Boris Ivanovic, Song Han, Trevor Darrell, Jitendra Malik, Marco Pavone, Boyi Li</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Motion understanding is fundamental to physical reasoning, enabling models to infer dynamics and predict future states. However, state-of-the-art models still struggle on recent motion benchmarks, primarily due to the scarcity of large-scale, fine-grained motion datasets. Existing motion datasets are often constructed from costly manual annotation, severely limiting scalability. To address this challenge, we introduce FoundationMotion, a fully automated data curation pipeline that constructs large-scale motion datasets. Our approach first detects and tracks objects in videos to extract their trajectories, then leverages these trajectories and video frames with Large Language Models (LLMs) to generate fine-grained captions and diverse question-answer pairs about motion and spatial reasoning. Using datasets produced by this pipeline, we fine-tune open-source models including NVILA-Video-15B and Qwen2.5-7B, achieving substantial improvements in motion understanding without compromising performance on other tasks. Notably, our models outperform strong closed-source baselines like Gemini-2.5 Flash and large open-source models such as Qwen2.5-VL-72B across diverse motion understanding datasets and benchmarks. FoundationMotion thus provides a scalable solution for curating fine-grained motion datasets that enable effective fine-tuning of diverse models to enhance motion understanding and spatial reasoning capabilities.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.10927</guid>
|
||||
<pubDate>Thu, 11 Dec 2025 18:53:15 +0000</pubDate>
|
||||
<title>Differentiable Evolutionary Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2512.13399</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13399.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sitao Cheng, Tianle Li, Xuhan Huang, Xunjian Yin, Difan Zou</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The design of effective reward functions presents a central and often arduous challenge in reinforcement learning (RL), particularly when developing autonomous agents for complex reasoning tasks. While automated reward optimization approaches exist, they typically rely on derivative-free evolutionary heuristics that treat the reward function as a black box, failing to capture the causal relationship between reward structure and task performance. To bridge this gap, we propose Differentiable Evolutionary Reinforcement Learning (DERL), a bilevel framework that enables the autonomous discovery of optimal reward signals. In DERL, a Meta-Optimizer evolves a reward function (i.e., Meta-Reward) by composing structured atomic primitives, guiding the training of an inner-loop policy. Crucially, unlike previous evolution, DERL is differentiable in its metaoptimization: it treats the inner-loop validation performance as a signal to update the Meta-Optimizer via reinforcement learning. This allows DERL to approximate the "meta-gradient" of task success, progressively learning to generate denser and more actionable feedback. We validate DERL across three distinct domains: robotic agent (ALFWorld), scientific simulation (ScienceWorld), and mathematical reasoning (GSM8k, MATH). Experimental results show that DERL achieves state-of-the-art performance on ALFWorld and ScienceWorld, significantly outperforming methods relying on heuristic rewards, especially in out-of-distribution scenarios. Analysis of the evolutionary trajectory demonstrates that DERL successfully captures the intrinsic structure of tasks, enabling selfimproving agent alignment without human intervention.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13399</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 14:50:08 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Flowception: Temporally Expansive Flow Matching for Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.11438</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11438.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tariq Berrada Ifriqi, John Nguyen, Karteek Alahari, Jakob Verbeek, Ricky T. Q. Chen</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive methods, Flowception alleviates error accumulation/drift as the frame insertion mechanism during sampling serves as an efficient compression mechanism to handle long-term context. Compared to full-sequence flows, our method reduces FLOPs for training three-fold, while also being more amenable to local attention variants, and allowing to learn the length of videos jointly with their content. Quantitative experimental results show improved FVD and VBench metrics over autoregressive and full-sequence baselines, which is further validated with qualitative results. Finally, by learning to insert and denoise frames in a sequence, Flowception seamlessly integrates different tasks such as image-to-video generation and video interpolation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.11438</guid>
|
||||
<pubDate>Fri, 12 Dec 2025 10:23:47 +0000</pubDate>
|
||||
<title>Janus: Disaggregating Attention and Experts for Scalable MoE Inference</title>
|
||||
<link>https://arxiv.org/abs/2512.13525</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13525.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhexiang Zhang, Ye Wang, Xiangyu Wang, Yumiao Zhao, Jingzhe Jiang, Qizhen Weng, Shaohuai Shi, Yin Chen, Minchen Yu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Large Mixture-of-Experts (MoE) model inference is challenging due to high resource demands and dynamic workloads. Existing solutions often deploy the entire model as a single monolithic unit, which applies a unified resource configuration to both attention and expert modules despite their different requirements, leading to limited scalability and resource inefficiency. In this paper, we propose Janus, a scalable MoE inference system that disaggregates attention and experts on separate GPU sub-clusters, enabling each module to be managed and scaled independently. Janus incorporates three key designs for efficient, disaggregated MoE inference. First, it proposes an adaptive two-phase communication scheme that exploits intra- and inter-node bandwidth hierarchies for low-latency data exchange. Second, motivated by the memory-bound nature of MoE modules, Janus introduces a lightweight scheduler and implements it as a GPU kernel to balance the number of activated experts across GPUs at minimal overhead, thereby reducing inference latency. Third, Janus performs fine-grained resource management to dynamically adjust expert placement and independently scale attention and MoE resources to improve overall efficiency. Evaluation shows Janus achieves up to 3.9 higher perGPU throughput than state-of-the-art systems while meeting per-token latency requirements.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13525</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 16:53:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Rethinking Expert Trajectory Utilization in LLM Post-training</title>
|
||||
<link>https://arxiv.org/abs/2512.11470</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11470.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Bowen Ding, Yuhan Chen, Jiayang Lv, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> While effective post-training integrates Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), the optimal mechanism for utilizing expert trajectories remains unresolved. We propose the Plasticity-Ceiling Framework to theoretically ground this landscape, decomposing performance into foundational SFT performance and the subsequent RL plasticity. Through extensive benchmarking, we establish the Sequential SFT-then-RL pipeline as the superior standard, overcoming the stability deficits of synchronized approaches. Furthermore, we derive precise scaling guidelines: (1) Transitioning to RL at the SFT Stable or Mild Overfitting Sub-phase maximizes the final ceiling by securing foundational SFT performance without compromising RL plasticity; (2) Refuting ``Less is More'' in the context of SFT-then-RL scaling, we demonstrate that Data Scale determines the primary post-training potential, while Trajectory Difficulty acts as a performance multiplier; and (3) Identifying that the Minimum SFT Validation Loss serves as a robust indicator for selecting the expert trajectories that maximize the final performance ceiling. Our findings provide actionable guidelines for maximizing the value extracted from expert trajectories.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.11470</guid>
|
||||
<pubDate>Fri, 12 Dec 2025 11:13:00 +0000</pubDate>
|
||||
<title>Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models</title>
|
||||
<link>https://arxiv.org/abs/2512.13607</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13607.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boxin Wang, Chankyu Lee, Nayeon Lee, Sheng-Chieh Lin, Wenliang Dai, Yang Chen, Yangyi Chen, Zhuolin Yang, Zihan Liu, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response lengths and verification latency. Such variability complicates the RL infrastructure, slows training, and makes training curriculum (e.g., response length extension) and hyperparameter selection challenging. In this work, we propose cascaded domain-wise reinforcement learning (Cascade RL) to develop general-purpose reasoning models, Nemotron-Cascade, capable of operating in both instruct and deep thinking modes. Departing from conventional approaches that blend heterogeneous prompts from different domains, Cascade RL orchestrates sequential, domain-wise RL, reducing engineering complexity and delivering state-of-the-art performance across a wide range of benchmarks. Notably, RLHF for alignment, when used as a pre-step, boosts the model's reasoning ability far beyond mere preference optimization, and subsequent domain-wise RLVR stages rarely degrade the benchmark performance attained in earlier domains and may even improve it (see an illustration in Figure 1). Our 14B model, after RL, outperforms its SFT teacher, DeepSeek-R1-0528, on LiveCodeBench v5/v6/Pro and achieves silver-medal performance in the 2025 International Olympiad in Informatics (IOI). We transparently share our training and data recipes.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13607</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:02:35 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions</title>
|
||||
<link>https://arxiv.org/abs/2512.11995</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.11995.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chenrui Fan, Yijun Liang, Shweta Bhardwaj, Kwesi Cobbina, Ming Li, Tianyi Zhou</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually require multiple rounds of exploration and reasoning in the visual space. Such visual thinking paths not only provide step-by-step exploration and verification as an AI detective but also produce better interpretations of the final answers. However, these paths are challenging to evaluate due to the large exploration space of intermediate steps. To bridge the gap, we develop an evaluation suite, ``Visual Reasoning with multi-step EXploration (V-REX)'', which is composed of a benchmark of challenging visual reasoning tasks requiring native multi-step exploration and an evaluation protocol. V-REX covers rich application scenarios across diverse domains. V-REX casts the multi-step exploratory reasoning into a Chain-of-Questions (CoQ) and disentangles VLMs' capability to (1) Planning: breaking down an open-ended task by selecting a chain of exploratory questions; and (2) Following: answering curated CoQ sequentially to collect information for deriving the final answer. By curating finite options of questions and answers per step, V-REX achieves a reliable quantitative and fine-grained analysis of the intermediate steps. By assessing SOTA proprietary and open-sourced VLMs, we reveal consistent scaling trends, significant differences between planning and following abilities, and substantial room for improvement in multi-step exploratory reasoning.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.11995</guid>
|
||||
<pubDate>Fri, 12 Dec 2025 19:18:41 +0000</pubDate>
|
||||
<title>Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation</title>
|
||||
<link>https://arxiv.org/abs/2512.13655</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13655.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Richard J. Young</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing, and security analysis. While abliteration techniques enable surgical removal of refusal representations through directional orthogonalization, the relative effectiveness of available implementations remains uncharacterized. This study evaluates four abliteration tools (Heretic, DECCP, ErisForge, FailSpy) across sixteen instruction-tuned models (7B-14B parameters), reporting tool compatibility on all 16 models and quantitative metrics on subsets dictated by tool support. Single-pass methods demonstrated superior capability preservation on the benchmarked subset (avg GSM8K change across three models: ErisForge -0.28 pp; DECCP -0.13 pp), while Bayesian-optimized abliteration produced variable distribution shift (KL divergence: 0.043-1.646) with model-dependent capability impact. These findings provide researchers with evidence-based selection criteria for abliteration tool deployment across diverse model architectures. The principal finding indicates that mathematical reasoning capabilities exhibit the highest sensitivity to abliteration interventions, with GSM8K change ranging from +1.51 pp to -18.81 pp (-26.5% relative) depending on tool selection and model architecture.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13655</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:48:42 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>AutoMV: An Automatic Multi-Agent System for Music Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.12196</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12196.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoxuan Tang, Xinping Lei, Chaoran Zhu, Shiyun Chen, Ruibin Yuan, Yizhi Li, Changjae Oh, Ge Zhang, Wenhao Huang, Emmanouil Benetos, Yang Liu, Jiaheng Liu, Yinghao Ma</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Music-to-Video (M2V) generation for full-length songs faces significant challenges. Existing methods produce short, disjointed clips, failing to align visuals with musical structure, beats, or lyrics, and lack temporal consistency. We propose AutoMV, a multi-agent system that generates full music videos (MVs) directly from a song. AutoMV first applies music processing tools to extract musical attributes, such as structure, vocal tracks, and time-aligned lyrics, and constructs these features as contextual inputs for following agents. The screenwriter Agent and director Agent then use this information to design short script, define character profiles in a shared external bank, and specify camera instructions. Subsequently, these agents call the image generator for keyframes and different video generators for "story" or "singer" scenes. A Verifier Agent evaluates their output, enabling multi-agent collaboration to produce a coherent longform MV. To evaluate M2V generation, we further propose a benchmark with four high-level categories (Music Content, Technical, Post-production, Art) and twelve ine-grained criteria. This benchmark was applied to compare commercial products, AutoMV, and human-directed MVs with expert human raters: AutoMV outperforms current baselines significantly across all four categories, narrowing the gap to professional MVs. Finally, we investigate using large multimodal models as automatic MV judges; while promising, they still lag behind human expert, highlighting room for future work.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12196</guid>
|
||||
<pubDate>Sat, 13 Dec 2025 05:53:50 +0000</pubDate>
|
||||
<title>RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics</title>
|
||||
<link>https://arxiv.org/abs/2512.13660</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13660.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Enshen Zhou, Cheng Chi, Yibo Li, Jingkun An, Jiayuan Zhang, Shanyu Rong, Yi Han, Yuheng Ji, Mengzhen Liu, Pengwei Wang, Zhongyuan Wang, Lu Sheng, Shanghang Zhang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric measurement. However, existing methods struggle with this compositional task. To this end, we propose RoboTracer, a 3D-aware VLM that first achieves both 3D spatial referring and measuring via a universal spatial encoder and a regression-supervised decoder to enhance scale awareness during supervised fine-tuning (SFT). Moreover, RoboTracer advances multi-step metric-grounded reasoning via reinforcement fine-tuning (RFT) with metric-sensitive process rewards, supervising key intermediate perceptual cues to accurately generate spatial traces. To support SFT and RFT training, we introduce TraceSpatial, a large-scale dataset of 30M QA pairs, spanning outdoor/indoor/tabletop scenes and supporting complex reasoning processes (up to 9 steps). We further present TraceSpatial-Bench, a challenging benchmark filling the gap to evaluate spatial tracing. Experimental results show that RoboTracer surpasses baselines in spatial understanding, measuring, and referring, with an average success rate of 79.1%, and also achieves SOTA performance on TraceSpatial-Bench by a large margin, exceeding Gemini-2.5-Pro by 36% accuracy. Notably, RoboTracer can be integrated with various control policies to execute long-horizon, dynamic tasks across diverse robots (UR5, G1 humanoid) in cluttered real-world scenes.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13660</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:52:43 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics</title>
|
||||
<link>https://arxiv.org/abs/2512.12602</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12602.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingdi Lei, Di Zhang, Soujanya Poria</p><p><b>Upvotes:</b> 33</p><p><b>Summary:</b> Linear-time attention and State Space Models (SSMs) promise to solve the quadratic cost bottleneck in long-context language models employing softmax attention. We introduce Error-Free Linear Attention (EFLA), a numerically stable, fully parallelism and generalized formulation of the delta rule. Specifically, we formulate the online learning update as a continuous-time dynamical system and prove that its exact solution is not only attainable but also computable in linear time with full parallelism. By leveraging the rank-1 structure of the dynamics matrix, we directly derive the exact closed-form solution effectively corresponding to the infinite-order Runge-Kutta method. This attention mechanism is theoretically free from error accumulation, perfectly capturing the continuous dynamics while preserving the linear-time complexity. Through an extensive suite of experiments, we show that EFLA enables robust performance in noisy environments, achieving lower language modeling perplexity and superior downstream benchmark performance than DeltaNet without introducing additional parameters. Our work provides a new theoretical foundation for building high-fidelity, scalable linear-time attention models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12602</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 08:51:02 +0000</pubDate>
|
||||
<title>Feedforward 3D Editing via Text-Steerable Image-to-3D</title>
|
||||
<link>https://arxiv.org/abs/2512.13678</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziqi Ma, Hongqiao Chen, Yisong Yue, Georgia Gkioxari</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent progress in image-to-3D has opened up immense possibilities for design, AR/VR, and robotics. However, to use AI-generated 3D assets in real applications, a critical requirement is the capability to edit them easily. We present a feedforward method, Steer3D, to add text steerability to image-to-3D models, which enables editing of generated 3D assets with language. Our approach is inspired by ControlNet, which we adapt to image-to-3D generation to enable text steering directly in a forward pass. We build a scalable data engine for automatic data generation, and develop a two-stage training recipe based on flow-matching training and Direct Preference Optimization (DPO). Compared to competing methods, Steer3D more faithfully follows the language instruction and maintains better consistency with the original 3D asset, while being 2.4x to 28.5x faster. Steer3D demonstrates that it is possible to add a new modality (text) to steer the generation of pretrained image-to-3D generative models with 100k data. Project website: https://glab-caltech.github.io/steer3d/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13678</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:58:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment</title>
|
||||
<link>https://arxiv.org/abs/2512.12692</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12692.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mahir Labib Dihan, Tanzima Hashem, Mohammed Eunus Ali, Md Rizwan Parvez</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> LLM-based agents often operate in a greedy, step-by-step manner, selecting actions solely based on the current observation without considering long-term consequences or alternative paths. This lack of foresight is particularly problematic in web environments, which are only partially observable-limited to browser-visible content (e.g., DOM and UI elements)-where a single misstep often requires complex and brittle navigation to undo. Without an explicit backtracking mechanism, agents struggle to correct errors or systematically explore alternative paths. Tree-search methods provide a principled framework for such structured exploration, but existing approaches lack mechanisms for safe backtracking, making them prone to unintended side effects. They also assume that all actions are reversible, ignoring the presence of irreversible actions-limitations that reduce their effectiveness in realistic web tasks. To address these challenges, we introduce WebOperator, a tree-search framework that enables reliable backtracking and strategic exploration. Our method incorporates a best-first search strategy that ranks actions by both reward estimates and safety considerations, along with a robust backtracking mechanism that verifies the feasibility of previously visited paths before replaying them, preventing unintended side effects. To further guide exploration, WebOperator generates action candidates from multiple, varied reasoning contexts to ensure diverse and robust exploration, and subsequently curates a high-quality action set by filtering out invalid actions pre-execution and merging semantically equivalent ones. Experimental results on WebArena and WebVoyager demonstrate the effectiveness of WebOperator. On WebArena, WebOperator achieves a state-of-the-art 54.6% success rate with gpt-4o, underscoring the critical advantage of integrating strategic foresight with safe execution.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12692</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 13:56:54 +0000</pubDate>
|
||||
<title>Olmo 3</title>
|
||||
<link>https://arxiv.org/abs/2512.13961</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13961.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Team Olmo, Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, David Graham, David Heineman, Dirk Groeneveld, Faeze Brahman, Finbarr Timbers, Hamish Ivison, Jacob Morrison, Jake Poznanski, Kyle Lo, Luca Soldaini, Matt Jordan, Mayee Chen, Michael Noukhovitch, Nathan Lambert, Pete Walsh, Pradeep Dasigi, Robert Berry, Saumya Malik, Saurabh Shah, Scott Geng, Shane Arora, Shashank Gupta, Taira Anderson, Teng Xiao, Tyler Murray, Tyler Romero, Victoria Graf, Akari Asai, Akshita Bhagia, Alexander Wettig, Alisa Liu, Aman Rangapur, Chloe Anastasiades, Costa Huang, Dustin Schwenk, Harsh Trivedi, Ian Magnusson, Jaron Lochner, Jiacheng Liu, Lester James V. Miranda, Maarten Sap, Malia Morgan, Michael Schmitz, Michal Guerquin, Michael Wilson, Regan Huff, Ronan Le Bras, Rui Xin, Rulin Shao, Sam Skjonsberg, Shannon Zejiang Shen, Shuyue Stella Li, Tucker Wilde, Valentina Pyatkin, Will Merrill, Yapei Chang, Yuling Gu, Zhiyuan Zeng, Ashish Sabharwal, Luke Zettlemoyer, Pang Wei Koh, Ali Farhadi, Noah A. Smith, Hannaneh Hajishirzi</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall. This release includes the entire model flow, i.e., the full lifecycle of the family of models, including every stage, checkpoint, data point, and dependency used to build it. Our flagship model, Olmo 3 Think 32B, is the strongest fully-open thinking model released to-date.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13961</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 23:41:48 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents</title>
|
||||
<link>https://arxiv.org/abs/2512.12730</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12730.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingzhe Ding, Shengda Long, Changxin Pu, Huan Zhou, Hongwan Gao, Xiang Gao, Chao He, Yue Hou, Fei Hu, Zhaojian Li, Weiran Shi, Zaiyuan Wang, Daoguang Zan, Chenchen Zhang, Xiaoxu Zhang, Qizhi Chen, Xianfu Cheng, Bo Deng, Qingshui Gu, Kai Hua, Juntao Lin, Pai Liu, Mingchen Li, Xuanguang Pan, Zifan Peng, Yujia Qin, Yong Shan, Zhewen Tan, Weihao Xie, Zihan Wang, Yishuo Yuan, Jiayu Zhang, Enduo Zhao, Yunfei Zhao, He Zhu, Chenyang Zou, Ming Ding, Jianpeng Jiao, Jiaheng Liu, Minghao Liu, Qian Liu, Chongyao Tao, Jian Yang, Tong Yang, Zhaoxiang Zhang, Xinjie Chen, Wenhao Huang, Ge Zhang</p><p><b>Upvotes:</b> 38</p><p><b>Summary:</b> Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior evaluations focus on localized code generation, scaffolded completion, or short-term repair tasks, leaving open the question of whether agents can sustain coherent reasoning, planning, and execution over the extended horizons demanded by real-world repository construction. To address this gap, we present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents. Given only a single natural-language requirements document and an empty workspace, agents must autonomously design the architecture, manage dependencies, implement multi-module logic, and produce a fully installable Python library. Our experiments across state-of-the-art open- and closed-source models reveal that long-horizon repository generation remains largely unsolved: even the strongest agents achieve below 40% average test pass rates and rarely complete an entire repository correctly. Detailed analysis uncovers fundamental long-horizon failure modes, including premature termination, loss of global coherence, fragile cross-file dependencies, and inadequate planning over hundreds of interaction steps. NL2Repo Bench establishes a rigorous, verifiable testbed for measuring sustained agentic competence and highlights long-horizon reasoning as a central bottleneck for the next generation of autonomous coding agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12730</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 15:12:13 +0000</pubDate>
|
||||
<title>Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models</title>
|
||||
<link>https://arxiv.org/abs/2512.14008</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14008.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shufan Li, Jiuxiang Gu, Kangning Liu, Zhe Lin, Zijun Wei, Aditya Grover, Jason Kuen</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, their inference speed remains suboptimal due to the need to repeatedly process redundant masked tokens at every sampling step. In this work, we propose Sparse-LaViDa, a novel modeling framework that dynamically truncates unnecessary masked tokens at each inference step to accelerate MDM sampling. To preserve generation quality, we introduce specialized register tokens that serve as compact representations for the truncated tokens. Furthermore, to ensure consistency between training and inference, we design a specialized attention mask that faithfully matches the truncated sampling procedure during training. Built upon the state-of-the-art unified MDM LaViDa-O, Sparse-LaViDa achieves up to a 2x speedup across diverse tasks including text-to-image generation, image editing, and mathematical reasoning, while maintaining generation quality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14008</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 02:06:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.12751</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12751.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhenya Yang, Zhe Liu, Yuxiang Lu, Liping Hou, Chenxuan Miao, Siyi Peng, Bailan Feng, Xiang Bai, Hengshuang Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Physics-aware driving world model is essential for drive planning, out-of-distribution data synthesis, and closed-loop evaluation. However, existing methods often rely on a single diffusion model to directly map driving actions to videos, which makes learning difficult and leads to physically inconsistent outputs. To overcome these challenges, we propose GenieDrive, a novel framework designed for physics-aware driving video generation. Our approach starts by generating 4D occupancy, which serves as a physics-informed foundation for subsequent video generation. 4D occupancy contains rich physical information, including high-resolution 3D structures and dynamics. To facilitate effective compression of such high-resolution occupancy, we propose a VAE that encodes occupancy into a latent tri-plane representation, reducing the latent size to only 58% of that used in previous methods. We further introduce Mutual Control Attention (MCA) to accurately model the influence of control on occupancy evolution, and we jointly train the VAE and the subsequent prediction module in an end-to-end manner to maximize forecasting accuracy. Together, these designs yield a 7.2% improvement in forecasting mIoU at an inference speed of 41 FPS, while using only 3.47 M parameters. Additionally, a Normalized Multi-View Attention is introduced in the video generation model to generate multi-view driving videos with guidance from our 4D occupancy, significantly improving video quality with a 20.7% reduction in FVD. Experiments demonstrate that GenieDrive enables highly controllable, multi-view consistent, and physics-aware driving video generation.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12751</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 16:23:51 +0000</pubDate>
|
||||
<title>MobileWorldBench: Towards Semantic World Modeling For Mobile Agents</title>
|
||||
<link>https://arxiv.org/abs/2512.14014</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14014.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Aditya Grover</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approaches face practical limitations in GUI settings, where predicting complex visual elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for GUI agents, where state transitions are described in natural language rather than predicting raw pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile GUI agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that significantly improves the world modeling capabilities of VLMs. Finally, we propose a novel framework that integrates VLM world models into the planning framework of mobile agents, demonstrating that semantic world models can directly benefit mobile agents by improving task success rates. The code and dataset is available at https://github.com/jacklishufan/MobileWorld</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14014</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 02:16:42 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence</title>
|
||||
<link>https://arxiv.org/abs/2512.12768</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12768.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianjiao Yu, Xinzhuo Li, Yifan Shen, Yuanzhe Liu, Ismini Lourentzou</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Recent advances in large multimodal models suggest that explicit reasoning mechanisms play a critical role in improving model reliability, interpretability, and cross-modal alignment. While such reasoning-centric approaches have been proven effective in language and vision tasks, their extension to 3D remains underdeveloped. CoRe3D introduces a unified 3D understanding and generation reasoning framework that jointly operates over semantic and spatial abstractions, enabling high-level intent inferred from language to directly guide low-level 3D content formation. Central to this design is a spatially grounded reasoning representation that decomposes 3D latent space into localized regions, allowing the model to reason over geometry in a compositional and procedural manner. By tightly coupling semantic chain-of-thought inference with structured spatial reasoning, CoRe3D produces 3D outputs that exhibit strong local consistency and faithful alignment with linguistic descriptions.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12768</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 17:05:11 +0000</pubDate>
|
||||
<title>OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value</title>
|
||||
<link>https://arxiv.org/abs/2512.14051</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14051.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mengzhang Cai, Xin Gao, Yu Li, Honglin Lin, Zheng Liu, Zhuoshi Pan, Qizhi Pei, Xiaoran Shang, Mengyuan Sun, Zinan Tang, Xiaoyang Wang, Zhanping Zhong, Yun Zhu, Dahua Lin, Conghui He, Lijun Wu</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> The rapid evolution of Large Language Models (LLMs) is predicated on the quality and diversity of post-training datasets. However, a critical dichotomy persists: while models are rigorously benchmarked, the data fueling them remains a black box--characterized by opaque composition, uncertain provenance, and a lack of systematic evaluation. This opacity hinders reproducibility and obscures the causal link between data characteristics and model behaviors. To bridge this gap, we introduce OpenDataArena (ODA), a holistic and open platform designed to benchmark the intrinsic value of post-training data. ODA establishes a comprehensive ecosystem comprising four key pillars: (i) a unified training-evaluation pipeline that ensures fair, open comparisons across diverse models (e.g., Llama, Qwen) and domains; (ii) a multi-dimensional scoring framework that profiles data quality along tens of distinct axes; (iii) an interactive data lineage explorer to visualize dataset genealogy and dissect component sources; and (iv) a fully open-source toolkit for training, evaluation, and scoring to foster data research. Extensive experiments on ODA--covering over 120 training datasets across multiple domains on 22 benchmarks, validated by more than 600 training runs and 40 million processed data points--reveal non-trivial insights. Our analysis uncovers the inherent trade-offs between data complexity and task performance, identifies redundancy in popular benchmarks through lineage tracing, and maps the genealogical relationships across datasets. We release all results, tools, and configurations to democratize access to high-quality data evaluation. Rather than merely expanding a leaderboard, ODA envisions a shift from trial-and-error data curation to a principled science of Data-Centric AI, paving the way for rigorous studies on data mixing laws and the strategic composition of foundation models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14051</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 03:33:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>State over Tokens: Characterizing the Role of Reasoning Tokens</title>
|
||||
<link>https://arxiv.org/abs/2512.12777</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12777.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Mosh Levy, Zohar Elyoseph, Shauli Ravfogel, Yoav Goldberg</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Large Language Models (LLMs) can generate reasoning tokens before their final answer to boost performance on complex tasks. While these sequences seem like human thought processes, empirical evidence reveals that they are not a faithful explanation of the model's actual reasoning process. To address this gap between appearance and function, we introduce the State over Tokens (SoT) conceptual framework. SoT reframes reasoning tokens not as a linguistic narrative, but as an externalized computational state -- the sole persistent information carrier across the model's stateless generation cycles. This explains how the tokens can drive correct reasoning without being a faithful explanation when read as text and surfaces previously overlooked research questions on these tokens. We argue that to truly understand the process that LLMs do, research must move beyond reading the reasoning tokens as text and focus on decoding them as state.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12777</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 17:30:34 +0000</pubDate>
|
||||
<title>Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed</title>
|
||||
<link>https://arxiv.org/abs/2512.14067</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14067.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yonggan Fu, Lexington Whalen, Zhifan Ye, Xin Dong, Shizhe Diao, Jingyu Liu, Chengyue Wu, Hao Zhang, Enze Xie, Song Han, Maksim Khadkevich, Jan Kautz, Yingyan Celine Lin, Pavlo Molchanov</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning efficiency lags behind that of autoregressive (AR) language models when trained from scratch. To this end, we study AR-to-dLM conversion to transform pretrained AR models into efficient dLMs that excel in speed while preserving AR models' task accuracy. We achieve this by identifying limitations in the attention patterns and objectives of existing AR-to-dLM methods and then proposing principles and methodologies for more effective AR-to-dLM conversion. Specifically, we first systematically compare different attention patterns and find that maintaining pretrained AR weight distributions is critical for effective AR-to-dLM conversion. As such, we introduce a continuous pretraining scheme with a block-wise attention pattern, which remains causal across blocks while enabling bidirectional modeling within each block. We find that this approach can better preserve pretrained AR models' weight distributions than fully bidirectional modeling, in addition to its known benefit of enabling KV caching, and leads to a win-win in accuracy and efficiency. Second, to mitigate the training-test gap in mask token distributions (uniform vs. highly left-to-right), we propose a position-dependent token masking strategy that assigns higher masking probabilities to later tokens during training to better mimic test-time behavior. Leveraging this framework, we conduct extensive studies of dLMs' attention patterns, training dynamics, and other design choices, providing actionable insights into scalable AR-to-dLM conversion. These studies lead to the Efficient-DLM family, which outperforms state-of-the-art AR models and dLMs, e.g., our Efficient-DLM 8B achieves +5.4%/+2.7% higher accuracy with 4.5x/2.7x higher throughput compared to Dream 7B and Qwen3 4B, respectively.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14067</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 04:12:17 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning</title>
|
||||
<link>https://arxiv.org/abs/2512.12799</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12799.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhe Liu, Runhui Huang, Rui Yang, Siming Yan, Zining Wang, Lu Hou, Di Lin, Xiang Bai, Hengshuang Zhao</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Although multi-modal large language models (MLLMs) have shown strong capabilities across diverse domains, their application in generating fine-grained 3D perception and prediction outputs in autonomous driving remains underexplored. In this paper, we propose DrivePI, a novel spatial-aware 4D MLLM that serves as a unified Vision-Language-Action (VLA) framework that is also compatible with vision-action (VA) models. Our method jointly performs spatial understanding, 3D perception (i.e., 3D occupancy), prediction (i.e., occupancy flow), and planning (i.e., action outputs) in parallel through end-to-end optimization. To obtain both precise geometric information and rich visual appearance, our approach integrates point clouds, multi-view images, and language instructions within a unified MLLM architecture. We further develop a data engine to generate text-occupancy and text-flow QA pairs for 4D spatial understanding. Remarkably, with only a 0.5B Qwen2.5 model as MLLM backbone, DrivePI as a single unified model matches or exceeds both existing VLA models and specialized VA models. Specifically, compared to VLA models, DrivePI outperforms OpenDriveVLA-7B by 2.5% mean accuracy on nuScenes-QA and reduces collision rate by 70% over ORION (from 0.37% to 0.11%) on nuScenes. Against specialized VA models, DrivePI surpasses FB-OCC by 10.3 RayIoU for 3D occupancy on OpenOcc, reduces the mAVE from 0.591 to 0.509 for occupancy flow on OpenOcc, and achieves 32% lower L2 error than VAD (from 0.72m to 0.49m) for planning on nuScenes. Code will be available at https://github.com/happinesslz/DrivePI</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12799</guid>
|
||||
<pubDate>Sun, 14 Dec 2025 18:45:54 +0000</pubDate>
|
||||
<title>Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in</title>
|
||||
<link>https://arxiv.org/abs/2512.14273</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14273.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoqian Shen, Min-Hung Chen, Yu-Chiang Frank Wang, Mohamed Elhoseiny, Ryo Hachiuma</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Grounded video question answering (GVQA) aims to localize relevant temporal segments in videos and generate accurate answers to a given question; however, large video-language models (LVLMs) exhibit limited temporal awareness. Although existing approaches based on Group Relative Policy Optimization (GRPO) attempt to improve temporal grounding, they still struggle to faithfully ground their answers in the relevant video evidence, leading to temporal mislocalization and hallucinations. In this work, we present Zoom-Zero, a coarse-to-fine framework that first localizes query-relevant segments and then temporally zooms into the most salient frames for finer-grained visual verification. Our method addresses the limits of GRPO for the GVQA task with two key innovations: (i) a zoom-in accuracy reward that validates the fidelity of temporal grounding prediction and facilitates fine-grained visual verification on grounded frames; (ii) token-selective credit assignment, which attributes rewards to the tokens responsible for temporal localization or answer generation, mitigating GRPO's issue in handling multi-faceted reward signals. Our proposed method advances grounded video question answering, improving temporal grounding by 5.2\% on NExT-GQA and 4.6\% on ReXTime, while also enhancing average answer accuracy by 2.4\%. Additionally, the coarse-to-fine zoom-in during inference further benefits long-form video understanding by preserving critical visual details without compromising global context, yielding an average improvement of 6.4\% on long-video benchmarks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14273</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 10:34:39 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management</title>
|
||||
<link>https://arxiv.org/abs/2512.12967</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.12967.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Weizhou Shen, Ziyi Yang, Chenliang Li, Zhiyuan Lu, Miao Peng, Huashan Sun, Yingcheng Shi, Shengyi Liao, Shaopeng Lai, Bo Zhang, Dayiheng Liu, Fei Huang, Jingren Zhou, Ming Yan</p><p><b>Upvotes:</b> 54</p><p><b>Summary:</b> We introduce QwenLong-L1.5, a model that achieves superior long-context reasoning capabilities through systematic post-training innovations. The key technical breakthroughs of QwenLong-L1.5 are as follows: (1) Long-Context Data Synthesis Pipeline: We develop a systematic synthesis framework that generates challenging reasoning tasks requiring multi-hop grounding over globally distributed evidence. By deconstructing documents into atomic facts and their underlying relationships, and then programmatically composing verifiable reasoning questions, our approach creates high-quality training data at scale, moving substantially beyond simple retrieval tasks to enable genuine long-range reasoning capabilities. (2) Stabilized Reinforcement Learning for Long-Context Training: To overcome the critical instability in long-context RL, we introduce task-balanced sampling with task-specific advantage estimation to mitigate reward bias, and propose Adaptive Entropy-Controlled Policy Optimization (AEPO) that dynamically regulates exploration-exploitation trade-offs. (3) Memory-Augmented Architecture for Ultra-Long Contexts: Recognizing that even extended context windows cannot accommodate arbitrarily long sequences, we develop a memory management framework with multi-stage fusion RL training that seamlessly integrates single-pass reasoning with iterative memory-based processing for tasks exceeding 4M tokens. Based on Qwen3-30B-A3B-Thinking, QwenLong-L1.5 achieves performance comparable to GPT-5 and Gemini-2.5-Pro on long-context reasoning benchmarks, surpassing its baseline by 9.90 points on average. On ultra-long tasks (1M~4M tokens), QwenLong-L1.5's memory-agent framework yields a 9.48-point gain over the agent baseline. Additionally, the acquired long-context reasoning ability translates to enhanced performance in general domains like scientific reasoning, memory tool using, and extended dialogue.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.12967</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 04:11:11 +0000</pubDate>
|
||||
<title>SS4D: Native 4D Generative Model via Structured Spacetime Latents</title>
|
||||
<link>https://arxiv.org/abs/2512.14284</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14284.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhibing Li, Mengchen Zhang, Tong Wu, Jing Tan, Jiaqi Wang, Dahua Lin</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency. At the core of our method is a compressed set of structured spacetime latents. Specifically, (1) To address the scarcity of 4D training data, we build on a pre-trained single-image-to-3D model, preserving strong spatial consistency. (2) Temporal consistency is enforced by introducing dedicated temporal layers that reason across frames. (3) To support efficient training and inference over long video sequences, we compress the latent sequence along the temporal axis using factorized 4D convolutions and temporal downsampling blocks. In addition, we employ a carefully designed training strategy to enhance robustness against occlusion</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14284</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 10:45:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Few-Step Distillation for Text-to-Image Generation: A Practical Guide</title>
|
||||
<link>https://arxiv.org/abs/2512.13006</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13006.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yifan Pu, Yizeng Han, Zhiwei Tang, Jiasheng Tang, Fan Wang, Bohan Zhuang, Gao Huang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Diffusion distillation has dramatically accelerated class-conditional image synthesis, but its applicability to open-ended text-to-image (T2I) generation is still unclear. We present the first systematic study that adapts and compares state-of-the-art distillation techniques on a strong T2I teacher model, FLUX.1-lite. By casting existing methods into a unified framework, we identify the key obstacles that arise when moving from discrete class labels to free-form language prompts. Beyond a thorough methodological analysis, we offer practical guidelines on input scaling, network architecture, and hyperparameters, accompanied by an open-source implementation and pretrained student models. Our findings establish a solid foundation for deploying fast, high-fidelity, and resource-efficient diffusion generators in real-world T2I applications. Code is available on github.com/alibaba-damo-academy/T2I-Distill.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13006</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 05:58:36 +0000</pubDate>
|
||||
<title>Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure</title>
|
||||
<link>https://arxiv.org/abs/2512.14336</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14336.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jooyeol Yun, Jaegul Choo</p><p><b>Upvotes:</b> 22</p><p><b>Summary:</b> Scalable Vector Graphics (SVG) are central to modern web design, and the demand to animate them continues to grow as web environments become increasingly dynamic. Yet automating the animation of vector graphics remains challenging for vision-language models (VLMs) despite recent progress in code generation and motion planning. VLMs routinely mis-handle SVGs, since visually coherent parts are often fragmented into low-level shapes that offer little guidance of which elements should move together. In this paper, we introduce a framework that recovers the semantic structure required for reliable SVG animation and reveals the missing layer that current VLM systems overlook. This is achieved through a statistical aggregation of multiple weak part predictions, allowing the system to stably infer semantics from noisy predictions. By reorganizing SVGs into semantic groups, our approach enables VLMs to produce animations with far greater coherence. Our experiments demonstrate substantial gains over existing approaches, suggesting that semantic recovery is the key step that unlocks robust SVG animation and supports more interpretable interactions between VLMs and vector graphics.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14336</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 12:03:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos</title>
|
||||
<link>https://arxiv.org/abs/2512.13080</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13080.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yicheng Feng, Wanpeng Zhang, Ye Wang, Hao Luo, Haoqi Yuan, Sipeng Zheng, Zongqing Lu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D physical environments, creating a significant gap between perception and action grounding. To bridge this gap, we propose a Spatial-Aware VLA Pretraining paradigm that performs explicit alignment between visual space and physical space during pretraining, enabling models to acquire 3D spatial understanding before robot policy learning. Starting from pretrained vision-language models, we leverage large-scale human demonstration videos to extract 3D visual and 3D action annotations, forming a new source of supervision that aligns 2D visual observations with 3D spatial reasoning. We instantiate this paradigm with VIPA-VLA, a dual-encoder architecture that incorporates a 3D visual encoder to augment semantic visual representations with 3D-aware features. When adapted to downstream robot tasks, VIPA-VLA achieves significantly improved grounding between 2D vision and 3D action, resulting in more robust and generalizable robotic policies.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13080</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 08:31:47 +0000</pubDate>
|
||||
<title>RePo: Language Models with Context Re-Positioning</title>
|
||||
<link>https://arxiv.org/abs/2512.14391</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14391.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Huayang Li, Tianyu Zhao, Richard Sproat</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. Drawing on Cognitive Load Theory (CLT), we argue that this uninformative structure increases extraneous cognitive load, consuming finite working memory capacity that should be allocated to deep reasoning and attention allocation. To address this, we propose RePo, a novel mechanism that reduces extraneous load via context re-positioning. Unlike standard approaches, RePo utilizes a differentiable module, f_φ, to assign token positions that capture contextual dependencies, rather than replying on pre-defined integer range. By continually pre-training on the OLMo-2 1B backbone, we demonstrate that RePo significantly enhances performance on tasks involving noisy contexts, structured data, and longer context length, while maintaining competitive performance on general short-context tasks. Detailed analysis reveals that RePo successfully allocate higher attention to distant but relevant information, assign positions in dense and non-linear space, and capture the intrinsic structure of the input context. Our code is available at https://github.com/SakanaAI/repo.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14391</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 13:30:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows</title>
|
||||
<link>https://arxiv.org/abs/2512.13168</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13168.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Adina Yakefu, Shuxin Zheng</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> We introduce a finance & accounting benchmark (Finch) for evaluating AI agents on real-world, enterprise-grade professional workflows -- interleaving data entry, structuring, formatting, web search, cross-file retrieval, calculation, modeling, validation, translation, visualization, and reporting. Finch is sourced from authentic enterprise workspaces at Enron (15,000 spreadsheets and 500,000 emails from 150 employees) and other financial institutions, preserving in-the-wild messiness across multimodal artifacts (text, tables, formulas, charts, code, and images) and spanning diverse domains such as budgeting, trading, and asset management. We propose a workflow construction process that combines LLM-assisted discovery with expert annotation: (1) LLM-assisted, expert-verified derivation of workflows from real-world email threads and version histories of spreadsheet files, and (2) meticulous expert annotation for workflows, requiring over 700 hours of domain-expert effort. This yields 172 composite workflows with 384 tasks, involving 1,710 spreadsheets with 27 million cells, along with PDFs and other artifacts, capturing the intrinsically messy, long-horizon, knowledge-intensive, and collaborative nature of real-world enterprise work. We conduct both human and automated evaluations of frontier AI systems including GPT 5.1, Claude Sonnet 4.5, Gemini 3 Pro, Grok 4, and Qwen 3 Max, and GPT 5.1 Pro spends 48 hours in total yet passes only 38.4% of workflows, while Claude Sonnet 4.5 passes just 25.0%. Comprehensive case studies further surface the challenges that real-world enterprise workflows pose for AI agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13168</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 10:28:45 +0000</pubDate>
|
||||
<title>S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation</title>
|
||||
<link>https://arxiv.org/abs/2512.14440</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14440.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Leon Sick, Lukas Hoyer, Dominik Engel, Pedro Hermosilla, Timo Ropinski</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> In recent years, the state-of-the-art in unsupervised video instance segmentation has heavily relied on synthetic video data, generated from object-centric image datasets such as ImageNet. However, video synthesis by artificially shifting and scaling image instance masks fails to accurately model realistic motion in videos, such as perspective changes, movement by parts of one or multiple instances, or camera motion. To tackle this issue, we propose an unsupervised video instance segmentation model trained exclusively on real video data. We start from unsupervised instance segmentation masks on individual video frames. However, these single-frame segmentations exhibit temporal noise and their quality varies through the video. Therefore, we establish temporal coherence by identifying high-quality keymasks in the video by leveraging deep motion priors. The sparse keymask pseudo-annotations are then used to train a segmentation model for implicit mask propagation, for which we propose a Sparse-To-Dense Distillation approach aided by a Temporal DropLoss. After training the final model on the resulting dense labelset, our approach outperforms the current state-of-the-art across various benchmarks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14440</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 14:26:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection</title>
|
||||
<link>https://arxiv.org/abs/2512.13250</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13250.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Juil Koo, Daehyeon Choi, Sangwoo Youn, Phillip Y. Lee, Minhyuk Sung</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Vision Language Models (VLMs) excel at visual question answering (VQA) but remain limited to snapshot vision, reasoning from static images. In contrast, embodied agents require ambulatory vision, actively moving to obtain more informative views. We introduce Visually Grounded Active View Selection (VG-AVS), a task that selects the most informative next viewpoint using only the visual information in the current image, without relying on scene memory or external knowledge. To support this task, we construct a synthetic dataset with automatically generated paired query-target views and question-answer prompts. We also propose a framework that fine-tunes pretrained VLMs through supervised fine-tuning (SFT) followed by RL-based policy optimization. Our approach achieves strong question answering performance based on viewpoint selection and generalizes robustly to unseen synthetic and real scenes. Furthermore, incorporating our learned VG-AVS framework into existing scene-exploration-based EQA systems improves downstream question-answering accuracy.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13250</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 12:04:26 +0000</pubDate>
|
||||
<title>A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2512.14442</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14442.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zixin Zhang, Kanghao Chen, Hanqing Wang, Hongfei Zhang, Harold Haodong Chen, Chenfei Liao, Litao Guo, Ying-Cong Chen</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Affordance prediction, which identifies interaction regions on objects based on language instructions, is critical for embodied AI. Prevailing end-to-end models couple high-level reasoning and low-level grounding into a single monolithic pipeline and rely on training over annotated datasets, which leads to poor generalization on novel objects and unseen environments. In this paper, we move beyond this paradigm by proposing A4-Agent, a training-free agentic framework that decouples affordance prediction into a three-stage pipeline. Our framework coordinates specialized foundation models at test time: (1) a Dreamer that employs generative models to visualize how an interaction would look; (2) a Thinker that utilizes large vision-language models to decide what object part to interact with; and (3) a Spotter that orchestrates vision foundation models to precisely locate where the interaction area is. By leveraging the complementary strengths of pre-trained models without any task-specific fine-tuning, our zero-shot framework significantly outperforms state-of-the-art supervised methods across multiple benchmarks and demonstrates robust generalization to real-world settings.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14442</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 14:27:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>KlingAvatar 2.0 Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2512.13313</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13313.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kling Team, Jialu Chen, Yikang Ding, Zhixue Fang, Kun Gai, Yuan Gao, Kang He, Jingyun Hua, Boyuan Jiang, Mingming Lao, Xiaohan Li, Hui Liu, Jiwen Liu, Xiaoqiang Liu, Yuan Liu, Shun Lu, Yongsen Mao, Yingchao Shao, Huafeng Shi, Xiaoyu Shi, Peiqin Sun, Songlin Tang, Pengfei Wan, Chao Wang, Xuebo Wang, Haoxian Zhang, Yuanxing Zhang, Yan Zhou</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Avatar video generation models have achieved remarkable progress in recent years. However, prior work exhibits limited efficiency in generating long-duration high-resolution videos, suffering from temporal drifting, quality degradation, and weak prompt following as video length increases. To address these challenges, we propose KlingAvatar 2.0, a spatio-temporal cascade framework that performs upscaling in both spatial resolution and temporal dimension. The framework first generates low-resolution blueprint video keyframes that capture global semantics and motion, and then refines them into high-resolution, temporally coherent sub-clips using a first-last frame strategy, while retaining smooth temporal transitions in long-form videos. To enhance cross-modal instruction fusion and alignment in extended videos, we introduce a Co-Reasoning Director composed of three modality-specific large language model (LLM) experts. These experts reason about modality priorities and infer underlying user intent, converting inputs into detailed storylines through multi-turn dialogue. A Negative Director further refines negative prompts to improve instruction alignment. Building on these components, we extend the framework to support ID-specific multi-character control. Extensive experiments demonstrate that our model effectively addresses the challenges of efficient, multimodally aligned long-form high-resolution video generation, delivering enhanced visual clarity, realistic lip-teeth rendering with accurate lip synchronization, strong identity preservation, and coherent multimodal instruction following.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13313</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 13:30:51 +0000</pubDate>
|
||||
<title>RecGPT-V2 Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2512.14503</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14503.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chao Yi, Dian Chen, Gaoyang Guo, Jiakai Tang, Jian Wu, Jing Yu, Mao Zhang, Wen Chen, Wenjun Yang, Yujie Luo, Yuning Jiang, Zhujin Gao, Bo Zheng, Binbin Cao, Changfa Wu, Dixuan Wang, Han Wu, Haoyi Hu, Kewei Zhu, Lang Tian, Lin Yang, Qiqi Huang, Siqi Yang, Wenbo Su, Xiaoxiao He, Xin Tong, Xu Chen, Xunke Xi, Xiaowei Huang, Yaxuan Wu, Yeqiu Yang, Yi Hu, Yujin Yuan, Yuliang Yan, Zile Zhou</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Large language models (LLMs) have demonstrated remarkable potential in transforming recommender systems from implicit behavioral pattern matching to explicit intent reasoning. While RecGPT-V1 successfully pioneered this paradigm by integrating LLM-based reasoning into user interest mining and item tag prediction, it suffers from four fundamental limitations: (1) computational inefficiency and cognitive redundancy across multiple reasoning routes; (2) insufficient explanation diversity in fixed-template generation; (3) limited generalization under supervised learning paradigms; and (4) simplistic outcome-focused evaluation that fails to match human standards. To address these challenges, we present RecGPT-V2 with four key innovations. First, a Hierarchical Multi-Agent System restructures intent reasoning through coordinated collaboration, eliminating cognitive duplication while enabling diverse intent coverage. Combined with Hybrid Representation Inference that compresses user-behavior contexts, our framework reduces GPU consumption by 60% and improves exclusive recall from 9.39% to 10.99%. Second, a Meta-Prompting framework dynamically generates contextually adaptive prompts, improving explanation diversity by +7.3%. Third, constrained reinforcement learning mitigates multi-reward conflicts, achieving +24.1% improvement in tag prediction and +13.0% in explanation acceptance. Fourth, an Agent-as-a-Judge framework decomposes assessment into multi-step reasoning, improving human preference alignment. Online A/B tests on Taobao demonstrate significant improvements: +2.98% CTR, +3.71% IPV, +2.19% TV, and +11.46% NER. RecGPT-V2 establishes both the technical feasibility and commercial viability of deploying LLM-powered intent reasoning at scale, bridging the gap between cognitive exploration and industrial utility.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14503</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 15:40:44 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>FIN-bench-v2: A Unified and Robust Benchmark Suite for Evaluating Finnish Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2512.13330</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13330.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Joona Kytöniemi, Jousia Piha, Akseli Reunamo, Fedor Vitiugin, Farrokh Mehryary, Sampo Pyysalo</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce FIN-bench-v2, a unified benchmark suite for evaluating large language models in Finnish. FIN-bench-v2 consolidates Finnish versions of widely used benchmarks together with an updated and expanded version of the original FIN-bench into a single, consistently formatted collection, covering multiple-choice and generative tasks across reading comprehension, commonsense reasoning, sentiment analysis, world knowledge, and alignment. All datasets are converted to HuggingFace Datasets, which include both cloze and multiple-choice prompt formulations with five variants per task, and we incorporate human annotation or review for machine-translated resources such as GoldenSwag and XED. To select robust tasks, we pretrain a set of 2.15B-parameter decoder-only models and use their learning curves to compute monotonicity, signal-to-noise, non-random performance, and model ordering consistency, retaining only tasks that satisfy all criteria. We further evaluate a set of larger instruction-tuned models to characterize performance across tasks and prompt formulations. All datasets, prompts, and evaluation configurations are publicly available via our fork of the Language Model Evaluation Harness at https://github.com/LumiOpen/lm-evaluation-harness. Supplementary resources are released in a separate repository at https://github.com/TurkuNLP/FIN-bench-v2.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13330</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 13:41:41 +0000</pubDate>
|
||||
<title>VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse</title>
|
||||
<link>https://arxiv.org/abs/2512.14531</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14531.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ying Nie, Kai Han, Hongguang Li, Hang Zhou, Tianyu Guo, Enhua Wu, Xinghao Chen, Yunhe Wang</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> The rapid scaling of Large Language Models (LLMs) has achieved remarkable performance, but it also leads to prohibitive memory costs. Existing parameter-efficient approaches such as pruning and quantization mainly compress pretrained models without enhancing architectural capacity, thereby hitting the representational ceiling of the base model. In this work, we propose VersatileFFN, a novel feed-forward network (FFN) that enables flexible reuse of parameters in both width and depth dimensions within a fixed parameter budget. Inspired by the dual-process theory of cognition, VersatileFFN comprises two adaptive pathways: a width-versatile path that generates a mixture of sub-experts from a single shared FFN, mimicking sparse expert routing without increasing parameters, and a depth-versatile path that recursively applies the same FFN to emulate deeper processing for complex tokens. A difficulty-aware gating dynamically balances the two pathways, steering "easy" tokens through the efficient width-wise route and allocating deeper iterative refinement to "hard" tokens. Crucially, both pathways reuse the same parameters, so all additional capacity comes from computation rather than memory. Experiments across diverse benchmarks and model scales demonstrate the effectiveness of the method. The code will be available at https://github.com/huawei-noah/noah-research/tree/master/VersatileFFN.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14531</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 16:08:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>RecTok: Reconstruction Distillation along Rectified Flow</title>
|
||||
<link>https://arxiv.org/abs/2512.13421</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13421.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qingyu Shi, Size Wu, Jinbin Bai, Kaidong Yu, Yujing Wang, Yunhai Tong, Xiangtai Li, Xuelong Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between dimensionality and generation quality, constraining existing methods to low-dimensional latent spaces. Although recent works have leveraged vision foundation models to enrich the semantics of visual tokenizers and accelerate convergence, high-dimensional tokenizers still underperform their low-dimensional counterparts. In this work, we propose RecTok, which overcomes the limitations of high-dimensional visual tokenizers through two key innovations: flow semantic distillation and reconstruction--alignment distillation. Our key insight is to make the forward flow in flow matching semantically rich, which serves as the training space of diffusion transformers, rather than focusing on the latent space as in previous works. Specifically, our method distills the semantic information in VFMs into the forward flow trajectories in flow matching. And we further enhance the semantics by introducing a masked feature reconstruction loss. Our RecTok achieves superior image reconstruction, generation quality, and discriminative performance. It achieves state-of-the-art results on the gFID-50K under both with and without classifier-free guidance settings, while maintaining a semantically rich latent space structure. Furthermore, as the latent dimensionality increases, we observe consistent improvements. Code and model are available at https://shi-qingyu.github.io/rectok.github.io.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13421</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 15:14:20 +0000</pubDate>
|
||||
<title>TAT: Task-Adaptive Transformer for All-in-One Medical Image Restoration</title>
|
||||
<link>https://arxiv.org/abs/2512.14550</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14550.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhiwen Yang, Jiaju Zhang, Yang Yi, Jian Liang, Bingzheng Wei, Yan Xu</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Medical image restoration (MedIR) aims to recover high-quality medical images from their low-quality counterparts. Recent advancements in MedIR have focused on All-in-One models capable of simultaneously addressing multiple different MedIR tasks. However, due to significant differences in both modality and degradation types, using a shared model for these diverse tasks requires careful consideration of two critical inter-task relationships: task interference, which occurs when conflicting gradient update directions arise across tasks on the same parameter, and task imbalance, which refers to uneven optimization caused by varying learning difficulties inherent to each task. To address these challenges, we propose a task-adaptive Transformer (TAT), a novel framework that dynamically adapts to different tasks through two key innovations. First, a task-adaptive weight generation strategy is introduced to mitigate task interference by generating task-specific weight parameters for each task, thereby eliminating potential gradient conflicts on shared weight parameters. Second, a task-adaptive loss balancing strategy is introduced to dynamically adjust loss weights based on task-specific learning difficulties, preventing task domination or undertraining. Extensive experiments demonstrate that our proposed TAT achieves state-of-the-art performance in three MedIR tasks--PET synthesis, CT denoising, and MRI super-resolution--both in task-specific and All-in-One settings. Code is available at https://github.com/Yaziwel/TAT.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14550</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 16:25:47 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Memory in the Age of AI Agents</title>
|
||||
<link>https://arxiv.org/abs/2512.13564</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13564.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuyang Hu, Shichun Liu, Yanwei Yue, Guibin Zhang, Boyang Liu, Fangyi Zhu, Jiahang Lin, Honglin Guo, Shihan Dou, Zhiheng Xi, Senjie Jin, Jiejun Tan, Yanbin Yin, Jiongnan Liu, Zeyu Zhang, Zhongxiang Sun, Yutao Zhu, Hao Sun, Boci Peng, Zhenrong Cheng, Xuanbo Fan, Jiaxin Guo, Xinlei Yu, Zhenhong Zhou, Zewen Hu, Jiahao Huo, Junhao Wang, Yuwei Niu, Yu Wang, Zhenfei Yin, Xiaobin Hu, Yue Liao, Qiankun Li, Kun Wang, Wangchunshu Zhou, Yixin Liu, Dawei Cheng, Qi Zhang, Tao Gui, Shirui Pan, Yan Zhang, Philip Torr, Zhicheng Dou, Ji-Rong Wen, Xuanjing Huang, Yu-Gang Jiang, Shuicheng Yan</p><p><b>Upvotes:</b> 62</p><p><b>Summary:</b> Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attention, the field has also become increasingly fragmented. Existing works that fall under the umbrella of agent memory often differ substantially in their motivations, implementations, and evaluation protocols, while the proliferation of loosely defined memory terminologies has further obscured conceptual clarity. Traditional taxonomies such as long/short-term memory have proven insufficient to capture the diversity of contemporary agent memory systems. This work aims to provide an up-to-date landscape of current agent memory research. We begin by clearly delineating the scope of agent memory and distinguishing it from related concepts such as LLM memory, retrieval augmented generation (RAG), and context engineering. We then examine agent memory through the unified lenses of forms, functions, and dynamics. From the perspective of forms, we identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory. From the perspective of functions, we propose a finer-grained taxonomy that distinguishes factual, experiential, and working memory. From the perspective of dynamics, we analyze how memory is formed, evolved, and retrieved over time. To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks. Beyond consolidation, we articulate a forward-looking perspective on emerging research frontiers, including memory automation, reinforcement learning integration, multimodal memory, multi-agent memory, and trustworthiness issues. We hope this survey serves not only as a reference for existing work, but also as a conceptual foundation for rethinking memory as a first-class primitive in the design of future agentic intelligence.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13564</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 17:22:34 +0000</pubDate>
|
||||
<title>WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling</title>
|
||||
<link>https://arxiv.org/abs/2512.14614</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14614.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenqiang Sun, Haiyu Zhang, Haoyuan Wang, Junta Wu, Zehan Wang, Zhenwei Wang, Yunhong Wang, Jun Zhang, Tengfei Wang, Chunchao Guo</p><p><b>Upvotes:</b> 48</p><p><b>Summary:</b> This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. WorldPlay draws power from three key innovations. 1) We use a Dual Action Representation to enable robust action control in response to the user's keyboard and mouse inputs. 2) To enforce long-term consistency, our Reconstituted Context Memory dynamically rebuilds context from past frames and uses temporal reframing to keep geometrically important but long-past frames accessible, effectively alleviating memory attenuation. 3) We also propose Context Forcing, a novel distillation method designed for memory-aware model. Aligning memory context between the teacher and student preserves the student's capacity to use long-range information, enabling real-time speeds while preventing error drift. Taken together, WorldPlay generates long-horizon streaming 720p video at 24 FPS with superior consistency, comparing favorably with existing techniques and showing strong generalization across diverse scenes. Project page and online demo can be found: https://3d-models.hunyuan.tencent.com/world/ and https://3d.hunyuan.tencent.com/sceneTo3D.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14614</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 17:22:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding</title>
|
||||
<link>https://arxiv.org/abs/2512.13586</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13586.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jia-Nan Li, Jian Guan, Wei Wu, Chongxuan Li</p><p><b>Upvotes:</b> 74</p><p><b>Summary:</b> Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV) caching, and incoherent generation arising from learning dependencies over an intractable space of token combinations. To address these limitations, we introduce ReFusion, a novel masked diffusion model that achieves superior performance and efficiency by elevating parallel decoding from the token level to a higher slot level, where each slot is a fixed-length, contiguous sub-sequence. This is achieved through an iterative ``plan-and-infill'' decoding process: a diffusion-based planning step first identifies a set of weakly dependent slots, and an autoregressive infilling step then decodes these selected slots in parallel. The slot-based design simultaneously unlocks full KV cache reuse with a unified causal framework and reduces the learning complexity from the token combination space to a manageable slot-level permutation space. Extensive experiments on seven diverse benchmarks show that ReFusion not only overwhelmingly surpasses prior MDMs with 34% performance gains and an over 18times speedup on average, but also bridges the performance gap to strong ARMs while maintaining a 2.33times average speedup.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13586</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 17:41:19 +0000</pubDate>
|
||||
<title>JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction</title>
|
||||
<link>https://arxiv.org/abs/2512.14620</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14620.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Atsuyuki Miyai, Shota Onohara, Jeonghun Baek, Kiyoharu Aizawa</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> This paper introduces JMMMU-Pro, an image-based Japanese Multi-discipline Multimodal Understanding Benchmark, and Vibe Benchmark Construction, a scalable construction method. Following the evolution from MMMU to MMMU-Pro, JMMMU-Pro extends JMMMU by composing the question image and question text into a single image, thereby creating a benchmark that requires integrated visual-textual understanding through visual perception. To build JMMMU-Pro, we propose Vibe Benchmark Construction, a methodology in which an image generative model (e.g., Nano Banana Pro) produces candidate visual questions, and humans verify the outputs and, when necessary, regenerate with adjusted prompts to ensure quality. By leveraging Nano Banana Pro's highly realistic image generation capabilities and its ability to embed clean Japanese text, we construct a high-quality benchmark at low cost, covering a wide range of background and layout designs. Experimental results show that all open-source LMMs struggle substantially with JMMMU-Pro, underscoring JMMMU-Pro as an important benchmark for guiding future efforts in the open-source community. We believe that JMMMU-Pro provides a more rigorous evaluation tool for assessing the Japanese capabilities of LMMs and that our Vibe Benchmark Construction also offers an efficient guideline for future development of image-based VQA benchmarks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14620</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 17:33:00 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Image Diffusion Preview with Consistency Solver</title>
|
||||
<link>https://arxiv.org/abs/2512.13592</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13592.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fu-Yun Wang, Hao Zhou, Liangzhe Yuan, Sanghyun Woo, Boqing Gong, Bohyung Han, Ming-Hsuan Yang, Han Zhang, Yukun Zhu, Ting Liu, Long Zhao</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs for user evaluation, deferring full-step refinement until the preview is deemed satisfactory. Existing acceleration methods, including training-free solvers and post-training distillation, struggle to deliver high-quality previews or ensure consistency between previews and final outputs. We propose ConsistencySolver derived from general linear multistep methods, a lightweight, trainable high-order solver optimized via Reinforcement Learning, that enhances preview quality and consistency. Experimental results demonstrate that ConsistencySolver significantly improves generation quality and consistency in low-step scenarios, making it ideal for efficient preview-and-refine workflows. Notably, it achieves FID scores on-par with Multistep DPM-Solver using 47% fewer steps, while outperforming distillation baselines. Furthermore, user studies indicate our approach reduces overall user interaction time by nearly 50% while maintaining generation quality. Code is available at https://github.com/G-U-N/consolver.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13592</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 17:47:49 +0000</pubDate>
|
||||
<title>EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models</title>
|
||||
<link>https://arxiv.org/abs/2512.14666</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14666.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zechen Bai, Chen Gao, Mike Zheng Shou</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through practice. Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models, yet remain fundamentally limited by Supervised Finetuning (SFT): requiring hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training. We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations. The key technical challenge is replacing oracle reward signals (unavailable at test time) with autonomous feedback. We address this through a learned progress estimator providing dense feedback, and critically, we design our framework to ``tame'' this inherently noisy signal via two mechanisms: (1) an accumulative progress estimation mechanism smoothing noisy point-wise estimates, and (2) a progressive horizon extension strategy enabling gradual policy evolution. EVOLVE-VLA achieves substantial gains: +8.6\% on long-horizon tasks, +22.0\% in 1-shot learning, and enables cross-task generalization -- achieving 20.8\% success on unseen tasks without task-specific demonstrations training (vs. 0\% for pure SFT). Qualitative analysis reveals emergent capabilities absent in demonstrations, including error recovery and novel strategies. This work represents a critical step toward VLAs that truly learn and adapt, moving beyond static imitation toward continuous self-improvements.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14666</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 18:26:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LongVie 2: Multimodal Controllable Ultra-Long Video World Model</title>
|
||||
<link>https://arxiv.org/abs/2512.13604</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13604.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jianxiong Gao, Zhaoxi Chen, Xian Liu, Junhao Zhuang, Chengming Xu, Jianfeng Feng, Yu Qiao, Yanwei Fu, Chenyang Si, Ziwei Liu</p><p><b>Upvotes:</b> 52</p><p><b>Summary:</b> Building video world models upon pretrained video generation systems represents an important yet challenging step toward general spatiotemporal intelligence. A world model should possess three essential properties: controllability, long-term visual quality, and temporal consistency. To this end, we take a progressive approach-first enhancing controllability and then extending toward long-term, high-quality generation. We present LongVie 2, an end-to-end autoregressive framework trained in three stages: (1) Multi-modal guidance, which integrates dense and sparse control signals to provide implicit world-level supervision and improve controllability; (2) Degradation-aware training on the input frame, bridging the gap between training and long-term inference to maintain high visual quality; and (3) History-context guidance, which aligns contextual information across adjacent clips to ensure temporal consistency. We further introduce LongVGenBench, a comprehensive benchmark comprising 100 high-resolution one-minute videos covering diverse real-world and synthetic environments. Extensive experiments demonstrate that LongVie 2 achieves state-of-the-art performance in long-range controllability, temporal coherence, and visual fidelity, and supports continuous video generation lasting up to five minutes, marking a significant step toward unified video world modeling.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13604</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 17:59:58 +0000</pubDate>
|
||||
<title>MMGR: Multi-Modal Generative Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2512.14691</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14691.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zefan Cai, Haoyi Qiu, Tianyi Ma, Haozhe Zhao, Gengze Zhou, Kung-Hsiang Huang, Parisa Kordjamshidi, Minjia Zhang, Xiao Wen, Jiuxiang Gu, Nanyun Peng, Junjie Hu</p><p><b>Upvotes:</b> 78</p><p><b>Summary:</b> Video foundation models generate visually realistic and temporally coherent content, but their reliability as world simulators depends on whether they capture physical, logical, and spatial constraints. Existing metrics such as Frechet Video Distance (FVD) emphasize perceptual quality and overlook reasoning failures, including violations of causality, physics, and global consistency. We introduce MMGR (Multi-Modal Generative Reasoning Evaluation and Benchmark), a principled evaluation framework based on five reasoning abilities: Physical, Logical, 3D Spatial, 2D Spatial, and Temporal. MMGR evaluates generative reasoning across three domains: Abstract Reasoning (ARC-AGI, Sudoku), Embodied Navigation (real-world 3D navigation and localization), and Physical Commonsense (sports and compositional interactions). MMGR applies fine-grained metrics that require holistic correctness across both video and image generation. We benchmark leading video models (Veo-3, Sora-2, Wan-2.2) and image models (Nano-banana, Nano-banana Pro, GPT-4o-image, Qwen-image), revealing strong performance gaps across domains. Models show moderate success on Physical Commonsense tasks but perform poorly on Abstract Reasoning (below 10 percent accuracy on ARC-AGI) and struggle with long-horizon spatial planning in embodied settings. Our analysis highlights key limitations in current models, including overreliance on perceptual data, weak global state consistency, and objectives that reward visual plausibility over causal correctness. MMGR offers a unified diagnostic benchmark and a path toward reasoning-aware generative world models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14691</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 18:58:04 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Directional Textual Inversion for Personalized Text-to-Image Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.13672</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13672.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kunhee Kim, NaHyeon Park, Kibeom Hong, Hyunjung Shim</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Textual Inversion (TI) is an efficient approach to text-to-image personalization but often fails on complex prompts. We trace these failures to embedding norm inflation: learned tokens drift to out-of-distribution magnitudes, degrading prompt conditioning in pre-norm Transformers. Empirically, we show semantics are primarily encoded by direction in CLIP token space, while inflated norms harm contextualization; theoretically, we analyze how large magnitudes attenuate positional information and hinder residual updates in pre-norm blocks. We propose Directional Textual Inversion (DTI), which fixes the embedding magnitude to an in-distribution scale and optimizes only direction on the unit hypersphere via Riemannian SGD. We cast direction learning as MAP with a von Mises-Fisher prior, yielding a constant-direction prior gradient that is simple and efficient to incorporate. Across personalization tasks, DTI improves text fidelity over TI and TI-variants while maintaining subject similarity. Crucially, DTI's hyperspherical parameterization enables smooth, semantically coherent interpolation between learned concepts (slerp), a capability that is absent in standard TI. Our findings suggest that direction-only optimization is a robust and scalable path for prompt-faithful personalization.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13672</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:57:07 +0000</pubDate>
|
||||
<title>CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives</title>
|
||||
<link>https://arxiv.org/abs/2512.14696</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14696.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Wang, Jiashun Wang, Jeff Tan, Yiwen Zhao, Jessica Hodgins, Shubham Tulsiani, Deva Ramanan</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We introduce CRISP, a method that recovers simulatable human motion and scene geometry from monocular video. Prior work on joint human-scene reconstruction relies on data-driven priors and joint optimization with no physics in the loop, or recovers noisy geometry with artifacts that cause motion tracking policies with scene interactions to fail. In contrast, our key insight is to recover convex, clean, and simulation-ready geometry by fitting planar primitives to a point cloud reconstruction of the scene, via a simple clustering pipeline over depth, normals, and flow. To reconstruct scene geometry that might be occluded during interactions, we make use of human-scene contact modeling (e.g., we use human posture to reconstruct the occluded seat of a chair). Finally, we ensure that human and scene reconstructions are physically-plausible by using them to drive a humanoid controller via reinforcement learning. Our approach reduces motion tracking failure rates from 55.2\% to 6.9\% on human-centric video benchmarks (EMDB, PROX), while delivering a 43\% faster RL simulation throughput. We further validate it on in-the-wild videos including casually-captured videos, Internet videos, and even Sora-generated videos. This demonstrates CRISP's ability to generate physically-valid human motion and interaction environments at scale, greatly advancing real-to-sim applications for robotics and AR/VR.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14696</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 18:59:50 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Towards Interactive Intelligence for Digital Humans</title>
|
||||
<link>https://arxiv.org/abs/2512.13674</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13674.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiyi Cai, Xuangeng Chu, Xiwei Gao, Sitong Gong, Yifei Huang, Caixin Kang, Kunhang Li, Haiyang Liu, Ruicong Liu, Yun Liu, Dianwen Ng, Zixiong Su, Erwin Wu, Yuhan Wu, Dingkun Yan, Tianyu Yan, Chang Zeng, Bo Zheng, You Zhou</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce Interactive Intelligence, a novel paradigm of digital human that is capable of personality-aligned expression, adaptive interaction, and self-evolution. To realize this, we present Mio (Multimodal Interactive Omni-Avatar), an end-to-end framework composed of five specialized modules: Thinker, Talker, Face Animator, Body Animator, and Renderer. This unified architecture integrates cognitive reasoning with real-time multimodal embodiment to enable fluid, consistent interaction. Furthermore, we establish a new benchmark to rigorously evaluate the capabilities of interactive intelligence. Extensive experiments demonstrate that our framework achieves superior performance compared to state-of-the-art methods across all evaluated dimensions. Together, these contributions move digital humans beyond superficial imitation toward intelligent interaction.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13674</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:57:35 +0000</pubDate>
|
||||
<title>Spherical Leech Quantization for Visual Tokenization and Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.14697</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14697.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yue Zhao, Hanwen Jiang, Zhenlin Xu, Chutong Yang, Ehsan Adeli, Philipp Krähenbühl</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Non-parametric quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of different non-parametric quantization methods through the lens of lattice coding. The geometry of lattice codes explains the necessity of auxiliary loss terms when training auto-encoders with certain existing lookup-free quantization variants such as BSQ. As a step forward, we explore a few possible candidates, including random lattices, generalized Fibonacci lattices, and densest sphere packing lattices. Among all, we find the Leech lattice-based quantization method, which is dubbed as Spherical Leech Quantization (Λ_{24}-SQ), leads to both a simplified training recipe and an improved reconstruction-compression tradeoff thanks to its high symmetry and even distribution on the hypersphere. In image tokenization and compression tasks, this quantization approach achieves better reconstruction quality across all metrics than BSQ, the best prior art, while consuming slightly fewer bits. The improvement also extends to state-of-the-art auto-regressive image generation frameworks.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14697</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 18:59:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Towards Scalable Pre-training of Visual Tokenizers for Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.13687</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13687.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingfeng Yao, Yuda Song, Yucong Zhou, Xinggang Wang</p><p><b>Upvotes:</b> 66</p><p><b>Summary:</b> The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information, leading to a foundation flaw: better pixel-level accuracy does not lead to higher-quality generation. This implies that pouring extensive compute into visual tokenizer pre-training translates poorly to improved performance in generation. We identify this as the ``pre-training scaling problem`` and suggest a necessary shift: to be effective for generation, a latent space must concisely represent high-level semantics. We present VTP, a unified visual tokenizer pre-training framework, pioneering the joint optimization of image-text contrastive, self-supervised, and reconstruction losses. Our large-scale study reveals two principal findings: (1) understanding is a key driver of generation, and (2) much better scaling properties, where generative performance scales effectively with compute, parameters, and data allocated to the pretraining of the visual tokenizer. After large-scale pre-training, our tokenizer delivers a competitive profile (78.2 zero-shot accuracy and 0.36 rFID on ImageNet) and 4.1 times faster convergence on generation compared to advanced distillation methods. More importantly, it scales effectively: without modifying standard DiT training specs, solely investing more FLOPS in pretraining VTP achieves 65.8\% FID improvement in downstream generation, while conventional autoencoder stagnates very early at 1/10 FLOPS. Our pre-trained models are available at https://github.com/MiniMax-AI/VTP.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13687</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:59:54 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LitePT: Lighter Yet Stronger Point Transformer</title>
|
||||
<link>https://arxiv.org/abs/2512.13689</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13689.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yuanwen Yue, Damien Robert, Jianyuan Wang, Sunghwan Hong, Jan Dirk Wegner, Christian Rupprecht, Konrad Schindler</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the role of different computational blocks in 3D point cloud networks and find an intuitive behaviour: convolution is adequate to extract low-level geometry at high-resolution in early layers, where attention is expensive without bringing any benefits; attention captures high-level semantics and context in low-resolution, deep layers more efficiently. Guided by this design principle, we propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers. To avoid the loss of spatial layout information when discarding redundant convolution layers, we introduce a novel, training-free 3D positional encoding, PointROPE. The resulting LitePT model has 3.6times fewer parameters, runs 2times faster, and uses 2times less memory than the state-of-the-art Point Transformer V3, but nonetheless matches or even outperforms it on a range of tasks and datasets. Code and models are available at: https://github.com/prs-eth/LitePT.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13689</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:59:57 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders</title>
|
||||
<link>https://arxiv.org/abs/2512.13690</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.13690.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Susung Hong, Chongjian Ge, Zhifei Zhang, Jui-Hsien Wang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Video diffusion models have revolutionized generative video synthesis, but they are imprecise, slow, and can be opaque during generation -- keeping users in the dark for a prolonged period. In this work, we propose DiffusionBrowser, a model-agnostic, lightweight decoder framework that allows users to interactively generate previews at any point (timestep or transformer block) during the denoising process. Our model can generate multi-modal preview representations that include RGB and scene intrinsics at more than 4times real-time speed (less than 1 second for a 4-second video) that convey consistent appearance and motion to the final video. With the trained decoder, we show that it is possible to interactively guide the generation at intermediate noise steps via stochasticity reinjection and modal steering, unlocking a new control capability. Moreover, we systematically probe the model using the learned decoders, revealing how scene, object, and other details are composed and assembled during the otherwise black-box denoising process.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.13690</guid>
|
||||
<pubDate>Mon, 15 Dec 2025 18:59:57 +0000</pubDate>
|
||||
<title>MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives</title>
|
||||
<link>https://arxiv.org/abs/2512.14699</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.14699.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sihui Ji, Xi Chen, Shuai Yang, Xin Tao, Pengfei Wan, Hengshuang Zhao</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with predefined strategies. However, different to-generate video chunks should refer to different historical cues, which is hard to satisfy with fixed strategies. In this work, we propose MemFlow to address this problem. Specifically, before generating the coming chunk, we dynamically update the memory bank by retrieving the most relevant historical frames with the text prompt of this chunk. This design enables narrative coherence even if new event happens or scenario switches in future frames. In addition, during generation, we only activate the most relevant tokens in the memory bank for each query in the attention layers, which effectively guarantees the generation efficiency. In this way, MemFlow achieves outstanding long-context consistency with negligible computation burden (7.9% speed reduction compared with the memory-free baseline) and keeps the compatibility with any streaming video generation model with KV cache.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.14699</guid>
|
||||
<pubDate>Tue, 16 Dec 2025 18:59:59 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user