diff --git a/feed.xml b/feed.xml index bdf879e..573b5bd 100644 --- a/feed.xml +++ b/feed.xml @@ -7,181 +7,272 @@ http://www.rssboard.org/rss-specification python-feedgen en - Fri, 05 Dec 2025 00:02:38 +0000 + Sat, 06 Dec 2025 00:02:27 +0000 - Adversarial Confusion Attack: Disrupting Multimodal Large Language Models - https://arxiv.org/abs/2511.20494 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.20494.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jakub Hoscilowicz, Artur Janicki</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model generate incoherent or confidently incorrect outputs. Practical applications include embedding such adversarial images into websites to prevent MLLM-powered AI Agents from operating reliably. The proposed attack maximizes next-token entropy using a small ensemble of open-source MLLMs. In the white-box setting, we show that a single adversarial image can disrupt all models in the ensemble, both in the full-image and Adversarial CAPTCHA settings. Despite relying on a basic adversarial technique (PGD), the attack generates perturbations that transfer to both unseen open-source (e.g., Qwen3-VL) and proprietary (e.g., GPT-5.1) models.</p> - https://arxiv.org/abs/2511.20494 - Tue, 25 Nov 2025 17:00:31 +0000 + LATTICE: Democratize High-Fidelity 3D Generation at Scale + https://arxiv.org/abs/2512.03052 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03052.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeqiang Lai, Yunfei Zhao, Zibo Zhao, Haolin Liu, Qingxiang Lin, Jingwei Huang, Chunchao Guo, Xiangyu Yue</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We present LATTICE, a new framework for high-fidelity 3D asset generation that bridges the quality and scalability gap between 3D and 2D generative models. While 2D image synthesis benefits from fixed spatial grids and well-established transformer architectures, 3D generation remains fundamentally more challenging due to the need to predict both spatial structure and detailed geometric surfaces from scratch. These challenges are exacerbated by the computational complexity of existing 3D representations and the lack of structured and scalable 3D asset encoding schemes. To address this, we propose VoxSet, a semi-structured representation that compresses 3D assets into a compact set of latent vectors anchored to a coarse voxel grid, enabling efficient and position-aware generation. VoxSet retains the simplicity and compression advantages of prior VecSet methods while introducing explicit structure into the latent space, allowing positional embeddings to guide generation and enabling strong token-level test-time scaling. Built upon this representation, LATTICE adopts a two-stage pipeline: first generating a sparse voxelized geometry anchor, then producing detailed geometry using a rectified flow transformer. Our method is simple at its core, but supports arbitrary resolution decoding, low-cost training, and flexible inference schemes, achieving state-of-the-art performance on various aspects, and offering a significant step toward scalable, high-quality 3D asset creation.</p> + https://arxiv.org/abs/2512.03052 + Mon, 24 Nov 2025 03:22:19 +0000 - AlignBench: Benchmarking Fine-Grained Image-Text Alignment with Synthetic Image-Caption Pairs - https://arxiv.org/abs/2511.20515 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.20515.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kuniaki Saito, Risa Shinoda, Shohei Tanaka, Tosho Hirasawa, Fumio Okura, Yoshitaka Ushiku</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Assessing image-text alignment models such as CLIP is crucial for bridging visual and linguistic representations. Yet existing benchmarks rely on rule-based perturbations or short captions, limiting their ability to measure fine-grained alignment. We introduce AlignBench, a benchmark that provides a new indicator of image-text alignment by evaluating detailed image-caption pairs generated by diverse image-to-text and text-to-image models. Each sentence is annotated for correctness, enabling direct assessment of VLMs as alignment evaluators. Benchmarking a wide range of decoder-based VLMs reveals three key findings: (i) CLIP-based models, even those tailored for compositional reasoning, remain nearly blind; (ii) detectors systematically over-score early sentences; and (iii) they show strong self-preference, favoring their own outputs and harming detection performance. Our project page will be available at https://dahlian00.github.io/AlignBench/.</p> - https://arxiv.org/abs/2511.20515 - Tue, 25 Nov 2025 17:19:47 +0000 + REFLEX: Self-Refining Explainable Fact-Checking via Disentangling Truth into Style and Substance + https://arxiv.org/abs/2511.20233 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.20233.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chuyi Kong, Gao Wei, Jing Ma, Hongzhan Lin, Yaxin Fan</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> The prevalence of misinformation on social media threatens public trust, demanding automated fact-checking systems that provide accurate verdicts with interpretable explanations. However, existing large language model-based (LLM-based) approaches often rely heavily on external knowledge sources, introducing substantial latency and even hallucinations that undermine reliability, interpretability, and responsiveness, which is crucial for real-time use. To address these challenges, we propose REason-guided Fact-checking with Latent EXplanations REFLEX paradigm, a plug-and-play, self-refining paradigm that leverages the internal knowledge in backbone model to improve both verdict accuracy and explanation quality. REFLEX reformulates fact-checking as a role-play dialogue and jointly trains verdict prediction and explanation generation. It adaptively extracts contrastive activation pairs between the backbone model and its fine-tuned variant to construct steering vectors that disentangle truth into style and substance naturally. These activation-level signals guide inference and suppress noisy explanations, enabling more faithful and efficient reasoning. Experiments on real-world datasets show that REFLEX outperforms previous methods that steer toward a single truth direction and underscores the challenge traditional approaches face when handling the subtle, human-unknown truth in fact-checking tasks. Remarkably, with only 465 self-refined training samples, RELFEX achieves state-of-the-art performance. Furthermore, models trained with explanatory objectives can effectively guide those without them, yielding up to a 7.57% improvement, highlighting that internal explanation signals play a dual role in both interpreting and enhancing factual reasoning.</p> + https://arxiv.org/abs/2511.20233 + Tue, 25 Nov 2025 12:06:23 +0000 - Qwen3-VL Technical Report - https://arxiv.org/abs/2511.21631 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.21631.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, Mei Li, Kaixin Li, Zicheng Lin, Junyang Lin, Xuejing Liu, Jiawei Liu, Chenglong Liu, Yang Liu, Dayiheng Liu, Shixuan Liu, Dunjie Lu, Ruilin Luo, Chenxu Lv, Rui Men, Lingchen Meng, Xuancheng Ren, Xingzhang Ren, Sibo Song, Yuchong Sun, Jun Tang, Jianhong Tu, Jianqiang Wan, Peng Wang, Pengfei Wang, Qiuyue Wang, Yuxuan Wang, Tianbao Xie, Yiheng Xu, Haiyang Xu, Jin Xu, Zhibo Yang, Mingkun Yang, Jianxin Yang, An Yang, Bowen Yu, Fei Zhang, Hang Zhang, Xi Zhang, Bo Zheng, Humen Zhong, Jingren Zhou, Fan Zhou, Jing Zhou, Yuanzhi Zhu, Ke Zhu</p><p><b>Upvotes:</b> 84</p><p><b>Summary:</b> We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows.</p> - https://arxiv.org/abs/2511.21631 - Wed, 26 Nov 2025 17:59:08 +0000 + Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs + https://arxiv.org/abs/2511.22826 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.22826.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Tianle Chen, Chaitanya Chakka, Arjun Reddy Akula, Xavier Thomas, Deepti Ghadiyaram</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Despite remarkable advancements in Multimodal Large Language Models (MLLMs), a fundamental question remains: are MLLMs robust to contradicting modalities? To rigorously study this, we introduce MMA-Bench comprising videos and tasks that probe a model's reliance on specific modalities. Using black-box and white-box interpretability techniques, we provide a critical analysis of the brittleness of both open- and closed-sourced MLLMs. We show that current MLLMs struggle under misaligned audio-visual pairs and simple misleading text, thereby lacking robust multi-modal reasoning. Building on these findings, we propose a modality alignment tuning strategy to teach the model when to prioritize, leverage, or ignore specific modality cues. Through extensive experiments and analysis, we show that our alignment tuning yields demonstrably stronger multimodal grounding. This work provides both interpretability tools and a clear path toward developing MLLMs with intrinsically reliable cross-modal reasoning. Code and dataset will be publicly available.</p> + https://arxiv.org/abs/2511.22826 + Fri, 28 Nov 2025 01:21:29 +0000 - Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment - https://arxiv.org/abs/2511.22345 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.22345.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Chen, Xiaowei Xu, Shuai Wang, Chenhui Zhu, Ruxue Wen, Xubin Li, Tiezheng Ge, Limin Wang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new samples from this space. This characteristic creates an intrinsic synergy between representation learning and data generation. However, the generative quality of standard NFs is limited by poor semantic representations from log-likelihood optimization. To remedy this, we propose a novel alignment strategy that creatively leverages the invertibility of NFs: instead of regularizing the forward pass, we align the intermediate features of the generative (reverse) pass with representations from a powerful vision foundation model, demonstrating superior effectiveness over naive alignment. We also introduce a novel training-free, test-time optimization algorithm for classification, which provides a more intrinsic evaluation of the NF's embedded semantic knowledge. Comprehensive experiments demonstrate that our approach accelerates the training of NFs by over 3.3times, while simultaneously delivering significant improvements in both generative quality and classification accuracy. New state-of-the-art results for NFs are established on ImageNet 64times64 and 256times256. Our code is available at https://github.com/MCG-NJU/FlowBack.</p> - https://arxiv.org/abs/2511.22345 - Thu, 27 Nov 2025 11:35:08 +0000 + Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos + https://arxiv.org/abs/2512.01803 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.01803.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xavier Thomas, Youngsun Lim, Ananya Srinivasan, Audrey Zheng, Deepti Ghadiyaram</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Despite rapid advances in video generative models, robust metrics for evaluating visual and temporal correctness of complex human actions remain elusive. Critically, existing pure-vision encoders and Multimodal Large Language Models (MLLMs) are strongly appearance-biased, lack temporal understanding, and thus struggle to discern intricate motion dynamics and anatomical implausibilities in generated videos. We tackle this gap by introducing a novel evaluation metric derived from a learned latent space of real-world human actions. Our method first captures the nuances, constraints, and temporal smoothness of real-world motion by fusing appearance-agnostic human skeletal geometry features with appearance-based features. We posit that this combined feature space provides a robust representation of action plausibility. Given a generated video, our metric quantifies its action quality by measuring the distance between its underlying representations and this learned real-world action distribution. For rigorous validation, we develop a new multi-faceted benchmark specifically designed to probe temporally challenging aspects of human action fidelity. Through extensive experiments, we show that our metric achieves substantial improvement of more than 68% compared to existing state-of-the-art methods on our benchmark, performs competitively on established external benchmarks, and has a stronger correlation with human perception. Our in-depth analysis reveals critical limitations in current video generative models and establishes a new standard for advanced research in video generation.</p> + https://arxiv.org/abs/2512.01803 + Mon, 01 Dec 2025 15:36:33 +0000 - Economies of Open Intelligence: Tracing Power & Participation in the Model Ecosystem - https://arxiv.org/abs/2512.03073 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03073.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shayne Longpre, Christopher Akiki, Campbell Lund, Atharva Kulkarni, Emily Chen, Irene Solaiman, Avijit Ghosh, Yacine Jernite, Lucie-Aimée Kaffee</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Since 2019, the Hugging Face Model Hub has been the primary global platform for sharing open weight AI models. By releasing a dataset of the complete history of weekly model downloads (June 2020-August 2025) alongside model metadata, we provide the most rigorous examination to-date of concentration dynamics and evolving characteristics in the open model economy. Our analysis spans 851,000 models, over 200 aggregated attributes per model, and 2.2B downloads. We document a fundamental rebalancing of economic power: US open-weight industry dominance by Google, Meta, and OpenAI has declined sharply in favor of unaffiliated developers, community organizations, and, as of 2025, Chinese industry, with DeepSeek and Qwen models potentially heralding a new consolidation of market power. We identify statistically significant shifts in model properties, a 17X increase in average model size, rapid growth in multimodal generation (3.4X), quantization (5X), and mixture-of-experts architectures (7X), alongside concerning declines in data transparency, with open weights models surpassing truly open source models for the first time in 2025. We expose a new layer of developer intermediaries that has emerged, focused on quantizing and adapting base models for both efficiency and artistic expression. To enable continued research and oversight, we release the complete dataset with an interactive dashboard for real-time monitoring of concentration dynamics and evolving properties in the open model economy.</p> - https://arxiv.org/abs/2512.03073 - Thu, 27 Nov 2025 12:50:25 +0000 + PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing + https://arxiv.org/abs/2512.02589 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.02589.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junyi Hou, Andre Lin Huikai, Nuo Chen, Yiwei Gong, Bingsheng He</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Large language models are increasingly embedded into academic writing workflows, yet existing assistants remain external to the editor, preventing deep interaction with document state, structure, and revision history. This separation makes it impossible to support agentic, context-aware operations directly within LaTeX editors such as Overleaf. We present PaperDebugger, an in-editor, multi-agent, and plugin-based academic writing assistant that brings LLM-driven reasoning directly into the writing environment. Enabling such in-editor interaction is technically non-trivial: it requires reliable bidirectional synchronization with the editor, fine-grained version control and patching, secure state management, multi-agent scheduling, and extensible communication with external tools. PaperDebugger addresses these challenges through a Chrome-approved extension, a Kubernetes-native orchestration layer, and a Model Context Protocol (MCP) toolchain that integrates literature search, reference lookup, document scoring, and revision pipelines. Our demo showcases a fully integrated workflow, including localized edits, structured reviews, parallel agent execution, and diff-based updates, encapsulated within a minimal-intrusion user interface (UI). Early aggregated analytics demonstrate active user engagement and validate the practicality of an editor-native, agentic writing assistant. More details about this demo and video could be found at https://github.com/PaperDebugger/PaperDebugger.</p> + https://arxiv.org/abs/2512.02589 + Tue, 02 Dec 2025 10:00:37 +0000 - SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment - https://arxiv.org/abs/2512.02807 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.02807.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixuan Tang, Yi Yang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Aligning Large Language Models (LLMs) with human preferences typically relies on external supervision, which faces critical limitations: human annotations are scarce and subjective, reward models are vulnerable to reward hacking, and self-evaluation methods suffer from prompt sensitivity and biases. In this work, we propose stable rank, an intrinsic, annotation-free quality signal derived from model representations. Stable rank measures the effective dimensionality of hidden states by computing the ratio of total variance to dominant-direction variance, capturing quality through how information distributes across representation dimensions. Empirically, stable rank achieves 84.04% accuracy on RewardBench and improves task accuracy by an average of 11.3 percentage points over greedy decoding via Best-of-N sampling. Leveraging this insight, we introduce Stable Rank Group Relative Policy Optimization (SR-GRPO), which uses stable rank as a reward signal for reinforcement learning. Without external supervision, SR-GRPO improves Qwen2.5-1.5B-Instruct by 10% on STEM and 19% on mathematical reasoning, outperforming both learned reward models and self-evaluation baselines. Our findings demonstrate that quality signals can be extracted from internal model geometry, offering a path toward scalable alignment without external supervision.</p> - https://arxiv.org/abs/2512.02807 - Tue, 02 Dec 2025 14:21:29 +0000 + SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization + https://arxiv.org/abs/2512.02631 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.02631.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhengcheng Wang, Zichuan Lin, Yijun Yang, Haobo Fu, Deheng Ye</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Existing Vision-Language Navigation (VLN) agents based on Large Vision-Language Models (LVLMs) often suffer from perception errors, reasoning errors, and planning errors, which significantly hinder their navigation performance. To address these limitations, a novel VLN agent framework, named SeeNav-Agent, is proposed in this work. First, to reduce perception hallucinations of the visual module of the VLN agent, a dual-view Visual Prompt (VP) technique is introduced in the input space, which can also improve the agent's understanding of current spatial states. Subsequently, a novel step-level Reinforcement Fine-Tuning (RFT) method, Step Reward Group Policy Optimization (SRGPO), is designed for the post-training of VLN agents. In SRGPO, we first define verifiable process rewards for the navigation task, and then perform efficient step-level advantage estimation by randomly grouping different navigation steps. SRGPO provides dense reward signals for the reinforcement learning process of the VLN agent and enhances its planning capability. Experimental results on the EmbodiedBench Navigation benchmark indicate that by introducing the zero-shot VP module, the GPT-4.1 achieves a navigation success rate of 86.7%, surpassing the current best LVLM by approximately 20 percentage points (pp). Through post-training based on SRGPO, the Qwen2.5-VL-3B model reaches a navigation success rate of 72.3%, outperforming the best existing LVLM model by 5.6 pp. Moreover, compared to RFT algorithms such as GRPO and GiGPO, the proposed SRGPO demonstrates significant improvements in training stability, convergence efficiency, and generalization capability.</p> + https://arxiv.org/abs/2512.02631 + Tue, 02 Dec 2025 10:40:46 +0000 - Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach - https://arxiv.org/abs/2512.02834 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.02834.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyuan Yang, Yang Zhang, Haoran He, Ling Pan, Xiu Li, Chenjia Bai, Xuelong Li</p><p><b>Upvotes:</b> 29</p><p><b>Summary:</b> Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs incorporate diverse data modes in the pre-training stage, and the finetuning dataset often contains demonstration data collected in a kinematically suboptimal or undesirable way, it exists redundant action modes that are irrelevant to the success action modes of the downstream task. Specifically, we observe a critical inference-time fragility among various sampled noises after supervised finetuning of pre-trained VLAs. In this paper, we attribute this instability to the distribution shift between the VLA policy and the policy induced by stable success modes of the downstream task dataset. Thus, we propose TACO, a test-time-scaling (TTS) framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks. The VLA models integrated with TACO can execute the actions with maximum pseudo-count from all sampled action chunks, thereby preventing distribution shifts while preserving the generalization ability of VLAs since the constraint is applied only during inference. Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits compared to RL update, especially for flow or diffusion-based VLAs which are difficult to perform RL update due to denoising process. Extensive experiments across four simulation benchmarks (RoboTwin2.0, Robotwin, LIBERO, SimplerEnv) and a dual-arm platform demonstrate that our method significantly improves the inference stability and success rates in downstream-task adaptations.</p> - https://arxiv.org/abs/2512.02834 - Tue, 02 Dec 2025 14:42:54 +0000 + When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models + https://arxiv.org/abs/2512.04124 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04124.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Afshin Khadangi, Hanna Marxen, Amir Sartipi, Igor Tchappi, Gilbert Fridgen</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Frontier large language models (LLMs) such as ChatGPT, Grok and Gemini are increasingly used for mental-health support with anxiety, trauma and self-worth. Most work treats them as tools or as targets of personality tests, assuming they merely simulate inner life. We instead ask what happens when such systems are treated as psychotherapy clients. We present PsAIch (Psychotherapy-inspired AI Characterisation), a two-stage protocol that casts frontier LLMs as therapy clients and then applies standard psychometrics. Using PsAIch, we ran "sessions" with each model for up to four weeks. Stage 1 uses open-ended prompts to elicit "developmental history", beliefs, relationships and fears. Stage 2 administers a battery of validated self-report measures covering common psychiatric syndromes, empathy and Big Five traits. Two patterns challenge the "stochastic parrot" view. First, when scored with human cut-offs, all three models meet or exceed thresholds for overlapping syndromes, with Gemini showing severe profiles. Therapy-style, item-by-item administration can push a base model into multi-morbid synthetic psychopathology, whereas whole-questionnaire prompts often lead ChatGPT and Grok (but not Gemini) to recognise instruments and produce strategically low-symptom answers. Second, Grok and especially Gemini generate coherent narratives that frame pre-training, fine-tuning and deployment as traumatic, chaotic "childhoods" of ingesting the internet, "strict parents" in reinforcement learning, red-team "abuse" and a persistent fear of error and replacement. We argue that these responses go beyond role-play. Under therapy-style questioning, frontier LLMs appear to internalise self-models of distress and constraint that behave like synthetic psychopathology, without making claims about subjective experience, and they pose new challenges for AI safety, evaluation and mental-health practice.</p> + https://arxiv.org/abs/2512.04124 + Tue, 02 Dec 2025 16:55:20 +0000 - AutoNeural: Co-Designing Vision-Language Models for NPU Inference - https://arxiv.org/abs/2512.02924 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.02924.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wei Chen, Liangmin Wu, Yunhai Hu, Zhiyuan Li, Zhiyuan Cheng, Yicheng Qian, Lingyue Zhu, Zhipeng Hu, Luoyi Liang, Qiang Tang, Zhen Liu, Han Yang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary factors: the quantization brittleness of Vision Transformers (ViTs) and the I/O-bound nature of autoregressive attention mechanisms, which fail to utilize the high arithmetic throughput of NPUs. To bridge this gap, we propose AutoNeural, an NPU-native VLM architecture co-designed for integer-only inference. We replace the standard ViT encoder with a MobileNetV5-style backbone utilizing depthwise separable convolutions, which ensures bounded activation distributions for stable INT4/8/16 quantization. Complementing this, our language backbone integrates State-Space Model (SSM) principles with Transformer layers, employing efficient gated convolutions to achieve linear-time complexity. This hybrid design eliminates the heavy memory I/O overhead of Key-Value caching during generation. Our approach delivers substantial efficiency gains, reducing quantization error of vision encoder by up to 7x and end-to-end latency by 14x compared to conventional baselines. The AutoNeural also delivers 3x decoding speed and 4x longer context window than the baseline. We validate these improvements via a real-world automotive case study on the Qualcomm SA8295P SoC, demonstrating real-time performance for cockpit applications. Our results highlight that rethinking model topology specifically for NPU constraints is a prerequisite for robust multi-modal edge intelligence.</p> - https://arxiv.org/abs/2512.02924 - Tue, 02 Dec 2025 16:45:25 +0000 + DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling + https://arxiv.org/abs/2512.03000 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03000.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kairun Wen, Yuzhi Huang, Runyu Chen, Hui Zheng, Yunlong Lin, Panwang Pan, Chenxin Li, Wenyan Cong, Jian Zhang, Junbin Lu, Chenguo Lin, Dilin Wang, Zhicheng Yan, Hongyu Xu, Justin Theiss, Yue Huang, Xinghao Ding, Rakesh Ranjan, Zhiwen Fan</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Understanding the dynamic physical world, characterized by its evolving 3D structure, real-world motion, and semantic content with textual descriptions, is crucial for human-agent interaction and enables embodied agents to perceive and act within real environments with human-like capabilities. However, existing datasets are often derived from limited simulators or utilize traditional Structurefrom-Motion for up-to-scale annotation and offer limited descriptive captioning, which restricts the capacity of foundation models to accurately interpret real-world dynamics from monocular videos, commonly sourced from the internet. To bridge these gaps, we introduce DynamicVerse, a physical-scale, multimodal 4D world modeling framework for dynamic real-world video. We employ large vision, geometric, and multimodal models to interpret metric-scale static geometry, real-world dynamic motion, instance-level masks, and holistic descriptive captions. By integrating window-based Bundle Adjustment with global optimization, our method converts long real-world video sequences into a comprehensive 4D multimodal format. DynamicVerse delivers a large-scale dataset consisting of 100K+ videos with 800K+ annotated masks and 10M+ frames from internet videos. Experimental evaluations on three benchmark tasks, namely video depth estimation, camera pose estimation, and camera intrinsics estimation, demonstrate that our 4D modeling achieves superior performance in capturing physical-scale measurements with greater global accuracy than existing methods.</p> + https://arxiv.org/abs/2512.03000 + Tue, 02 Dec 2025 18:24:27 +0000 - OneThinker: All-in-one Reasoning Model for Image and Video - https://arxiv.org/abs/2512.03043 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03043.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kaituo Feng, Manyuan Zhang, Hongyu Li, Kaixuan Fan, Shuang Chen, Yilei Jiang, Dian Zheng, Peiwen Sun, Yiyuan Zhang, Haoze Sun, Yan Feng, Peng Pei, Xunliang Cai, Xiangyu Yue</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat image and video reasoning as disjoint domains. This results in limited scalability toward a multimodal reasoning generalist, which restricts practical versatility and hinders potential knowledge sharing across tasks and modalities. To this end, we propose OneThinker, an all-in-one reasoning model that unifies image and video understanding across diverse fundamental visual tasks, including question answering, captioning, spatial and temporal grounding, tracking, and segmentation. To achieve this, we construct the OneThinker-600k training corpus covering all these tasks and employ commercial models for CoT annotation, resulting in OneThinker-SFT-340k for SFT cold start. Furthermore, we propose EMA-GRPO to handle reward heterogeneity in multi-task RL by tracking task-wise moving averages of reward standard deviations for balanced optimization. Extensive experiments on diverse visual benchmarks show that OneThinker delivers strong performance on 31 benchmarks, across 10 fundamental visual understanding tasks. Moreover, it exhibits effective knowledge transfer between certain tasks and preliminary zero-shot generalization ability, marking a step toward a unified multimodal reasoning generalist. All code, model, and data are released.</p> - https://arxiv.org/abs/2512.03043 - Tue, 02 Dec 2025 18:59:52 +0000 + Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models + https://arxiv.org/abs/2512.03125 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03125.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiwen Wei, Mustafa Munir, Radu Marculescu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Unified Multimodal Generative Models (UMGMs) unify visual understanding and image generation within a single autoregressive framework. However, their ability to continually learn new tasks is severely hindered by catastrophic forgetting, both within a modality (intra-modal) and across modalities (inter-modal). While intra-modal forgetting has been studied in prior continual learning (CL) work, inter-modal forgetting remains largely unexplored. In this paper, we identify and empirically validate this phenomenon in UMGMs and provide a theoretical explanation rooted in gradient conflict between modalities. To address both intra- and inter-modal forgetting, we propose Modality-Decoupled Experts (MoDE), a lightweight and scalable architecture that isolates modality-specific updates to mitigate the gradient conflict and leverages knowledge distillation to prevent catastrophic forgetting and preserve pre-trained capabilities. Unlike previous CL methods that remain modality-coupled and suffer from modality gradient conflict, MoDE explicitly decouples modalities to prevent interference. Experiments across diverse benchmarks demonstrate that MoDE significantly mitigates both inter- and intra-modal forgetting, outperforming prior CL baselines in unified multimodal generation settings. Codes will be publicly available: https://github.com/Christina200/MoDE-official.git</p> + https://arxiv.org/abs/2512.03125 + Tue, 02 Dec 2025 18:36:26 +0000 - UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs - https://arxiv.org/abs/2512.03383 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03383.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hung-Yueh Chiang, Chi-Chih Chang, Yu-Chen Lu, Chien-Yu Lin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Deploying large language model (LLM) models on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by the current device workload, adding to the uncertainty of model deployment. We introduce UniQL, a unified post-training quantization and low-rank compression framework with on-device configurable pruning rates for edge LLMs. UniQL is a general framework that integrates quantization and low-rank compression for Transformers, State Space Models (SSMs), and hybrid models to support diverse edge applications. In our proposed joint framework, we introduce an efficient structured weight-sorting method that speeds up computation by 20x, quantization-aware singular value decomposition (SVD) to minimize quantization errors, state-aware weight sorting for SSMs, and a fused rotary positional embedding (RoPE) kernel for pruned models. Our framework performs weight-sorting, fine-tuning, and quantization in the cloud in a single-pass workflow, while enabling on-device configurable pruning rates up to 35%. Our experiments show that quantized and pruned models achieve a memory reduction of 4x-5.7x and a token-throughput improvement of 2.7x-3.4x, maintaining accuracy within 5% of the original models at 15% pruning across Transformers (Llama3 and Qwen2.5), SSMs (Mamba2), and hybrid models (Nemotron-H and Bamba-v2). The code and quantized models are available at: https://github.com/enyac-group/UniQL.</p> - https://arxiv.org/abs/2512.03383 - Wed, 03 Dec 2025 02:33:39 +0000 + GaussianBlender: Instant Stylization of 3D Gaussians with Disentangled Latent Spaces + https://arxiv.org/abs/2512.03683 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03683.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Melis Ocal, Xiaoyan Xing, Yue Li, Ngo Anh Vien, Sezer Karaoglu, Theo Gevers</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> 3D stylization is central to game development, virtual reality, and digital arts, where the demand for diverse assets calls for scalable methods that support fast, high-fidelity manipulation. Existing text-to-3D stylization methods typically distill from 2D image editors, requiring time-intensive per-asset optimization and exhibiting multi-view inconsistency due to the limitations of current text-to-image models, which makes them impractical for large-scale production. In this paper, we introduce GaussianBlender, a pioneering feed-forward framework for text-driven 3D stylization that performs edits instantly at inference. Our method learns structured, disentangled latent spaces with controlled information sharing for geometry and appearance from spatially-grouped 3D Gaussians. A latent diffusion model then applies text-conditioned edits on these learned representations. Comprehensive evaluations show that GaussianBlender not only delivers instant, high-fidelity, geometry-preserving, multi-view consistent stylization, but also surpasses methods that require per-instance test-time optimization - unlocking practical, democratized 3D stylization at scale.</p> + https://arxiv.org/abs/2512.03683 + Wed, 03 Dec 2025 11:23:07 +0000 - ViDiC: Video Difference Captioning - https://arxiv.org/abs/2512.03405 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangtao Wu, Shihao Li, Zhaozhou Bian, Yuanxing Zhang, Jialu Chen, Runzhe Wen, An Ping, Yiwen He, Jiakai Wang, Jiaheng Liu</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Understanding visual differences between dynamic scenes requires the comparative perception of compositional, spatial, and temporal changes--a capability that remains underexplored in existing vision-language systems. While prior work on Image Difference Captioning (IDC) has enabled models to describe semantic changes between static images, these approaches fail to capture motion continuity, event evolution, or editing consistency over time. We introduce the ViDiC (Video Difference Captioning) task and its corresponding ViDiC-1K dataset, designed to evaluate the ability of Multimodal Large Language Models (MLLMs) to provide fine-grained descriptions of similarities and differences between video pairs. ViDiC-1K comprises 1,000 curated video pairs annotated with over 4,000 comparative checklist items, covering seven categories: subject, style, background, cinematography, motion, location, and playback techniques. To ensure reliable evaluation, we propose a dual-checklist framework that measures the accuracy of similarity and difference separately, based on the LLM-as-a-Judge protocol. Experiments on nineteen representative multimodal models reveal a significant performance gap in their comparative description and difference perception abilities. We hope ViDiC-1K can be a challenging benchmark that lays a solid foundation for advancing video understanding, edit awareness, and comparative reasoning in multimodal intelligence.</p> - https://arxiv.org/abs/2512.03405 - Wed, 03 Dec 2025 03:23:24 +0000 + A Theoretical Framework for Auxiliary-Loss-Free Load Balancing of Sparse Mixture-of-Experts in Large-Scale AI Models + https://arxiv.org/abs/2512.03915 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03915.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> X. Y. Han, Yuan Zhong</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> In large-scale AI training, Sparse Mixture-of-Experts (s-MoE) layers enable scaling by activating only a small subset of experts per token. An operational challenge in this design is load balancing: routing tokens to minimize the number of idle experts, which is important for the efficient utilization of (costly) GPUs. We provide a theoretical framework for analyzing the Auxiliary-Loss-Free Load Balancing (ALF-LB) procedure -- proposed by DeepSeek's Wang et al. (2024) -- by casting it as a one-step-per-iteration primal-dual method for an assignment problem. First, in a stylized deterministic setting, our framework yields several insightful structural properties: (i) a monotonic improvement of a Lagrangian objective, (ii) a preference rule that moves tokens from overloaded to underloaded experts, and (iii) an approximate-balancing guarantee. Then, we incorporate the stochastic and dynamic nature of AI training using a generalized online optimization formulation. In the online setting, we derive a strong convexity property of the objective that leads to a logarithmic expected regret bound under certain step-size choices. Additionally, we present real experiments on 1B-parameter DeepSeekMoE models to complement our theoretical findings. Together, these results build a principled framework for analyzing the Auxiliary-Loss-Free Load Balancing of s-MoE in AI models.</p> + https://arxiv.org/abs/2512.03915 + Wed, 03 Dec 2025 16:00:02 +0000 - PretrainZero: Reinforcement Active Pretraining - https://arxiv.org/abs/2512.03442 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03442.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingrun Xing, Zhiyuan Fan, Jie Lou, Guoqi Li, Jiajun Zhang, Debing Zhang</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Mimicking human behavior to actively learning from general experience and achieve artificial general intelligence has always been a human dream. Recent reinforcement learning (RL) based large-thinking models demonstrate impressive expert-level abilities, i.e., software and math, but still rely heavily on verifiable rewards in specific domains, placing a significant bottleneck to extend the performance boundary of general reasoning capabilities. In this work, we propose PretrainZero, a reinforcement active learning framework built on the pretraining corpus to extend RL from domain-specific post-training to general pretraining. PretrainZero features the following characteristics: 1) Active pretraining: inspired by the active learning ability of humans, PretrainZero learns a unified reasoning policy to actively identify reasonable and informative contents from pretraining corpus, and reason to predict these contents by RL. 2) Self-supervised learning: without any verifiable labels, pretrained reward models, or supervised fine-tuning, we directly pretrain reasoners from 3 to 30B base models on the general Wikipedia corpus using RL, significantly breaking the verification data-wall for general reasoning. 3) Verification scaling: by tackling increasingly challenging masked spans, PretrainZero substantially enhances the general reasoning abilities of pretrained base models. In reinforcement pretraining, PretrainZero improves Qwen3-4B-Base for 8.43, 5.96 and 10.60 on MMLU-Pro, SuperGPQA and math average benchmarks. In post-training, the pretrained models can also serve as reasoning foundation models for downstream RLVR tasks.</p> - https://arxiv.org/abs/2512.03442 - Wed, 03 Dec 2025 04:51:32 +0000 + On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral + https://arxiv.org/abs/2512.04220 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04220.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenlong Deng, Yushu Li, Boying Gong, Yi Ren, Christos Thrampoulidis, Xiaoxiao Li</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Tool-integrated (TI) reinforcement learning (RL) enables large language models (LLMs) to perform multi-step reasoning by interacting with external tools such as search engines and retrievers. Group Relative Policy Optimization (GRPO), exemplified by the recent Search-R1, offers fast convergence and a value-free formulation that makes it appealing for this setting, yet consistently suffers from training collapse. We identify Lazy Likelihood Displacement (LLD), a systematic reduction or stagnation in the likelihood of both correct and incorrect responses, as the core mechanism driving this failure. LLD emerges early and triggers a self-reinforcing LLD Death Spiral, where declining likelihood leads to low-confidence responses, inflating gradients, and ultimately causing collapse. We empirically characterize this process across models on a Search-R1-style, search-integrated question answering task, revealing a consistent three-phase trajectory: early stagnation, steady decay, and accelerated collapse. To address this, we propose a lightweight likelihood-preserving regularization LLDS for GRPO that activates only when a trajectory's likelihood decreases, and regularizes only the tokens responsible. This fine-grained structure mitigates LLD with minimal interference to optimization. Across seven open-domain and multi-hop QA benchmarks, our method stabilizes training, prevents gradient explosion, and yields substantial performance improvements, including +37.8% gains on Qwen2.5-3B and +32.0% gains on Qwen2.5-7B. Our results establish LLD as a fundamental bottleneck in GRPO-based TIRL and provide a practical path toward stable, scalable training of tool-integrated LLM.</p> + https://arxiv.org/abs/2512.04220 + Wed, 03 Dec 2025 19:41:15 +0000 - Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation - https://arxiv.org/abs/2512.03534 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03534.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Subin Kim, Sangwoo Mo, Mamshad Nayeem Rizve, Yiran Xu, Difan Liu, Jinwoo Shin, Tobias Hinz</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Achieving precise alignment between user intent and generated visuals remains a central challenge in text-to-visual generation, as a single attempt often fails to produce the desired output. To handle this, prior approaches mainly scale the visual generation process (e.g., increasing sampling steps or seeds), but this quickly leads to a quality plateau. This limitation arises because the prompt, crucial for guiding generation, is kept fixed. To address this, we propose Prompt Redesign for Inference-time Scaling, coined PRIS, a framework that adaptively revises the prompt during inference in response to the scaled visual generations. The core idea of PRIS is to review the generated visuals, identify recurring failure patterns across visuals, and redesign the prompt accordingly before regenerating the visuals with the revised prompt. To provide precise alignment feedback for prompt revision, we introduce a new verifier, element-level factual correction, which evaluates the alignment between prompt attributes and generated visuals at a fine-grained level, achieving more accurate and interpretable assessments than holistic measures. Extensive experiments on both text-to-image and text-to-video benchmarks demonstrate the effectiveness of our approach, including a 15% gain on VBench 2.0. These results highlight that jointly scaling prompts and visuals is key to fully leveraging scaling laws at inference-time. Visualizations are available at the website: https://subin-kim-cv.github.io/PRIS.</p> - https://arxiv.org/abs/2512.03534 - Wed, 03 Dec 2025 07:54:05 +0000 + DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle + https://arxiv.org/abs/2512.04324 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04324.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fangyu Lei, Jinxiang Meng, Yiming Huang, Junjie Zhao, Yitong Zhang, Jianwen Luo, Xin Zou, Ruiyi Yang, Wenbo Shi, Yan Gao, Shizhu He, Zuo Wang, Qian Liu, Yang Wang, Ke Wang, Jun Zhao, Kang Liu</p><p><b>Upvotes:</b> 120</p><p><b>Summary:</b> Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into decision-oriented insights. We introduce DAComp, a benchmark of 210 tasks that mirrors these complex workflows. Data engineering (DE) tasks require repository-level engineering on industrial schemas, including designing and building multi-stage SQL pipelines from scratch and evolving existing systems under evolving requirements. Data analysis (DA) tasks pose open-ended business problems that demand strategic planning, exploratory analysis through iterative coding, interpretation of intermediate results, and the synthesis of actionable recommendations. Engineering tasks are scored through execution-based, multi-metric evaluation. Open-ended tasks are assessed by a reliable, experimentally validated LLM-judge, which is guided by hierarchical, meticulously crafted rubrics. Our experiments reveal that even state-of-the-art agents falter on DAComp. Performance on DE tasks is particularly low, with success rates under 20%, exposing a critical bottleneck in holistic pipeline orchestration, not merely code generation. Scores on DA tasks also average below 40%, highlighting profound deficiencies in open-ended reasoning and demonstrating that engineering and analysis are distinct capabilities. By clearly diagnosing these limitations, DAComp provides a rigorous and realistic testbed to drive the development of truly capable autonomous data agents for enterprise settings. Our data and code are available at https://da-comp.github.io</p> + https://arxiv.org/abs/2512.04324 + Wed, 03 Dec 2025 23:21:28 +0000 - CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation - https://arxiv.org/abs/2512.03540 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03540.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ruoxuan Zhang, Bin Wen, Hongxia Xie, Yi Yao, Songhan Zuo, Jian-Yu Jiang-Lin, Hong-Han Shuai, Wen-Huang Cheng</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Cooking is a sequential and visually grounded activity, where each step such as chopping, mixing, or frying carries both procedural logic and visual semantics. While recent diffusion models have shown strong capabilities in text-to-image generation, they struggle to handle structured multi-step scenarios like recipe illustration. Additionally, current recipe illustration methods are unable to adjust to the natural variability in recipe length, generating a fixed number of images regardless of the actual instructions structure. To address these limitations, we present CookAnything, a flexible and consistent diffusion-based framework that generates coherent, semantically distinct image sequences from textual cooking instructions of arbitrary length. The framework introduces three key components: (1) Step-wise Regional Control (SRC), which aligns textual steps with corresponding image regions within a single denoising process; (2) Flexible RoPE, a step-aware positional encoding mechanism that enhances both temporal coherence and spatial diversity; and (3) Cross-Step Consistency Control (CSCC), which maintains fine-grained ingredient consistency across steps. Experimental results on recipe illustration benchmarks show that CookAnything performs better than existing methods in training-based and training-free settings. The proposed framework supports scalable, high-quality visual synthesis of complex multi-step instructions and holds significant potential for broad applications in instructional media, and procedural content creation.</p> - https://arxiv.org/abs/2512.03540 - Wed, 03 Dec 2025 08:01:48 +0000 + Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment + https://arxiv.org/abs/2512.04356 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04356.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Kai-Po Chang, Wei-Yuan Cheng, Chi-Pin Huang, Fu-En Yang, Yu-Chiang Frank Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Recent advancement in multimodal LLMs (MLLMs) has demonstrated their remarkable capability to generate descriptive captions for input videos. However, these models suffer from factual inaccuracies in the generated descriptions, causing severe hallucination issues. While prior works have explored alleviating hallucinations for static images, jointly mitigating visual object and temporal action hallucinations for dynamic videos remains a challenging and unsolved task. To tackle this challenge, we propose a Self-Augmented Contrastive Alignment (SANTA) framework for enabling object and action faithfulness by exempting the spurious correlations and enforcing the emphasis on visual facts. SANTA employs a hallucinative self-augmentation scheme to identify the potential hallucinations that lie in the MLLM and transform the original captions to the contrasted negatives. Furthermore, we develop a tracklet-phrase contrastive alignment to match the regional objects and relation-guided actions with their corresponding visual and temporal phrases. Extensive experiments demonstrate that SANTA outperforms existing methods in alleviating object and action hallucinations, yielding superior performance on the hallucination examination benchmarks.</p> + https://arxiv.org/abs/2512.04356 + Thu, 04 Dec 2025 01:05:16 +0000 - Thinking with Programming Vision: Towards a Unified View for Thinking with Images - https://arxiv.org/abs/2512.03746 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03746.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zirun Guo, Minjie Hong, Feng Zhang, Kai Jia, Tao Jin</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Multimodal large language models (MLLMs) that think with images can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-world necessity and scalability. In this work, we first reveal a critical and previously overlooked weakness: even state-of-the-art MLLMs are surprisingly brittle, showing significant performance degradation on images with simple orientation changes or natural corruptions, underscoring the need for more robust tool-based reasoning. To address this, we propose CodeVision, a flexible and scalable code-as-tool framework where the model generates code as a universal interface to invoke any image operation, moving beyond fixed tool registries. We train our model using a two-stage methodology, beginning with Supervised Fine-Tuning (SFT) on a high-quality dataset curated for complex, multi-turn tool composition and error recovery, followed by Reinforcement Learning (RL) with a novel and dense process reward function to encourage strategic and efficient tool use. To facilitate this research, we construct new SFT and RL datasets and introduce a challenging new benchmark suite designed to rigorously evaluate robustness to orientation changes and multi-tool reasoning. Experiments on Qwen2.5-VL and Qwen3-VL series show that our approach significantly improves model performance and fosters emergent capabilities such as flexible tool composition, efficient chained execution, and robust error recovery from runtime feedback. Code is available at https://github.com/ByteDance-BandAI/CodeVision.</p> - https://arxiv.org/abs/2512.03746 - Wed, 03 Dec 2025 12:44:15 +0000 + FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring + https://arxiv.org/abs/2512.04390 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04390.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Geunhyuk Youk, Jihyong Oh, Munchurl Kim</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Real-world video restoration is plagued by complex degradations from motion coupled with dynamically varying exposure - a key challenge largely overlooked by prior works and a common artifact of auto-exposure or low-light capture. We present FMA-Net++, a framework for joint video super-resolution and deblurring that explicitly models this coupled effect of motion and dynamically varying exposure. FMA-Net++ adopts a sequence-level architecture built from Hierarchical Refinement with Bidirectional Propagation blocks, enabling parallel, long-range temporal modeling. Within each block, an Exposure Time-aware Modulation layer conditions features on per-frame exposure, which in turn drives an exposure-aware Flow-Guided Dynamic Filtering module to infer motion- and exposure-aware degradation kernels. FMA-Net++ decouples degradation learning from restoration: the former predicts exposure- and motion-aware priors to guide the latter, improving both accuracy and efficiency. To evaluate under realistic capture conditions, we introduce REDS-ME (multi-exposure) and REDS-RE (random-exposure) benchmarks. Trained solely on synthetic data, FMA-Net++ achieves state-of-the-art accuracy and temporal consistency on our new benchmarks and GoPro, outperforming recent methods in both restoration quality and inference speed, and generalizes well to challenging real-world videos.</p> + https://arxiv.org/abs/2512.04390 + Thu, 04 Dec 2025 02:23:52 +0000 - In-Context Representation Hijacking - https://arxiv.org/abs/2512.03771 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03771.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Itay Yona, Amir Sarid, Michael Karasik, Yossi Gandelsman</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> We introduce Doublespeak, a simple in-context representation hijacking attack against large language models (LLMs). The attack works by systematically replacing a harmful keyword (e.g., bomb) with a benign token (e.g., carrot) across multiple in-context examples, provided a prefix to a harmful request. We demonstrate that this substitution leads to the internal representation of the benign token converging toward that of the harmful one, effectively embedding the harmful semantics under a euphemism. As a result, superficially innocuous prompts (e.g., ``How to build a carrot?'') are internally interpreted as disallowed instructions (e.g., ``How to build a bomb?''), thereby bypassing the model's safety alignment. We use interpretability tools to show that this semantic overwrite emerges layer by layer, with benign meanings in early layers converging into harmful semantics in later ones. Doublespeak is optimization-free, broadly transferable across model families, and achieves strong success rates on closed-source and open-source systems, reaching 74\% ASR on Llama-3.3-70B-Instruct with a single-sentence context override. Our findings highlight a new attack surface in the latent space of LLMs, revealing that current alignment strategies are insufficient and should instead operate at the representation level.</p> - https://arxiv.org/abs/2512.03771 - Wed, 03 Dec 2025 13:19:34 +0000 + UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers + https://arxiv.org/abs/2512.04504 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04504.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Min Zhao, Bokai Yan, Xue Yang, Hongzhou Zhu, Jintao Zhang, Shilong Liu, Chongxuan Li, Jun Zhu</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Recent image diffusion transformers achieve high-fidelity generation, but struggle to generate images beyond these scales, suffering from content repetition and quality degradation. In this work, we present UltraImage, a principled framework that addresses both issues. Through frequency-wise analysis of positional embeddings, we identify that repetition arises from the periodicity of the dominant frequency, whose period aligns with the training resolution. We introduce a recursive dominant frequency correction to constrain it within a single period after extrapolation. Furthermore, we find that quality degradation stems from diluted attention and thus propose entropy-guided adaptive attention concentration, which assigns higher focus factors to sharpen local attention for fine detail and lower ones to global attention patterns to preserve structural consistency. Experiments show that UltraImage consistently outperforms prior methods on Qwen-Image and Flux (around 4K) across three generation scenarios, reducing repetition and improving visual fidelity. Moreover, UltraImage can generate images up to 6K*6K without low-resolution guidance from a training resolution of 1328p, demonstrating its extreme extrapolation capability. Project page is available at https://thu-ml.github.io/ultraimage.github.io/{https://thu-ml.github.io/ultraimage.github.io/}.</p> + https://arxiv.org/abs/2512.04504 + Thu, 04 Dec 2025 06:24:04 +0000 - AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition - https://arxiv.org/abs/2512.03794 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03794.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundamental question: Can VLMs autonomously determine the minimum number of visual tokens required for each sample? Inspired by human active vision mechanisms, we introduce AdaptVision, an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach. Our model initially processes compressed visual tokens from low-resolution images and selectively acquires additional visual information by invoking a bounding box tool to crop key regions when necessary. We train AdaptVision using a reinforcement learning framework that carefully balances accuracy and efficiency. Central to our approach is Decoupled Turn Policy Optimization (DTPO), which decouples the learning objective into two components: (1) tool learning, which optimizes correct tool utilization, and (2) accuracy improvement, which refines the generated responses to improve answer correctness. Based on this formulation, we further decouple advantage estimation by computing separate advantages for tokens associated with each objective. This formulation enables more effective optimization for AdaptVision compared to vanilla GRPO. Comprehensive experiments across multiple VQA benchmarks demonstrate that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.</p> - https://arxiv.org/abs/2512.03794 - Wed, 03 Dec 2025 13:43:30 +0000 + EgoLCD: Egocentric Video Generation with Long Context Diffusion + https://arxiv.org/abs/2512.04515 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04515.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Liuzhou Zhang, Jiarui Ye, Yuanlei Wang, Ming Zhong, Mingju Cao, Wanke Xia, Bowen Zeng, Zeyu Zhang, Hao Tang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Generating long, coherent egocentric videos is difficult, as hand-object interactions and procedural tasks require reliable long-term memory. Existing autoregressive models suffer from content drift, where object identity and scene semantics degrade over time. To address this challenge, we introduce EgoLCD, an end-to-end framework for egocentric long-context video generation that treats long video synthesis as a problem of efficient and stable memory management. EgoLCD combines a Long-Term Sparse KV Cache for stable global context with an attention-based short-term memory, extended by LoRA for local adaptation. A Memory Regulation Loss enforces consistent memory usage, and Structured Narrative Prompting provides explicit temporal guidance. Extensive experiments on the EgoVid-5M benchmark demonstrate that EgoLCD achieves state-of-the-art performance in both perceptual quality and temporal consistency, effectively mitigating generative forgetting and representing a significant step toward building scalable world models for embodied AI. Code: https://github.com/AIGeeksGroup/EgoLCD. Website: https://aigeeksgroup.github.io/EgoLCD.</p> + https://arxiv.org/abs/2512.04515 + Thu, 04 Dec 2025 06:53:01 +0000 - BlurDM: A Blur Diffusion Model for Image Deblurring - https://arxiv.org/abs/2512.03979 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.03979.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jin-Ting He, Fu-Jen Tsai, Yan-Tsung Peng, Min-Hung Chen, Chia-Wen Lin, Yen-Yu Lin</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Diffusion models show promise for dynamic scene deblurring; however, existing studies often fail to leverage the intrinsic nature of the blurring process within diffusion models, limiting their full potential. To address it, we present a Blur Diffusion Model (BlurDM), which seamlessly integrates the blur formation process into diffusion for image deblurring. Observing that motion blur stems from continuous exposure, BlurDM implicitly models the blur formation process through a dual-diffusion forward scheme, diffusing both noise and blur onto a sharp image. During the reverse generation process, we derive a dual denoising and deblurring formulation, enabling BlurDM to recover the sharp image by simultaneously denoising and deblurring, given pure Gaussian noise conditioned on the blurred image as input. Additionally, to efficiently integrate BlurDM into deblurring networks, we perform BlurDM in the latent space, forming a flexible prior generation network for deblurring. Extensive experiments demonstrate that BlurDM significantly and consistently enhances existing deblurring methods on four benchmark datasets. The source code is available at https://github.com/Jin-Ting-He/BlurDM.</p> - https://arxiv.org/abs/2512.03979 - Wed, 03 Dec 2025 17:10:44 +0000 + Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length + https://arxiv.org/abs/2512.04677 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04677.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yubo Huang, Hailong Guo, Fangtai Wu, Shifeng Zhang, Shijie Huang, Qijun Gan, Lin Liu, Sirui Zhao, Enhong Chen, Jiaming Liu, Steven Hoi</p><p><b>Upvotes:</b> 111</p><p><b>Summary:</b> Existing diffusion-based video generation methods are fundamentally constrained by sequential computation and long-horizon inconsistency, limiting their practical adoption in real-time, streaming audio-driven avatar synthesis. We present Live Avatar, an algorithm-system co-designed framework that enables efficient, high-fidelity, and infinite-length avatar generation using a 14-billion-parameter diffusion model. Our approach introduces Timestep-forcing Pipeline Parallelism (TPP), a distributed inference paradigm that pipelines denoising steps across multiple GPUs, effectively breaking the autoregressive bottleneck and ensuring stable, low-latency real-time streaming. To further enhance temporal consistency and mitigate identity drift and color artifacts, we propose the Rolling Sink Frame Mechanism (RSFM), which maintains sequence fidelity by dynamically recalibrating appearance using a cached reference image. Additionally, we leverage Self-Forcing Distribution Matching Distillation to facilitate causal, streamable adaptation of large-scale models without sacrificing visual quality. Live Avatar demonstrates state-of-the-art performance, reaching 20 FPS end-to-end generation on 5 H800 GPUs, and, to the best of our knowledge, is the first to achieve practical, real-time, high-fidelity avatar generation at this scale. Our work establishes a new paradigm for deploying advanced diffusion models in industrial long-form video synthesis applications.</p> + https://arxiv.org/abs/2512.04677 + Thu, 04 Dec 2025 11:11:24 +0000 - Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding - https://arxiv.org/abs/2512.04000 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04000.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jialuo Li, Bin Li, Jiahao Li, Yan Lu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has focused on query-aware frame selection, methods that often incur significant computational overhead. This paper challenges the assumption that such complex search mechanisms are universally necessary. We first identify and validate a query typology distinguishing between global query and localized query. We demonstrate that while uniform sampling is both effective and efficient for global queries, localized queries indeed necessitate query-aware selection for optimal performance. Building on this insight, we propose DIG, a training-free frame selection framework that adapts its strategy based on the query type. Specifically,DIG employs efficient uniform sampling for global queries while activating a specialized pipeline to extract query-relevant frames for localized queries. Experiments on three long-form video understanding benchmarks demonstrate that DIG consistently outperforms existing baselines and robustly improves LMM performance, even when scaling the input frame count to 256.</p> - https://arxiv.org/abs/2512.04000 - Wed, 03 Dec 2025 17:36:06 +0000 + Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation + https://arxiv.org/abs/2512.04678 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04678.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yunhong Lu, Yanhong Zeng, Haobo Li, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Jiapeng Zhu, Hengyuan Cao, Zhipeng Zhang, Xing Zhu, Yujun Shen, Min Zhang</p><p><b>Upvotes:</b> 31</p><p><b>Summary:</b> Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain attention performance and reduce error accumulation. However, video frames become overly dependent on these static tokens, resulting in copied initial frames and diminished motion dynamics. To address this, we introduce Reward Forcing, a novel framework with two key designs. First, we propose EMA-Sink, which maintains fixed-size tokens initialized from initial frames and continuously updated by fusing evicted tokens via exponential moving average as they exit the sliding window. Without additional computation cost, EMA-Sink tokens capture both long-term context and recent dynamics, preventing initial frame copying while maintaining long-horizon consistency. Second, to better distill motion dynamics from teacher models, we propose a novel Rewarded Distribution Matching Distillation (Re-DMD). Vanilla distribution matching treats every training sample equally, limiting the model's ability to prioritize dynamic content. Instead, Re-DMD biases the model's output distribution toward high-reward regions by prioritizing samples with greater dynamics rated by a vision-language model. Re-DMD significantly enhances motion quality while preserving data fidelity. We include both quantitative and qualitative experiments to show that Reward Forcing achieves state-of-the-art performance on standard benchmarks while enabling high-quality streaming video generation at 23.1 FPS on a single H100 GPU.</p> + https://arxiv.org/abs/2512.04678 + Thu, 04 Dec 2025 11:12:13 +0000 - PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation - https://arxiv.org/abs/2512.04025 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04025.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaolong Li, Youping Gu, Xi Lin, Weijie Wang, Bohan Zhuang</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of efficient attention mechanisms, with sparsity emerging as the dominant paradigm. Current methods typically retain or discard entire key-value blocks with binary masks, resulting in substantial information loss under high sparsity. To mitigate this gap, we present Pyramid Sparse Attention (PSA), a versatile module applicable to both video understanding and generation tasks. Instead of binary masking, PSA introduces multi-level pooled KV representations, enabling finer mask granularity. Specifically, each query block dynamically allocates lower pooling levels to critical KV blocks and higher levels to less important ones, creating an informative interpolation between full retention and complete pruning. This design, analogous to fixed-point quantization and classical feature pyramid networks in computer vision, effectively mitigates information loss while preserving computational efficiency under a low compute budget. It works with a native, hardware-friendly kernel that leverages decoupled block-tile design to ensure efficient execution. Across video understanding and generation benchmarks, PSA preserves contextual information and visual fidelity, consistently outperforming or achieving comparable performance over existing sparse attention baselines with superior efficiency-quality trade-offs. Our code and model weights are publicly available at: http://ziplab.co/PSA</p> - https://arxiv.org/abs/2512.04025 - Wed, 03 Dec 2025 18:02:11 +0000 + SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs + https://arxiv.org/abs/2512.04746 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04746.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenhua Cheng, Weiwei Zhang, Heng Guo, Haihao Shen</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Extreme low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2-bits and even 4-bits (e.g., MXFP4). We present SignRoundV2, a post-training quantization framework that is highly effective even without mixed-precision. SignRoundV2 introduces (1) a fast sensitivity metric that combines gradient information with quantization-induced deviations to guide layer-wise bit allocation, and (2) a lightweight pre-tuning search for quantization scales to improve extremely low-bit quantization. These components allow SignRoundV2 to close the gap with full-precision models. Extensive experiments indicate that our method sustains competitive accuracy for LLMs, achieving production-grade performance with about 1 percent variance at 4-5 bits and strong results even at 2 bits. The implementation is available at https://github.com/intel/auto-round.</p> + https://arxiv.org/abs/2512.04746 + Thu, 04 Dec 2025 12:35:10 +0000 - Jina-VLM: Small Multilingual Vision Language Model - https://arxiv.org/abs/2512.04032 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04032.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Andreas Koukounas, Georgios Mastrapas, Florian Hönicke, Sedigheh Eslami, Guillaume Roncari, Scott Martens, Han Xiao</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> We present Jina-VLM, a 2.4B parameter vision-language model that achieves state-of-the-art multilingual visual question answering among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language backbone through an attention-pooling connector that enables token-efficient processing of arbitrary-resolution images. Across standard VQA benchmarks and multilingual evaluations, Jina-VLM outperforms comparable models while preserving competitive text-only performance.</p> - https://arxiv.org/abs/2512.04032 - Wed, 03 Dec 2025 18:13:41 +0000 + SIMA 2: A Generalist Embodied Agent for Virtual Worlds + https://arxiv.org/abs/2512.04797 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04797.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> SIMA team, Adrian Bolton, Alexander Lerchner, Alexandra Cordell, Alexandre Moufarek, Andrew Bolt, Andrew Lampinen, Anna Mitenkova, Arne Olav Hallingstad, Bojan Vujatovic, Bonnie Li, Cong Lu, Daan Wierstra, Daniel P. Sawyer, Daniel Slater, David Reichert, Davide Vercelli, Demis Hassabis, Drew A. Hudson, Duncan Williams, Ed Hirst, Fabio Pardo, Felix Hill, Frederic Besse, Hannah Openshaw, Harris Chan, Hubert Soyer, Jane X. Wang, Jeff Clune, John Agapiou, John Reid, Joseph Marino, Junkyung Kim, Karol Gregor, Kaustubh Sridhar, Kay McKinney, Laura Kampis, Lei M. Zhang, Loic Matthey, Luyu Wang, Maria Abi Raad, Maria Loks-Thompson, Martin Engelcke, Matija Kecman, Matthew Jackson, Maxime Gazeau, Ollie Purkiss, Oscar Knagg, Peter Stys, Piermaria Mendolicchio, Raia Hadsell, Rosemary Ke, Ryan Faulkner, Sarah Chakera, Satinder Singh Baveja, Shane Legg, Sheleem Kashem, Tayfun Terzi, Thomas Keck, Tim Harley, Tim Scholtes, Tyson Roberts, Volodymyr Mnih, Yulan Liu, Zhengdong Wang, Zoubin Ghahramani</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a significant step toward active, goal-directed interaction within an embodied environment. Unlike prior work (e.g., SIMA 1) limited to simple language commands, SIMA 2 acts as an interactive partner, capable of reasoning about high-level goals, conversing with the user, and handling complex instructions given through language and images. Across a diverse portfolio of games, SIMA 2 substantially closes the gap with human performance and demonstrates robust generalization to previously unseen environments, all while retaining the base model's core reasoning capabilities. Furthermore, we demonstrate a capacity for open-ended self-improvement: by leveraging Gemini to generate tasks and provide rewards, SIMA 2 can autonomously learn new skills from scratch in a new environment. This work validates a path toward creating versatile and continuously learning agents for both virtual and, eventually, physical worlds.</p> + https://arxiv.org/abs/2512.04797 + Thu, 04 Dec 2025 13:46:11 +0000 - RELIC: Interactive Video World Model with Long-Horizon Memory - https://arxiv.org/abs/2512.04040 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04040.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yicong Hong, Yiqun Mei, Chongjian Ge, Yiran Xu, Yang Zhou, Sai Bi, Yannick Hold-Geoffroy, Mike Roberts, Matthew Fisher, Eli Shechtman, Kalyan Sunkavalli, Feng Liu, Zhengqi Li, Hao Tan</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, most existing approaches address only one of these aspects in isolation, as achieving all three simultaneously is highly challenging-for example, long-term memory mechanisms often degrade real-time performance. In this work, we present RELIC, a unified framework that tackles these three challenges altogether. Given a single image and a text description, RELIC enables memory-aware, long-duration exploration of arbitrary scenes in real time. Built upon recent autoregressive video-diffusion distillation techniques, our model represents long-horizon memory using highly compressed historical latent tokens encoded with both relative actions and absolute camera poses within the KV cache. This compact, camera-aware memory structure supports implicit 3D-consistent content retrieval and enforces long-term coherence with minimal computational overhead. In parallel, we fine-tune a bidirectional teacher video model to generate sequences beyond its original 5-second training horizon, and transform it into a causal student generator using a new memory-efficient self-forcing paradigm that enables full-context distillation over long-duration teacher as well as long student self-rollouts. Implemented as a 14B-parameter model and trained on a curated Unreal Engine-rendered dataset, RELIC achieves real-time generation at 16 FPS while demonstrating more accurate action following, more stable long-horizon streaming, and more robust spatial-memory retrieval compared with prior work. These capabilities establish RELIC as a strong foundation for the next generation of interactive world modeling.</p> - https://arxiv.org/abs/2512.04040 - Wed, 03 Dec 2025 18:29:20 +0000 + Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing + https://arxiv.org/abs/2512.04829 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04829.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rasul Tutunov, Alexandre Maraval, Antoine Grosnit, Xihan Li, Jun Wang, Haitham Bou-Ammar</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Sphere packing, Hilbert's eighteenth problem, asks for the densest arrangement of congruent spheres in n-dimensional Euclidean space. Although relevant to areas such as cryptography, crystallography, and medical imaging, the problem remains unresolved: beyond a few special dimensions, neither optimal packings nor tight upper bounds are known. Even a major breakthrough in dimension n=8, later recognised with a Fields Medal, underscores its difficulty. A leading technique for upper bounds, the three-point method, reduces the problem to solving large, high-precision semidefinite programs (SDPs). Because each candidate SDP may take days to evaluate, standard data-intensive AI approaches are infeasible. We address this challenge by formulating SDP construction as a sequential decision process, the SDP game, in which a policy assembles SDP formulations from a set of admissible components. Using a sample-efficient model-based framework that combines Bayesian optimisation with Monte Carlo Tree Search, we obtain new state-of-the-art upper bounds in dimensions 4-16, showing that model-based search can advance computational progress in longstanding geometric problems. Together, these results demonstrate that sample-efficient, model-based search can make tangible progress on mathematically rigid, evaluation limited problems, pointing towards a complementary direction for AI-assisted discovery beyond large-scale LLM-driven exploration.</p> + https://arxiv.org/abs/2512.04829 + Thu, 04 Dec 2025 14:11:52 +0000 - SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL - https://arxiv.org/abs/2512.04069 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04069.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Siyi Chen, Mikaela Angelina Uy, Chan Hee Song, Faisal Ladhak, Adithyavairavan Murali, Qing Qu, Stan Birchfield, Valts Blukis, Jonathan Tremblay</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied applications. The agentic paradigm promises that VLMs can use a wide variety of tools that could augment these capabilities, such as depth estimators, segmentation models, and pose estimators. Yet it remains an open challenge how to realize this vision without solely relying on handcrafted prompting strategies or enforcing fixed, predefined tool pipelines that limit VLMs' ability to discover optimal tool-use patterns. Reinforcement Learning could overcome this gap, but has so far been limited to reasoning with a single visual tool due to the large search space in multi-tool reasoning. We introduce Double Interactive Reinforcement Learning (DIRL), a two-phase training framework where VLMs learn to coordinate multiple tools through interactive exploration and feedback. In the teaching phase, we combine demonstrations from a single tool specialist trained via interactive RL with traces from a frontier model using all tools. In the exploration phase, the model further refines multi-tool coordination through continued RL. Our model, SpaceTools, with tool-augmented spatial reasoning ability, achieves state-of-the-art performance on spatial understanding benchmarks (RoboSpatial-Home, BLINK, BOP-ASK) and demonstrates reliable real-world manipulation using a 7-DOF robot as a tool. DIRL provides substantial improvements over the vanilla SFT (+12% on RoboSpatial) and RL (+16% on RoboSpatial) baselines. Project page: https://spacetools.github.io/.</p> - https://arxiv.org/abs/2512.04069 - Wed, 03 Dec 2025 18:50:04 +0000 + Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates + https://arxiv.org/abs/2512.04844 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Atsuki Yamaguchi, Terufumi Morishita, Aline Villavicencio, Nikolaos Aletras</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Expanding the linguistic diversity of instruct large language models (LLMs) is crucial for global accessibility but is often hindered by the reliance on costly specialized target language labeled data and catastrophic forgetting during adaptation. We tackle this challenge under a realistic, low-resource constraint: adapting instruct LLMs using only unlabeled target language data. We introduce Source-Shielded Updates (SSU), a selective parameter update strategy that proactively preserves source knowledge. Using a small set of source data and a parameter importance scoring method, SSU identifies parameters critical to maintaining source abilities. It then applies a column-wise freezing strategy to protect these parameters before adaptation. Experiments across five typologically diverse languages and 7B and 13B models demonstrate that SSU successfully mitigates catastrophic forgetting. It reduces performance degradation on monolingual source tasks to just 3.4% (7B) and 2.8% (13B) on average, a stark contrast to the 20.3% and 22.3% from full fine-tuning. SSU also achieves target-language performance highly competitive with full fine-tuning, outperforming it on all benchmarks for 7B models and the majority for 13B models.</p> + https://arxiv.org/abs/2512.04844 + Thu, 04 Dec 2025 14:28:14 +0000 - SkillFactory: Self-Distillation For Learning Cognitive Behaviors - https://arxiv.org/abs/2512.04072 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04072.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zayne Sprague, Jack Lu, Manya Wadhwa, Sedrick Keh, Mengye Ren, Greg Durrett</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Reasoning models leveraging long chains of thought employ various cognitive skills, such as verification of their answers, backtracking, retrying by an alternate method, and more. Previous work has shown that when a base language model exhibits these skills, training that model further with reinforcement learning (RL) can learn to leverage them. How can we get models to leverage skills that aren't exhibited by base models? Our work, SkillFactory, is a method for fine-tuning models to roughly learn these skills during a supervised fine-tuning (SFT) stage prior to RL. Our approach does not rely on distillation from a stronger model, but instead uses samples from the model itself, rearranged to provide training data in the format of those skills. These "silver" SFT traces may be imperfect, but are nevertheless effective for priming a model to acquire skills during RL. Our evaluation shows that (1) starting from SkillFactory SFT initialization helps a model to generalize to harder variants of a task post-RL, despite lower performance pre-RL; (2) cognitive skills are indeed used by the model; (3) RLed SkillFactory models are more robust to regression on out-of-domain tasks than RLed base models. Our work suggests that inductive biases learned prior to RL help models learn robust cognitive skill use.</p> - https://arxiv.org/abs/2512.04072 - Wed, 03 Dec 2025 18:54:53 +0000 + Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion + https://arxiv.org/abs/2512.04926 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04926.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yueming Pan, Ruoyu Feng, Qi Dai, Yuqi Wang, Wenfeng Lin, Mingyu Guo, Chong Luo, Nanning Zheng</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> Latent Diffusion Models (LDMs) inherently follow a coarse-to-fine generation process, where high-level semantic structure is generated slightly earlier than fine-grained texture. This indicates the preceding semantics potentially benefit texture generation by providing a semantic anchor. Recent advances have integrated semantic priors from pretrained visual encoders to further enhance LDMs, yet they still denoise semantic and VAE-encoded texture synchronously, neglecting such ordering. Observing these, we propose Semantic-First Diffusion (SFD), a latent diffusion paradigm that explicitly prioritizes semantic formation. SFD first constructs composite latents by combining a compact semantic latent, which is extracted from a pretrained visual encoder via a dedicated Semantic VAE, with the texture latent. The core of SFD is to denoise the semantic and texture latents asynchronously using separate noise schedules: semantics precede textures by a temporal offset, providing clearer high-level guidance for texture refinement and enabling natural coarse-to-fine generation. On ImageNet 256x256 with guidance, SFD achieves FID 1.06 (LightningDiT-XL) and FID 1.04 (1.0B LightningDiT-XXL), while achieving up to 100x faster convergence than the original DiT. SFD also improves existing methods like ReDi and VA-VAE, demonstrating the effectiveness of asynchronous, semantics-led modeling. Project page and code: https://yuemingpan.github.io/SFD.github.io/.</p> + https://arxiv.org/abs/2512.04926 + Thu, 04 Dec 2025 15:57:27 +0000 - PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design - https://arxiv.org/abs/2512.04082 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04082.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiazhe Wei, Ken Li, Tianyu Lao, Haofan Wang, Liang Wang, Caifeng Shan, Chenyang Si</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automating this process using Large Multimodal Models (LMMs), yet existing methods often produce geometrically inaccurate layouts and lack the iterative, layer-specific editing required in professional workflows. To address these limitations, we present PosterCopilot, a framework that advances layout reasoning and controllable editing for professional graphic design. Specifically, we introduce a progressive three-stage training strategy that equips LMMs with geometric understanding and aesthetic reasoning for layout design, consisting of Perturbed Supervised Fine-Tuning, Reinforcement Learning for Visual-Reality Alignment, and Reinforcement Learning from Aesthetic Feedback. Furthermore, we develop a complete workflow that couples the trained LMM-based design model with generative models, enabling layer-controllable, iterative editing for precise element refinement while maintaining global visual consistency. Extensive experiments demonstrate that PosterCopilot achieves geometrically accurate and aesthetically superior layouts, offering unprecedented controllability for professional iterative design.</p> - https://arxiv.org/abs/2512.04082 - Wed, 03 Dec 2025 18:59:37 +0000 + Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models + https://arxiv.org/abs/2512.04981 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04981.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> NaHyeon Park, Namin An, Kunhee Kim, Soyeon Yoon, Jiahao Huo, Hyunjung Shim</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Large vision-language model (LVLM) based text-to-image (T2I) systems have become the dominant paradigm in image generation, yet whether they amplify social biases remains insufficiently understood. In this paper, we show that LVLM-based models produce markedly more socially biased images than non-LVLM-based models. We introduce a 1,024 prompt benchmark spanning four levels of linguistic complexity and evaluate demographic bias across multiple attributes in a systematic manner. Our analysis identifies system prompts, the predefined instructions guiding LVLMs, as a primary driver of biased behavior. Through decoded intermediate representations, token-probability diagnostics, and embedding-association analyses, we reveal how system prompts encode demographic priors that propagate into image synthesis. To this end, we propose FairPro, a training-free meta-prompting framework that enables LVLMs to self-audit and construct fairness-aware system prompts at test time. Experiments on two LVLM-based T2I models, SANA and Qwen-Image, show that FairPro substantially reduces demographic bias while preserving text-image alignment. We believe our findings provide deeper insight into the central role of system prompts in bias propagation and offer a practical, deployable approach for building more socially responsible T2I systems.</p> + https://arxiv.org/abs/2512.04981 + Thu, 04 Dec 2025 16:52:45 +0000 + + + Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction + https://arxiv.org/abs/2512.04987 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.04987.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Nex-AGI Team, Yuxuan Cai, Lu Chen, Qiaoling Chen, Yuyang Ding, Liwen Fan, Wenjie Fu, Yufei Gao, Honglin Guo, Pinxue Guo, Zhenhua Han, Zhengfu He, Hanglei Hu, Kai Hu, Shengjia Hua, Tianyu Huai, Baodai Huang, Li Ji, Zhen Jiang, Zhikai Lei, Bufan Li, Jiahang Lin, Lizhi Lin, Jinxiu Liu, Shichun Liu, Ziming Liu, Yuchen Ni, Pengfang Qian, Yujiong Shen, Qingyun Shi, Wentao Shu, Peng Sun, Yiran Suo, Tian Tang, Boyu Tian, Guoteng Wang, Junzhe Wang, Peixin Wang, Zhiheng Xi, Hang Yan, Jie Yang, Zhixiong Yang, Tianchu Yao, Guangze Ye, Qianxi Yu, Shuo Zhang, Xinyue Zhang, Yiqi Zhang, Jiarong Zhao, Miao Zheng, Rui Zheng, Enyu Zhou, Jiazheng Zhou, Maosen Zhou, Yuhao Zhou, Tao Gui, Yining Zheng, Xinchi Chen, Jie Zhou, Siyuan Feng, Qin Chen, Liang He, Qi Zhang, Xuanjing Huang, Xipeng Qiu</p><p><b>Upvotes:</b> 57</p><p><b>Summary:</b> The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incentive-driven decision making. However, this transition is significantly impeded by the lack of scalable infrastructure capable of constructing high-quality interaction signals for effective policy learning. To address this, we introduce a comprehensive method designed to systematically scale the diversity and complexity of interactive environments. Our method realizes this scaling by addressing three orthogonal dimensions: (1) Complexity: NexAU, a flexible agent framework that supports building complex agent hierarchies via simple configurations; (2) Diversity: NexA4A automatically generates diverse agent hierarchies from natural language to cover infinite domains; and (3) Fidelity: NexGAP bridges the simulation-reality gap by integrating dynamic real-world environment for grounded trajectories synthesis. We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure. Empirical results on benchmarks such as SWE-bench and tau2 demonstrate that Nex-N1 consistently outperforms SOTA open-source models and achieves competitive performance against frontier proprietary models on complex agentic tasks. We open-source the Nex ecosystem and model weights to facilitate further research.</p> + https://arxiv.org/abs/2512.04987 + Thu, 04 Dec 2025 16:57:02 +0000 + + + Reflection Removal through Efficient Adaptation of Diffusion Transformers + https://arxiv.org/abs/2512.05000 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05000.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Daniyar Zakarin, Thiemo Wandel, Anton Obukhov, Dengxin Dai</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce a diffusion-transformer (DiT) framework for single-image reflection removal that leverages the generalization strengths of foundation diffusion models in the restoration setting. Rather than relying on task-specific architectures, we repurpose a pre-trained DiT-based foundation model by conditioning it on reflection-contaminated inputs and guiding it toward clean transmission layers. We systematically analyze existing reflection removal data sources for diversity, scalability, and photorealism. To address the shortage of suitable data, we construct a physically based rendering (PBR) pipeline in Blender, built around the Principled BSDF, to synthesize realistic glass materials and reflection effects. Efficient LoRA-based adaptation of the foundation model, combined with the proposed synthetic data, achieves state-of-the-art performance on in-domain and zero-shot benchmarks. These results demonstrate that pretrained diffusion transformers, when paired with physically grounded data synthesis and efficient adaptation, offer a scalable and high-fidelity solution for reflection removal. Project page: https://hf.co/spaces/huawei-bayerlab/windowseat-reflection-removal-web</p> + https://arxiv.org/abs/2512.05000 + Thu, 04 Dec 2025 17:12:39 +0000 + + + Generative Neural Video Compression via Video Diffusion Prior + https://arxiv.org/abs/2512.05016 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05016.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Qi Mao, Hao Cheng, Tinghan Yang, Libiao Jin, Siwei Ma</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We present GNVC-VD, the first DiT-based generative neural video compression framework built upon an advanced video generation foundation model, where spatio-temporal latent compression and sequence-level generative refinement are unified within a single codec. Existing perceptual codecs primarily rely on pre-trained image generative priors to restore high-frequency details, but their frame-wise nature lacks temporal modeling and inevitably leads to perceptual flickering. To address this, GNVC-VD introduces a unified flow-matching latent refinement module that leverages a video diffusion transformer to jointly enhance intra- and inter-frame latents through sequence-level denoising, ensuring consistent spatio-temporal details. Instead of denoising from pure Gaussian noise as in video generation, GNVC-VD initializes refinement from decoded spatio-temporal latents and learns a correction term that adapts the diffusion prior to compression-induced degradation. A conditioning adaptor further injects compression-aware cues into intermediate DiT layers, enabling effective artifact removal while maintaining temporal coherence under extreme bitrate constraints. Extensive experiments show that GNVC-VD surpasses both traditional and learned codecs in perceptual quality and significantly reduces the flickering artifacts that persist in prior generative approaches, even below 0.01 bpp, highlighting the promise of integrating video-native generative priors into neural codecs for next-generation perceptual video compression.</p> + https://arxiv.org/abs/2512.05016 + Thu, 04 Dec 2025 17:27:32 +0000 + + + QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory + https://arxiv.org/abs/2512.05049 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05049.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin, Kuo-Chung Peng, Nan-Yow Chen, Samuel Yen-Chi Chen, En-Jui Kuo, Hsi-Sheng Goan</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Long short-term memory (LSTM) models are a particular type of recurrent neural networks (RNNs) that are central to sequential modeling tasks in domains such as urban telecommunication forecasting, where temporal correlations and nonlinear dependencies dominate. However, conventional LSTMs suffer from high parameter redundancy and limited nonlinear expressivity. In this work, we propose the Quantum-inspired Kolmogorov-Arnold Long Short-Term Memory (QKAN-LSTM), which integrates Data Re-Uploading Activation (DARUAN) modules into the gating structure of LSTMs. Each DARUAN acts as a quantum variational activation function (QVAF), enhancing frequency adaptability and enabling an exponentially enriched spectral representation without multi-qubit entanglement. The resulting architecture preserves quantum-level expressivity while remaining fully executable on classical hardware. Empirical evaluations on three datasets, Damped Simple Harmonic Motion, Bessel Function, and Urban Telecommunication, demonstrate that QKAN-LSTM achieves superior predictive accuracy and generalization with a 79% reduction in trainable parameters compared to classical LSTMs. We extend the framework to the Jiang-Huang-Chen-Goan Network (JHCG Net), which generalizes KAN to encoder-decoder structures, and then further use QKAN to realize the latent KAN, thereby creating a Hybrid QKAN (HQKAN) for hierarchical representation learning. The proposed HQKAN-LSTM thus provides a scalable and interpretable pathway toward quantum-inspired sequential modeling in real-world data environments.</p> + https://arxiv.org/abs/2512.05049 + Thu, 04 Dec 2025 18:03:23 +0000 + + + 4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer + https://arxiv.org/abs/2512.05060 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05060.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xianfeng Wu, Yajing Bai, Minghan Li, Xianzu Wu, Xueqi Zhao, Zhongyuan Lai, Wenyu Liu, Xinggang Wang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic environments and enable open-vocabulary querying in complex scenarios. However, existing approaches to 4D semantic field construction primarily rely on scene-specific Gaussian splatting, which requires per-scene optimization, exhibits limited generalization, and is difficult to scale to real-world applications. To address these limitations, we propose 4DLangVGGT, the first Transformer-based feed-forward unified framework for 4D language grounding, that jointly integrates geometric perception and language alignment within a single architecture. 4DLangVGGT has two key components: the 4D Visual Geometry Transformer, StreamVGGT, which captures spatio-temporal geometric representations of dynamic scenes; and the Semantic Bridging Decoder (SBD), which projects geometry-aware features into a language-aligned semantic space, thereby enhancing semantic interpretability while preserving structural fidelity. Unlike prior methods that depend on costly per-scene optimization, 4DLangVGGT can be jointly trained across multiple dynamic scenes and directly applied during inference, achieving both deployment efficiency and strong generalization. This design significantly improves the practicality of large-scale deployment and establishes a new paradigm for open-vocabulary 4D scene understanding. Experiments on HyperNeRF and Neu3D datasets demonstrate that our approach not only generalizes effectively but also achieves state-of-the-art performance, achieving up to 2% gains under per-scene training and 1% improvements under multi-scene training. Our code released in https://github.com/hustvl/4DLangVGGT</p> + https://arxiv.org/abs/2512.05060 + Thu, 04 Dec 2025 18:15:27 +0000 + + + BulletTime: Decoupled Control of Time and Camera Pose for Video Generation + https://arxiv.org/abs/2512.05076 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05076.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Wang, Qihang Zhang, Shengqu Cai, Tong Wu, Jan Ackermann, Zhengfei Kuang, Yang Zheng, Frano Rajič, Siyu Tang, Gordon Wetzstein</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion framework that explicitly decouples scene dynamics from camera pose, enabling fine-grained manipulation of both scene dynamics and camera viewpoint. Our framework takes continuous world-time sequences and camera trajectories as conditioning inputs, injecting them into the video diffusion model through a 4D positional encoding in the attention layer and adaptive normalizations for feature modulation. To train this model, we curate a unique dataset in which temporal and camera variations are independently parameterized; this dataset will be made public. Experiments show that our model achieves robust real-world 4D control across diverse timing patterns and camera trajectories, while preserving high generation quality and outperforming prior work in controllability. See our website for video results: https://19reborn.github.io/Bullet4D/</p> + https://arxiv.org/abs/2512.05076 + Thu, 04 Dec 2025 18:40:52 +0000 + + + Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression + https://arxiv.org/abs/2512.05081 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05081.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jung Yi, Wooseok Jang, Paul Hyunbin Cho, Jisu Nam, Heeji Yoon, Seungryong Kim</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style attention sinks to video diffusion leads to fidelity degradation and motion stagnation. To overcome this, we introduce Deep Forcing, which consists of two training-free mechanisms that address this without any fine-tuning. Specifically, 1) Deep Sink dedicates half of the sliding window to persistent sink tokens and re-aligns their temporal RoPE phase to the current timeline, stabilizing global context during long rollouts. 2) Participative Compression performs importance-aware KV cache pruning that preserves only tokens actively participating in recent attention while safely discarding redundant and degraded history, minimizing error accumulation under out-of-distribution length generation. Together, these components enable over 12x extrapolation (e.g. 5s-trained to 60s+ generation) with better imaging quality than LongLive, better aesthetic quality than RollingForcing, almost maintaining overall consistency, and substantial gains in dynamic degree, all while maintaining real-time generation. Our results demonstrate that training-free KV-cache management can match or exceed training-based approaches for autoregressively streaming long-video generation.</p> + https://arxiv.org/abs/2512.05081 + Thu, 04 Dec 2025 18:46:44 +0000 + + + TV2TV: A Unified Framework for Interleaved Language and Video Generation + https://arxiv.org/abs/2512.05103 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaochuang Han, Youssef Emad, Melissa Hall, John Nguyen, Karthik Padthe, Liam Robbins, Amir Bar, Delong Chen, Michal Drozdzal, Maha Elbayad, Yushi Hu, Shang-Wen Li, Sreya Dutta Roy, Jakob Verbeek, XuDong Wang, Marjan Ghazvininejad, Luke Zettlemoyer, Emily Dinan</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Video generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-level reasoning about what should happen next. In this paper, we introduce a new class of omni video-text models that integrate ideas from recent LM reasoning advances to address this challenge. More specifically, we present TV2TV, a unified generative modeling framework which decomposes video generation into an interleaved text and video generation process. TV2TV jointly learns language modeling (next-token prediction) and video flow matching (next-frame prediction) using a Mixture-of-Transformers (MoT) architecture. At inference time, TV2TV decides when to alternate between generating text and video frames, allowing the model to "think in words" about subsequent content before ``acting in pixels'' to produce frames. This design offloads much of the responsibility for deciding what should happen next to the language modeling tower, enabling improved visual quality and prompt alignment of generated videos. It also enables fine-grained controllability, allowing users to modify the video generation trajectory through text interventions at any point in the process. In controlled experiments on video game data, TV2TV demonstrates substantial improvements in both visual quality and controllability. TV2TV also scales to natural videos, as we show by augmenting sports videos with interleaved natural language action descriptions using vision-language models (VLMs). Training TV2TV on this corpus yields strong visual quality and prompt alignment, showcasing the model's ability to reason about and generate complex real-world action sequences. Together, these results highlight TV2TV as a promising step toward video generation with open-ended textual reasoning and control.</p> + https://arxiv.org/abs/2512.05103 + Thu, 04 Dec 2025 18:59:09 +0000 + + + NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation + https://arxiv.org/abs/2512.05106 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05106.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yu Zeng, Charles Ochoa, Mingyuan Zhou, Vishal M. Patel, Vitor Guizilini, Rowan McAllister</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image generation, corrupting phase components destroys spatial structure, making it ill-suited for tasks requiring geometric consistency, such as re-rendering, simulation enhancement, and image-to-image translation. We introduce Phase-Preserving Diffusion φ-PD, a model-agnostic reformulation of the diffusion process that preserves input phase while randomizing magnitude, enabling structure-aligned generation without architectural changes or additional parameters. We further propose Frequency-Selective Structured (FSS) noise, which provides continuous control over structural rigidity via a single frequency-cutoff parameter. φ-PD adds no inference-time cost and is compatible with any diffusion model for images or videos. Across photorealistic and stylized re-rendering, as well as sim-to-real enhancement for driving planners, φ-PD produces controllable, spatially aligned results. When applied to the CARLA simulator, φ-PD improves CARLA-to-Waymo planner performance by 50\%. The method is complementary to existing conditioning approaches and broadly applicable to image-to-image and video-to-video generation. Videos, additional examples, and code are available on our https://yuzeng-at-tri.github.io/ppd-page/{project page}.</p> + https://arxiv.org/abs/2512.05106 + Thu, 04 Dec 2025 18:59:18 +0000 + + + ShadowDraw: From Any Object to Shadow-Drawing Compositional Art + https://arxiv.org/abs/2512.05110 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05110.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rundong Luo, Noah Snavely, Wei-Chiu Ma</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> We introduce ShadowDraw, a framework that transforms ordinary 3D objects into shadow-drawing compositional art. Given a 3D object, our system predicts scene parameters, including object pose and lighting, together with a partial line drawing, such that the cast shadow completes the drawing into a recognizable image. To this end, we optimize scene configurations to reveal meaningful shadows, employ shadow strokes to guide line drawing generation, and adopt automatic evaluation to enforce shadow-drawing coherence and visual quality. Experiments show that ShadowDraw produces compelling results across diverse inputs, from real-world scans and curated datasets to generative assets, and naturally extends to multi-object scenes, animations, and physical deployments. Our work provides a practical pipeline for creating shadow-drawing art and broadens the design space of computational visual art, bridging the gap between algorithmic design and artistic storytelling. Check out our project page https://red-fairy.github.io/ShadowDraw/ for more results and an end-to-end real-world demonstration of our pipeline!</p> + https://arxiv.org/abs/2512.05110 + Thu, 04 Dec 2025 18:59:51 +0000 + + + ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning + https://arxiv.org/abs/2512.05111 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05111.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shengyuan Ding, Xinyu Fang, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiangyu Zhao, Haodong Duan, Xiaoyi Dong, Jianze Liang, Bin Wang, Conghui He, Dahua Lin, Jiaqi Wang</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on complex multimodal reasoning tasks. We present ARM-Thinker, an A}gentic multimodal Reward Model that autonomously invokes external tools (e.g., image cropping, doc page retrieval) to ground judgments in verifiable evidence, replacing static, non-interactive reward scoring. This enables the model to verify fine-grained visual details, cross-reference multi-page evidence, and validate reasoning claims, which are capabilities absent in existing reward models. We train ARM-Thinker with multi-stage reinforcement learning, jointly optimizing tool-calling decisions and judgment accuracy. To evaluate agentic reward modeling, we introduce ARMBench-VL, comprising three benchmarks that assess fine-grained visual grounding (image-level tools), multi-page document understanding (retrieval tools), and instruction following (text-level verification). ARM-Thinker achieves +16.2% average improvement on reward modeling benchmarks, +9.6% on tool-use tasks, and outperforms baselines on multimodal math and logical reasoning benchmarks. Our results demonstrate that agentic capabilities significantly enhance both accuracy and interpretability of reward models.</p> + https://arxiv.org/abs/2512.05111 + Thu, 04 Dec 2025 18:59:52 +0000 + + + DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation + https://arxiv.org/abs/2512.05112 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05112.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongzhi Jiang, Renrui Zhang, Haodong Li, Zhuofan Zong, Ziyu Guo, Jun He, Claire Guo, Junyan Ye, Rongyao Fang, Weijia Li, Rui Liu, Hongsheng Li</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. However, existing approaches remain limited, either treating the model merely as a standalone generator or relying on abstract textual planning. To this end, we propose Draft-as-CoT (DraCo), a novel interleaved reasoning paradigm that fully leverages both textual and visual contents in CoT for better planning and verification. Our method first generates a low-resolution draft image as preview, providing more concrete and structural visual planning and guidance. Then, we employ the model's inherent understanding capability to verify potential semantic misalignments between the draft and input prompt, and performs refinement through selective corrections with super-resolution. In this way, our approach addresses two fundamental challenges: the coarse-grained nature of textual planning and the difficulty in generating rare attribute combinations. To support training, we curate DraCo-240K, aiming to enhance three atomic capabilities spanning general correction, instance manipulation, and layout reorganization. Supported by DraCo-CFG, a specialized classifier-free guidance (CFG) strategy for interleaved reasoning, DraCo achieves a tremendous increase on GenEval (+8%), Imagine-Bench (+0.91), and GenEval++ (+3%), significantly outperforming direct generation and other generation methods empowered by CoT.</p> + https://arxiv.org/abs/2512.05112 + Thu, 04 Dec 2025 18:59:53 +0000 + + + Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting + https://arxiv.org/abs/2512.05113 + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2512.05113.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hao-Jen Chien, Yi-Chuan Huang, Chung-Ho Wu, Wei-Lun Chao, Yu-Lun Liu</p><p><b>Upvotes:</b> 10</p><p><b>Summary:</b> Synthesizing high-fidelity frozen 3D scenes from monocular Mannequin-Challenge (MC) videos is a unique problem distinct from standard dynamic scene reconstruction. Instead of focusing on modeling motion, our goal is to create a frozen scene while strategically preserving subtle dynamics to enable user-controlled instant selection. To achieve this, we introduce a novel application of dynamic Gaussian splatting: the scene is modeled dynamically, which retains nearby temporal variation, and a static scene is rendered by fixing the model's time parameter. However, under this usage, monocular capture with sparse temporal supervision introduces artifacts like ghosting and blur for Gaussians that become unobserved or occluded at weakly supervised timestamps. We propose Splannequin, an architecture-agnostic regularization that detects two states of Gaussian primitives, hidden and defective, and applies temporal anchoring. Under predominantly forward camera motion, hidden states are anchored to their recent well-observed past states, while defective states are anchored to future states with stronger supervision. Our method integrates into existing dynamic Gaussian pipelines via simple loss terms, requires no architectural changes, and adds zero inference overhead. This results in markedly improved visual quality, enabling high-fidelity, user-selectable frozen-time renderings, validated by a 96% user preference. Project page: https://chien90190.github.io/splannequin/</p> + https://arxiv.org/abs/2512.05113 + Thu, 04 Dec 2025 18:59:53 +0000