bot: update RSS feed
This commit is contained in:
github-actions[bot]
38
feed.xml
38
feed.xml
@@ -7,7 +7,7 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Sun, 07 Dec 2025 00:02:41 +0000</lastBuildDate>
|
||||
<lastBuildDate>Mon, 08 Dec 2025 00:02:47 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>LATTICE: Democratize High-Fidelity 3D Generation at Scale</title>
|
||||
<link>https://arxiv.org/abs/2512.03052</link>
|
||||
@@ -32,14 +32,14 @@
|
||||
<item>
|
||||
<title>Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos</title>
|
||||
<link>https://arxiv.org/abs/2512.01803</link>
|
||||
<description><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> 2</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></description>
|
||||
<description><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> 3</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.01803</guid>
|
||||
<pubDate>Mon, 01 Dec 2025 15:36:33 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing</title>
|
||||
<link>https://arxiv.org/abs/2512.02589</link>
|
||||
<description><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> 29</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></description>
|
||||
<description><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> 38</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.02589</guid>
|
||||
<pubDate>Tue, 02 Dec 2025 10:00:37 +0000</pubDate>
|
||||
</item>
|
||||
@@ -60,7 +60,7 @@
|
||||
<item>
|
||||
<title>DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling</title>
|
||||
<link>https://arxiv.org/abs/2512.03000</link>
|
||||
<description><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> 16</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></description>
|
||||
<description><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> 25</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.03000</guid>
|
||||
<pubDate>Tue, 02 Dec 2025 18:24:27 +0000</pubDate>
|
||||
</item>
|
||||
@@ -74,7 +74,7 @@
|
||||
<item>
|
||||
<title>GaussianBlender: Instant Stylization of 3D Gaussians with Disentangled Latent Spaces</title>
|
||||
<link>https://arxiv.org/abs/2512.03683</link>
|
||||
<description><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></description>
|
||||
<description><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> 2</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.03683</guid>
|
||||
<pubDate>Wed, 03 Dec 2025 11:23:07 +0000</pubDate>
|
||||
</item>
|
||||
@@ -88,21 +88,21 @@
|
||||
<item>
|
||||
<title>On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral</title>
|
||||
<link>https://arxiv.org/abs/2512.04220</link>
|
||||
<description><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> 8</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></description>
|
||||
<description><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> 9</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04220</guid>
|
||||
<pubDate>Wed, 03 Dec 2025 19:41:15 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle</title>
|
||||
<link>https://arxiv.org/abs/2512.04324</link>
|
||||
<description><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> 126</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></description>
|
||||
<description><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> 128</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04324</guid>
|
||||
<pubDate>Wed, 03 Dec 2025 23:21:28 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment</title>
|
||||
<link>https://arxiv.org/abs/2512.04356</link>
|
||||
<description><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> 7</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></description>
|
||||
<description><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> 8</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04356</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 01:05:16 +0000</pubDate>
|
||||
</item>
|
||||
@@ -123,28 +123,28 @@
|
||||
<item>
|
||||
<title>EgoLCD: Egocentric Video Generation with Long Context Diffusion</title>
|
||||
<link>https://arxiv.org/abs/2512.04515</link>
|
||||
<description><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> 3</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></description>
|
||||
<description><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> 4</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04515</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 06:53:01 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length</title>
|
||||
<link>https://arxiv.org/abs/2512.04677</link>
|
||||
<description><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> 135</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></description>
|
||||
<description><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> 139</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04677</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 11:11:24 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation</title>
|
||||
<link>https://arxiv.org/abs/2512.04678</link>
|
||||
<description><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></description>
|
||||
<description><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> 33</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04678</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 11:12:13 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs</title>
|
||||
<link>https://arxiv.org/abs/2512.04746</link>
|
||||
<description><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> 8</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></description>
|
||||
<description><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> 10</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04746</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 12:35:10 +0000</pubDate>
|
||||
</item>
|
||||
@@ -172,7 +172,7 @@
|
||||
<item>
|
||||
<title>Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion</title>
|
||||
<link>https://arxiv.org/abs/2512.04926</link>
|
||||
<description><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> 28</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></description>
|
||||
<description><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> 32</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04926</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 15:57:27 +0000</pubDate>
|
||||
</item>
|
||||
@@ -186,14 +186,14 @@
|
||||
<item>
|
||||
<title>Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction</title>
|
||||
<link>https://arxiv.org/abs/2512.04987</link>
|
||||
<description><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> 60</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></description>
|
||||
<description><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> 62</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.04987</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 16:57:02 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Reflection Removal through Efficient Adaptation of Diffusion Transformers</title>
|
||||
<link>https://arxiv.org/abs/2512.05000</link>
|
||||
<description><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> 9</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></description>
|
||||
<description><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> 11</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.05000</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 17:12:39 +0000</pubDate>
|
||||
</item>
|
||||
@@ -228,7 +228,7 @@
|
||||
<item>
|
||||
<title>Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression</title>
|
||||
<link>https://arxiv.org/abs/2512.05081</link>
|
||||
<description><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> 5</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></description>
|
||||
<description><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> 19</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.05081</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 18:46:44 +0000</pubDate>
|
||||
</item>
|
||||
@@ -256,21 +256,21 @@
|
||||
<item>
|
||||
<title>ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2512.05111</link>
|
||||
<description><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> 37</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></description>
|
||||
<description><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> 42</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.05111</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 18:59:52 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation</title>
|
||||
<link>https://arxiv.org/abs/2512.05112</link>
|
||||
<description><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></description>
|
||||
<description><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> 9</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.05112</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 18:59:53 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting</title>
|
||||
<link>https://arxiv.org/abs/2512.05113</link>
|
||||
<description><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> 13</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></description>
|
||||
<description><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> 14</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></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2512.05113</guid>
|
||||
<pubDate>Thu, 04 Dec 2025 18:59:53 +0000</pubDate>
|
||||
</item>
|
||||
|
||||
Reference in New Issue
Block a user