diff --git a/feed.xml b/feed.xml index f0b22c1..53b03fc 100644 --- a/feed.xml +++ b/feed.xml @@ -7,18 +7,18 @@ http://www.rssboard.org/rss-specification python-feedgen en - Sun, 23 Nov 2025 00:02:59 +0000 + Mon, 24 Nov 2025 00:02:41 +0000 Draft and Refine with Visual Experts https://arxiv.org/abs/2511.11005 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11005.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sungheon Jeong, Ryozo Masukawa, Jihong Park, Sanggeon Yun, Wenjun Huang, Hanning Chen, Mahdi Imani, Mohsen Imani</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> While recent Large Vision-Language Models (LVLMs) exhibit strong multimodal reasoning abilities, they often produce ungrounded or hallucinated responses because they rely too heavily on linguistic priors instead of visual evidence. This limitation highlights the absence of a quantitative measure of how much these models actually use visual information during reasoning. We propose Draft and Refine (DnR), an agent framework driven by a question-conditioned utilization metric. The metric quantifies the model's reliance on visual evidence by first constructing a query-conditioned relevance map to localize question-specific cues and then measuring dependence through relevance-guided probabilistic masking. Guided by this metric, the DnR agent refines its initial draft using targeted feedback from external visual experts. Each expert's output (such as boxes or masks) is rendered as visual cues on the image, and the model is re-queried to select the response that yields the largest improvement in utilization. This process strengthens visual grounding without retraining or architectural changes. Experiments across VQA and captioning benchmarks show consistent accuracy gains and reduced hallucination, demonstrating that measuring visual utilization provides a principled path toward more interpretable and evidence-driven multimodal agent systems.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.11005.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sungheon Jeong, Ryozo Masukawa, Jihong Park, Sanggeon Yun, Wenjun Huang, Hanning Chen, Mahdi Imani, Mohsen Imani</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> While recent Large Vision-Language Models (LVLMs) exhibit strong multimodal reasoning abilities, they often produce ungrounded or hallucinated responses because they rely too heavily on linguistic priors instead of visual evidence. This limitation highlights the absence of a quantitative measure of how much these models actually use visual information during reasoning. We propose Draft and Refine (DnR), an agent framework driven by a question-conditioned utilization metric. The metric quantifies the model's reliance on visual evidence by first constructing a query-conditioned relevance map to localize question-specific cues and then measuring dependence through relevance-guided probabilistic masking. Guided by this metric, the DnR agent refines its initial draft using targeted feedback from external visual experts. Each expert's output (such as boxes or masks) is rendered as visual cues on the image, and the model is re-queried to select the response that yields the largest improvement in utilization. This process strengthens visual grounding without retraining or architectural changes. Experiments across VQA and captioning benchmarks show consistent accuracy gains and reduced hallucination, demonstrating that measuring visual utilization provides a principled path toward more interpretable and evidence-driven multimodal agent systems.</p> https://arxiv.org/abs/2511.11005 Fri, 14 Nov 2025 06:50:14 +0000 Generalist Foundation Models Are Not Clinical Enough for Hospital Operations https://arxiv.org/abs/2511.13703 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lavender Y. Jiang, Angelica Chen, Xu Han, Xujin Chris Liu, Radhika Dua, Kevin Eaton, Frederick Wolff, Robert Steele, Jeff Zhang, Anton Alyakin, Qingkai Pan, Yanbing Chen, Karl L. Sangwon, Daniel A. Alber, Jaden Stryker, Jin Vivian Lee, Yindalon Aphinyanaphongs, Kyunghyun Cho, Eric Karl Oermann</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Hospitals and healthcare systems rely on operational decisions that determine patient flow, cost, and quality of care. Despite strong performance on medical knowledge and conversational benchmarks, foundation models trained on general text may lack the specialized knowledge required for these operational decisions. We introduce Lang1, a family of models (100M-7B parameters) pretrained on a specialized corpus blending 80B clinical tokens from NYU Langone Health's EHRs and 627B tokens from the internet. To rigorously evaluate Lang1 in real-world settings, we developed the REalistic Medical Evaluation (ReMedE), a benchmark derived from 668,331 EHR notes that evaluates five critical tasks: 30-day readmission prediction, 30-day mortality prediction, length of stay, comorbidity coding, and predicting insurance claims denial. In zero-shot settings, both general-purpose and specialized models underperform on four of five tasks (36.6%-71.7% AUROC), with mortality prediction being an exception. After finetuning, Lang1-1B outperforms finetuned generalist models up to 70x larger and zero-shot models up to 671x larger, improving AUROC by 3.64%-6.75% and 1.66%-23.66% respectively. We also observed cross-task scaling with joint finetuning on multiple tasks leading to improvement on other tasks. Lang1-1B effectively transfers to out-of-distribution settings, including other clinical tasks and an external health system. Our findings suggest that predictive capabilities for hospital operations require explicit supervised finetuning, and that this finetuning process is made more efficient by in-domain pretraining on EHR. Our findings support the emerging view that specialized LLMs can compete with generalist models in specialized tasks, and show that effective healthcare systems AI requires the combination of in-domain pretraining, supervised finetuning, and real-world evaluation beyond proxy benchmarks.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.13703.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lavender Y. Jiang, Angelica Chen, Xu Han, Xujin Chris Liu, Radhika Dua, Kevin Eaton, Frederick Wolff, Robert Steele, Jeff Zhang, Anton Alyakin, Qingkai Pan, Yanbing Chen, Karl L. Sangwon, Daniel A. Alber, Jaden Stryker, Jin Vivian Lee, Yindalon Aphinyanaphongs, Kyunghyun Cho, Eric Karl Oermann</p><p><b>Upvotes:</b> 18</p><p><b>Summary:</b> Hospitals and healthcare systems rely on operational decisions that determine patient flow, cost, and quality of care. Despite strong performance on medical knowledge and conversational benchmarks, foundation models trained on general text may lack the specialized knowledge required for these operational decisions. We introduce Lang1, a family of models (100M-7B parameters) pretrained on a specialized corpus blending 80B clinical tokens from NYU Langone Health's EHRs and 627B tokens from the internet. To rigorously evaluate Lang1 in real-world settings, we developed the REalistic Medical Evaluation (ReMedE), a benchmark derived from 668,331 EHR notes that evaluates five critical tasks: 30-day readmission prediction, 30-day mortality prediction, length of stay, comorbidity coding, and predicting insurance claims denial. In zero-shot settings, both general-purpose and specialized models underperform on four of five tasks (36.6%-71.7% AUROC), with mortality prediction being an exception. After finetuning, Lang1-1B outperforms finetuned generalist models up to 70x larger and zero-shot models up to 671x larger, improving AUROC by 3.64%-6.75% and 1.66%-23.66% respectively. We also observed cross-task scaling with joint finetuning on multiple tasks leading to improvement on other tasks. Lang1-1B effectively transfers to out-of-distribution settings, including other clinical tasks and an external health system. Our findings suggest that predictive capabilities for hospital operations require explicit supervised finetuning, and that this finetuning process is made more efficient by in-domain pretraining on EHR. Our findings support the emerging view that specialized LLMs can compete with generalist models in specialized tasks, and show that effective healthcare systems AI requires the combination of in-domain pretraining, supervised finetuning, and real-world evaluation beyond proxy benchmarks.</p> https://arxiv.org/abs/2511.13703 Mon, 17 Nov 2025 18:52:22 +0000 @@ -46,21 +46,21 @@ SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models https://arxiv.org/abs/2511.15605 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.15605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Senyu Fei, Siyin Wang, Li Ji, Ao Li, Shiduo Zhang, Liming Liu, Jinlong Hou, Jingjing Gong, Xianzhong Zhao, Xipeng Qiu</p><p><b>Upvotes:</b> 14</p><p><b>Summary:</b> Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital post-training strategy to overcome these limits, yet current VLA-RL methods, including group-based optimization approaches, are crippled by severe reward sparsity. Relying on binary success indicators wastes valuable information in failed trajectories, resulting in low training efficiency. To solve this, we propose Self-Referential Policy Optimization (SRPO), a novel VLA-RL framework. SRPO eliminates the need for external demonstrations or manual reward engineering by leveraging the model's own successful trajectories, generated within the current training batch, as a self-reference. This allows us to assign a progress-wise reward to failed attempts. A core innovation is the use of latent world representations to measure behavioral progress robustly. Instead of relying on raw pixels or requiring domain-specific fine-tuning, we utilize the compressed, transferable encodings from a world model's latent space. These representations naturally capture progress patterns across environments, enabling accurate, generalized trajectory comparison. Empirical evaluations on the LIBERO benchmark demonstrate SRPO's efficiency and effectiveness. Starting from a supervised baseline with 48.9% success, SRPO achieves a new state-of-the-art success rate of 99.2% in just 200 RL steps, representing a 103% relative improvement without any extra supervision. Furthermore, SRPO shows substantial robustness, achieving a 167% performance improvement on the LIBERO-Plus benchmark.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.15605.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Senyu Fei, Siyin Wang, Li Ji, Ao Li, Shiduo Zhang, Liming Liu, Jinlong Hou, Jingjing Gong, Xianzhong Zhao, Xipeng Qiu</p><p><b>Upvotes:</b> 16</p><p><b>Summary:</b> Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital post-training strategy to overcome these limits, yet current VLA-RL methods, including group-based optimization approaches, are crippled by severe reward sparsity. Relying on binary success indicators wastes valuable information in failed trajectories, resulting in low training efficiency. To solve this, we propose Self-Referential Policy Optimization (SRPO), a novel VLA-RL framework. SRPO eliminates the need for external demonstrations or manual reward engineering by leveraging the model's own successful trajectories, generated within the current training batch, as a self-reference. This allows us to assign a progress-wise reward to failed attempts. A core innovation is the use of latent world representations to measure behavioral progress robustly. Instead of relying on raw pixels or requiring domain-specific fine-tuning, we utilize the compressed, transferable encodings from a world model's latent space. These representations naturally capture progress patterns across environments, enabling accurate, generalized trajectory comparison. Empirical evaluations on the LIBERO benchmark demonstrate SRPO's efficiency and effectiveness. Starting from a supervised baseline with 48.9% success, SRPO achieves a new state-of-the-art success rate of 99.2% in just 200 RL steps, representing a 103% relative improvement without any extra supervision. Furthermore, SRPO shows substantial robustness, achieving a 167% performance improvement on the LIBERO-Plus benchmark.</p> https://arxiv.org/abs/2511.15605 Wed, 19 Nov 2025 16:52:23 +0000 First Frame Is the Place to Go for Video Content Customization https://arxiv.org/abs/2511.15700 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.15700.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxi Chen, Zongxia Li, Zhichao Liu, Guangyao Shi, Xiyang Wu, Fuxiao Liu, Cornelia Fermuller, Brandon Y. Feng, Yiannis Aloimonos</p><p><b>Upvotes:</b> 45</p><p><b>Summary:</b> What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this work, we reveal a fundamentally different perspective: video models implicitly treat the first frame as a conceptual memory buffer that stores visual entities for later reuse during generation. Leveraging this insight, we show that it's possible to achieve robust and generalized video content customization in diverse scenarios, using only 20-50 training examples without architectural changes or large-scale finetuning. This unveils a powerful, overlooked capability of video generation models for reference-based video customization.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.15700.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jingxi Chen, Zongxia Li, Zhichao Liu, Guangyao Shi, Xiyang Wu, Fuxiao Liu, Cornelia Fermuller, Brandon Y. Feng, Yiannis Aloimonos</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this work, we reveal a fundamentally different perspective: video models implicitly treat the first frame as a conceptual memory buffer that stores visual entities for later reuse during generation. Leveraging this insight, we show that it's possible to achieve robust and generalized video content customization in diverse scenarios, using only 20-50 training examples without architectural changes or large-scale finetuning. This unveils a powerful, overlooked capability of video generation models for reference-based video customization.</p> https://arxiv.org/abs/2511.15700 Wed, 19 Nov 2025 18:56:50 +0000 Step-Audio-R1 Technical Report https://arxiv.org/abs/2511.15848 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.15848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang, Haoyang Zhang, Yuxin Li, Daijiao Liu, Yayue Deng, Donghang Wu, Jun Chen, Liang Zhao, Chengyuan Yao, Hexin Liu, Eng Siong Chng, Xuerui Yang, Xiangyu Zhang, Daxin Jiang, Gang Yu</p><p><b>Upvotes:</b> 44</p><p><b>Summary:</b> Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon persists in audio language models: they consistently perform better with minimal or no reasoning, raising a fundamental question - can audio intelligence truly benefit from deliberate thinking? We introduce Step-Audio-R1, the first audio reasoning model that successfully unlocks reasoning capabilities in the audio domain. Through our proposed Modality-Grounded Reasoning Distillation (MGRD) framework, Step-Audio-R1 learns to generate audio-relevant reasoning chains that genuinely ground themselves in acoustic features rather than hallucinating disconnected deliberations. Our model exhibits strong audio reasoning capabilities, surpassing Gemini 2.5 Pro and achieving performance comparable to the state-of-the-art Gemini 3 Pro across comprehensive audio understanding and reasoning benchmarks spanning speech, environmental sounds, and music. These results demonstrate that reasoning is a transferable capability across modalities when appropriately anchored, transforming extended deliberation from a liability into a powerful asset for audio intelligence. By establishing the first successful audio reasoning model, Step-Audio-R1 opens new pathways toward building truly multimodal reasoning systems that think deeply across all sensory modalities.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.15848.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang, Haoyang Zhang, Yuxin Li, Daijiao Liu, Yayue Deng, Donghang Wu, Jun Chen, Liang Zhao, Chengyuan Yao, Hexin Liu, Eng Siong Chng, Xuerui Yang, Xiangyu Zhang, Daxin Jiang, Gang Yu</p><p><b>Upvotes:</b> 46</p><p><b>Summary:</b> Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon persists in audio language models: they consistently perform better with minimal or no reasoning, raising a fundamental question - can audio intelligence truly benefit from deliberate thinking? We introduce Step-Audio-R1, the first audio reasoning model that successfully unlocks reasoning capabilities in the audio domain. Through our proposed Modality-Grounded Reasoning Distillation (MGRD) framework, Step-Audio-R1 learns to generate audio-relevant reasoning chains that genuinely ground themselves in acoustic features rather than hallucinating disconnected deliberations. Our model exhibits strong audio reasoning capabilities, surpassing Gemini 2.5 Pro and achieving performance comparable to the state-of-the-art Gemini 3 Pro across comprehensive audio understanding and reasoning benchmarks spanning speech, environmental sounds, and music. These results demonstrate that reasoning is a transferable capability across modalities when appropriately anchored, transforming extended deliberation from a liability into a powerful asset for audio intelligence. By establishing the first successful audio reasoning model, Step-Audio-R1 opens new pathways toward building truly multimodal reasoning systems that think deeply across all sensory modalities.</p> https://arxiv.org/abs/2511.15848 Wed, 19 Nov 2025 20:12:50 +0000 @@ -74,7 +74,7 @@ Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning https://arxiv.org/abs/2511.16043 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16043.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin, Fang Wu, Yiyang Zhou, Caiming Xiong, Huaxiu Yao</p><p><b>Upvotes:</b> 59</p><p><b>Summary:</b> Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model's inherent capabilities and single-round interactions, hindering the development of complex curricula involving tool use or dynamic reasoning. We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data through multi-step co-evolution and seamless tool integration. Agent0 establishes a symbiotic competition between two agents initialized from the same base LLM: a curriculum agent that proposes increasingly challenging frontier tasks, and an executor agent that learns to solve them. We integrate external tools to enhance the executor's problem-solving capacity; this improvement, in turn, pressures the curriculum agent to construct more complex, tool-aware tasks. Through this iterative process, Agent0 establishes a self-reinforcing cycle that continuously produces high-quality curricula. Empirically, Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks. Code is available at https://github.com/aiming-lab/Agent0.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16043.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin, Fang Wu, Yiyang Zhou, Caiming Xiong, Huaxiu Yao</p><p><b>Upvotes:</b> 71</p><p><b>Summary:</b> Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model's inherent capabilities and single-round interactions, hindering the development of complex curricula involving tool use or dynamic reasoning. We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data through multi-step co-evolution and seamless tool integration. Agent0 establishes a symbiotic competition between two agents initialized from the same base LLM: a curriculum agent that proposes increasingly challenging frontier tasks, and an executor agent that learns to solve them. We integrate external tools to enhance the executor's problem-solving capacity; this improvement, in turn, pressures the curriculum agent to construct more complex, tool-aware tasks. Through this iterative process, Agent0 establishes a self-reinforcing cycle that continuously produces high-quality curricula. Empirically, Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks. Code is available at https://github.com/aiming-lab/Agent0.</p> https://arxiv.org/abs/2511.16043 Thu, 20 Nov 2025 05:01:57 +0000 @@ -88,28 +88,28 @@ NaTex: Seamless Texture Generation as Latent Color Diffusion https://arxiv.org/abs/2511.16317 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeqiang Lai, Yunfei Zhao, Zibo Zhao, Xin Yang, Xin Huang, Jingwei Huang, Xiangyu Yue, Chunchao Guo</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> We present NaTex, a native texture generation framework that predicts texture color directly in 3D space. In contrast to previous approaches that rely on baking 2D multi-view images synthesized by geometry-conditioned Multi-View Diffusion models (MVDs), NaTex avoids several inherent limitations of the MVD pipeline. These include difficulties in handling occluded regions that require inpainting, achieving precise mesh-texture alignment along boundaries, and maintaining cross-view consistency and coherence in both content and color intensity. NaTex features a novel paradigm that addresses the aforementioned issues by viewing texture as a dense color point cloud. Driven by this idea, we propose latent color diffusion, which comprises a geometry-awared color point cloud VAE and a multi-control diffusion transformer (DiT), entirely trained from scratch using 3D data, for texture reconstruction and generation. To enable precise alignment, we introduce native geometry control that conditions the DiT on direct 3D spatial information via positional embeddings and geometry latents. We co-design the VAE-DiT architecture, where the geometry latents are extracted via a dedicated geometry branch tightly coupled with the color VAE, providing fine-grained surface guidance that maintains strong correspondence with the texture. With these designs, NaTex demonstrates strong performance, significantly outperforming previous methods in texture coherence and alignment. Moreover, NaTex also exhibits strong generalization capabilities, either training-free or with simple tuning, for various downstream applications, e.g., material generation, texture refinement, and part segmentation and texturing.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16317.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zeqiang Lai, Yunfei Zhao, Zibo Zhao, Xin Yang, Xin Huang, Jingwei Huang, Xiangyu Yue, Chunchao Guo</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> We present NaTex, a native texture generation framework that predicts texture color directly in 3D space. In contrast to previous approaches that rely on baking 2D multi-view images synthesized by geometry-conditioned Multi-View Diffusion models (MVDs), NaTex avoids several inherent limitations of the MVD pipeline. These include difficulties in handling occluded regions that require inpainting, achieving precise mesh-texture alignment along boundaries, and maintaining cross-view consistency and coherence in both content and color intensity. NaTex features a novel paradigm that addresses the aforementioned issues by viewing texture as a dense color point cloud. Driven by this idea, we propose latent color diffusion, which comprises a geometry-awared color point cloud VAE and a multi-control diffusion transformer (DiT), entirely trained from scratch using 3D data, for texture reconstruction and generation. To enable precise alignment, we introduce native geometry control that conditions the DiT on direct 3D spatial information via positional embeddings and geometry latents. We co-design the VAE-DiT architecture, where the geometry latents are extracted via a dedicated geometry branch tightly coupled with the color VAE, providing fine-grained surface guidance that maintains strong correspondence with the texture. With these designs, NaTex demonstrates strong performance, significantly outperforming previous methods in texture coherence and alignment. Moreover, NaTex also exhibits strong generalization capabilities, either training-free or with simple tuning, for various downstream applications, e.g., material generation, texture refinement, and part segmentation and texturing.</p> https://arxiv.org/abs/2511.16317 Thu, 20 Nov 2025 12:47:22 +0000 MiMo-Embodied: X-Embodied Foundation Model Technical Report https://arxiv.org/abs/2511.16518 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16518.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoshuai Hao, Lei Zhou, Zhijian Huang, Zhiwen Hou, Yingbo Tang, Lingfeng Zhang, Guang Li, Zheng Lu, Shuhuai Ren, Xianhui Meng, Yuchen Zhang, Jing Wu, Jinghui Lu, Chenxu Dang, Jiayi Guan, Jianhua Wu, Zhiyi Hou, Hanbing Li, Shumeng Xia, Mingliang Zhou, Yinan Zheng, Zihao Yue, Shuhao Gu, Hao Tian, Yuannan Shen, Jianwei Cui, Wen Zhang, Shaoqing Xu, Bing Wang, Haiyang Sun, Zeyu Zhu, Yuncheng Jiang, Zibin Guo, Chuhong Gong, Chaofan Zhang, Wenbo Ding, Kun Ma, Guang Chen, Rui Cai, Diyun Xiang, Heng Qu, Fuli Luo, Hangjun Ye, Long Chen</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16518.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xiaoshuai Hao, Lei Zhou, Zhijian Huang, Zhiwen Hou, Yingbo Tang, Lingfeng Zhang, Guang Li, Zheng Lu, Shuhuai Ren, Xianhui Meng, Yuchen Zhang, Jing Wu, Jinghui Lu, Chenxu Dang, Jiayi Guan, Jianhua Wu, Zhiyi Hou, Hanbing Li, Shumeng Xia, Mingliang Zhou, Yinan Zheng, Zihao Yue, Shuhao Gu, Hao Tian, Yuannan Shen, Jianwei Cui, Wen Zhang, Shaoqing Xu, Bing Wang, Haiyang Sun, Zeyu Zhu, Yuncheng Jiang, Zibin Guo, Chuhong Gong, Chaofan Zhang, Wenbo Ding, Kun Ma, Guang Chen, Rui Cai, Diyun Xiang, Heng Qu, Fuli Luo, Hangjun Ye, Long Chen</p><p><b>Upvotes:</b> 20</p><p><b>Summary:</b> We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.</p> https://arxiv.org/abs/2511.16518 Thu, 20 Nov 2025 16:34:55 +0000 TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval https://arxiv.org/abs/2511.16528 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Özay Ezerceli, Mahmoud El Hussieni, Selva Taş, Reyhan Bayraktar, Fatma Betül Terzioğlu, Yusuf Çelebi, Yağız Asker</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Neural information retrieval systems excel in high-resource languages but remain underexplored for morphologically rich, lower-resource languages such as Turkish. Dense bi-encoders currently dominate Turkish IR, yet late-interaction models -- which retain token-level representations for fine-grained matching -- have not been systematically evaluated. We introduce TurkColBERT, the first comprehensive benchmark comparing dense encoders and late-interaction models for Turkish retrieval. Our two-stage adaptation pipeline fine-tunes English and multilingual encoders on Turkish NLI/STS tasks, then converts them into ColBERT-style retrievers using PyLate trained on MS MARCO-TR. We evaluate 10 models across five Turkish BEIR datasets covering scientific, financial, and argumentative domains. Results show strong parameter efficiency: the 1.0M-parameter colbert-hash-nano-tr is 600times smaller than the 600M turkish-e5-large dense encoder while preserving over 71\% of its average mAP. Late-interaction models that are 3--5times smaller than dense encoders significantly outperform them; ColmmBERT-base-TR yields up to +13.8\% mAP on domain-specific tasks. For production-readiness, we compare indexing algorithms: MUVERA+Rerank is 3.33times faster than PLAID and offers +1.7\% relative mAP gain. This enables low-latency retrieval, with ColmmBERT-base-TR achieving 0.54 ms query times under MUVERA. We release all checkpoints, configs, and evaluation scripts. Limitations include reliance on moderately sized datasets (leq50K documents) and translated benchmarks, which may not fully reflect real-world Turkish retrieval conditions; larger-scale MUVERA evaluations remain necessary.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16528.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Özay Ezerceli, Mahmoud El Hussieni, Selva Taş, Reyhan Bayraktar, Fatma Betül Terzioğlu, Yusuf Çelebi, Yağız Asker</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Neural information retrieval systems excel in high-resource languages but remain underexplored for morphologically rich, lower-resource languages such as Turkish. Dense bi-encoders currently dominate Turkish IR, yet late-interaction models -- which retain token-level representations for fine-grained matching -- have not been systematically evaluated. We introduce TurkColBERT, the first comprehensive benchmark comparing dense encoders and late-interaction models for Turkish retrieval. Our two-stage adaptation pipeline fine-tunes English and multilingual encoders on Turkish NLI/STS tasks, then converts them into ColBERT-style retrievers using PyLate trained on MS MARCO-TR. We evaluate 10 models across five Turkish BEIR datasets covering scientific, financial, and argumentative domains. Results show strong parameter efficiency: the 1.0M-parameter colbert-hash-nano-tr is 600times smaller than the 600M turkish-e5-large dense encoder while preserving over 71\% of its average mAP. Late-interaction models that are 3--5times smaller than dense encoders significantly outperform them; ColmmBERT-base-TR yields up to +13.8\% mAP on domain-specific tasks. For production-readiness, we compare indexing algorithms: MUVERA+Rerank is 3.33times faster than PLAID and offers +1.7\% relative mAP gain. This enables low-latency retrieval, with ColmmBERT-base-TR achieving 0.54 ms query times under MUVERA. We release all checkpoints, configs, and evaluation scripts. Limitations include reliance on moderately sized datasets (leq50K documents) and translated benchmarks, which may not fully reflect real-world Turkish retrieval conditions; larger-scale MUVERA evaluations remain necessary.</p> https://arxiv.org/abs/2511.16528 Thu, 20 Nov 2025 16:42:21 +0000 TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding https://arxiv.org/abs/2511.16595 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16595.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boshen Xu, Zihan Xiao, Jiaze Li, Jianzhong Ju, Zhenbo Luo, Jian Luan, Qin Jin</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding 10,000 frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while extending frame numbers. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16595.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Boshen Xu, Zihan Xiao, Jiaze Li, Jianzhong Ju, Zhenbo Luo, Jian Luan, Qin Jin</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding 10,000 frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while extending frame numbers. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.</p> https://arxiv.org/abs/2511.16595 Thu, 20 Nov 2025 17:48:21 +0000 @@ -123,7 +123,7 @@ SAM 3D: 3Dfy Anything in Images https://arxiv.org/abs/2511.16624 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16624.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin, Jiawei Liu, Ziqi Ma, Anushka Sagar, Bowen Song, Xiaodong Wang, Jianing Yang, Bowen Zhang, Piotr Dollár, Georgia Gkioxari, Matt Feiszli, Jitendra Malik</p><p><b>Upvotes:</b> 53</p><p><b>Summary:</b> We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve this with a human- and model-in-the-loop pipeline for annotating object shape, texture, and pose, providing visually grounded 3D reconstruction data at unprecedented scale. We learn from this data in a modern, multi-stage training framework that combines synthetic pretraining with real-world alignment, breaking the 3D "data barrier". We obtain significant gains over recent work, with at least a 5:1 win rate in human preference tests on real-world objects and scenes. We will release our code and model weights, an online demo, and a new challenging benchmark for in-the-wild 3D object reconstruction.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16624.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin, Jiawei Liu, Ziqi Ma, Anushka Sagar, Bowen Song, Xiaodong Wang, Jianing Yang, Bowen Zhang, Piotr Dollár, Georgia Gkioxari, Matt Feiszli, Jitendra Malik</p><p><b>Upvotes:</b> 64</p><p><b>Summary:</b> We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve this with a human- and model-in-the-loop pipeline for annotating object shape, texture, and pose, providing visually grounded 3D reconstruction data at unprecedented scale. We learn from this data in a modern, multi-stage training framework that combines synthetic pretraining with real-world alignment, breaking the 3D "data barrier". We obtain significant gains over recent work, with at least a 5:1 win rate in human preference tests on real-world objects and scenes. We will release our code and model weights, an online demo, and a new challenging benchmark for in-the-wild 3D object reconstruction.</p> https://arxiv.org/abs/2511.16624 Thu, 20 Nov 2025 18:31:46 +0000 @@ -137,14 +137,14 @@ Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs https://arxiv.org/abs/2511.16664 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Ruisi Cai, Marcin Chochowski, Ameya Sunil Mahabaleshwarkar, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, Jan Kautz, Bryan Catanzaro, Ashwath Aithal, Nima Tajbakhsh, Pavlo Molchanov</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Training a family of large language models targeting multiple scales and deployment objectives is prohibitively expensive, requiring separate training runs for each different size. Recent work on model compression through pruning and knowledge distillation has reduced this cost; however, this process still incurs hundreds of billions of tokens worth of training cost per compressed model. In this paper, we present Nemotron Elastic, a framework for building reasoning-oriented LLMs, including hybrid Mamba-Attention architectures, that embed multiple nested submodels within a single parent model, each optimized for different deployment configurations and budgets. Each of these submodels shares weights with the parent model and can be extracted zero-shot during deployment without additional training or fine-tuning. We enable this functionality through an end-to-end trained router, tightly coupled to a two-stage training curriculum designed specifically for reasoning models. We additionally introduce group-aware SSM elastification that preserves Mamba's structural constraints, heterogeneous MLP elastification, normalized MSE-based layer importance for improved depth selection, and knowledge distillation enabling simultaneous multi-budget optimization. We apply Nemotron Elastic to the Nemotron Nano V2 12B model, simultaneously producing a 9B and a 6B model using only 110B training tokens; this results in over 360x cost reduction compared to training model families from scratch, and around 7x compared to SoTA compression techniques. Each of the nested models performs on par or better than the SoTA in accuracy. Moreover, unlike other compression methods, the nested capability of our approach allows having a many-in-one reasoning model that has constant deployment memory against the number of models in the family.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16664.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Ruisi Cai, Marcin Chochowski, Ameya Sunil Mahabaleshwarkar, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, Jan Kautz, Bryan Catanzaro, Ashwath Aithal, Nima Tajbakhsh, Pavlo Molchanov</p><p><b>Upvotes:</b> 19</p><p><b>Summary:</b> Training a family of large language models targeting multiple scales and deployment objectives is prohibitively expensive, requiring separate training runs for each different size. Recent work on model compression through pruning and knowledge distillation has reduced this cost; however, this process still incurs hundreds of billions of tokens worth of training cost per compressed model. In this paper, we present Nemotron Elastic, a framework for building reasoning-oriented LLMs, including hybrid Mamba-Attention architectures, that embed multiple nested submodels within a single parent model, each optimized for different deployment configurations and budgets. Each of these submodels shares weights with the parent model and can be extracted zero-shot during deployment without additional training or fine-tuning. We enable this functionality through an end-to-end trained router, tightly coupled to a two-stage training curriculum designed specifically for reasoning models. We additionally introduce group-aware SSM elastification that preserves Mamba's structural constraints, heterogeneous MLP elastification, normalized MSE-based layer importance for improved depth selection, and knowledge distillation enabling simultaneous multi-budget optimization. We apply Nemotron Elastic to the Nemotron Nano V2 12B model, simultaneously producing a 9B and a 6B model using only 110B training tokens; this results in over 360x cost reduction compared to training model families from scratch, and around 7x compared to SoTA compression techniques. Each of the nested models performs on par or better than the SoTA in accuracy. Moreover, unlike other compression methods, the nested capability of our approach allows having a many-in-one reasoning model that has constant deployment memory against the number of models in the family.</p> https://arxiv.org/abs/2511.16664 Thu, 20 Nov 2025 18:59:21 +0000 V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models https://arxiv.org/abs/2511.16668 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Luo, Xuanlei Zhao, Baijiong Lin, Lingting Zhu, Liyao Tang, Yuqi Liu, Ying-Cong Chen, Shengju Qian, Xin Wang, Yang You</p><p><b>Upvotes:</b> 47</p><p><b>Summary:</b> Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. The benchmark is built from both synthetic and real-world image sequences and provides a diverse set of answer-verifiable tasks that are reproducible, scalable, and unambiguous. Evaluations of six state-of-the-art video models reveal clear dimension-wise differences, with strong variation in structured, spatial, pattern-based, and physical reasoning. We further compare video models with strong image models, analyze common hallucination behaviors, and study how video duration affects Chain-of-Frames reasoning. Overall, V-ReasonBench offers a unified and reproducible framework for measuring video reasoning and aims to support the development of models with more reliable, human-aligned reasoning skills.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16668.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yang Luo, Xuanlei Zhao, Baijiong Lin, Lingting Zhu, Liyao Tang, Yuqi Liu, Ying-Cong Chen, Shengju Qian, Xin Wang, Yang You</p><p><b>Upvotes:</b> 49</p><p><b>Summary:</b> Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. The benchmark is built from both synthetic and real-world image sequences and provides a diverse set of answer-verifiable tasks that are reproducible, scalable, and unambiguous. Evaluations of six state-of-the-art video models reveal clear dimension-wise differences, with strong variation in structured, spatial, pattern-based, and physical reasoning. We further compare video models with strong image models, analyze common hallucination behaviors, and study how video duration affects Chain-of-Frames reasoning. Overall, V-ReasonBench offers a unified and reproducible framework for measuring video reasoning and aims to support the development of models with more reliable, human-aligned reasoning skills.</p> https://arxiv.org/abs/2511.16668 Thu, 20 Nov 2025 18:59:42 +0000 @@ -158,7 +158,7 @@ Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation https://arxiv.org/abs/2511.16671 - <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16671.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Guo, Renrui Zhang, Hongyu Li, Manyuan Zhang, Xinyan Chen, Sifan Wang, Yan Feng, Peng Pei, Pheng-Ann Heng</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation process, yet they lack on-the-fly multimodal interaction during the generation itself. In this preliminary study, we introduce Thinking-while-Generating (TwiG), the first interleaved framework that enables co-evolving textual reasoning throughout the visual generation process. As visual content is progressively generating, textual reasoning is interleaved to both guide upcoming local regions and reflect on previously synthesized ones. This dynamic interplay produces more context-aware and semantically rich visual outputs. To unveil the potential of this framework, we investigate three candidate strategies, zero-shot prompting, supervised fine-tuning (SFT) on our curated TwiG-50K dataset, and reinforcement learning (RL) via a customized TwiG-GRPO strategy, each offering unique insights into the dynamics of interleaved reasoning. We hope this work inspires further research into interleaving textual reasoning for enhanced visual generation. Code will be released at: https://github.com/ZiyuGuo99/Thinking-while-Generating.</p> + <p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2511.16671.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Ziyu Guo, Renrui Zhang, Hongyu Li, Manyuan Zhang, Xinyan Chen, Sifan Wang, Yan Feng, Peng Pei, Pheng-Ann Heng</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation process, yet they lack on-the-fly multimodal interaction during the generation itself. In this preliminary study, we introduce Thinking-while-Generating (TwiG), the first interleaved framework that enables co-evolving textual reasoning throughout the visual generation process. As visual content is progressively generating, textual reasoning is interleaved to both guide upcoming local regions and reflect on previously synthesized ones. This dynamic interplay produces more context-aware and semantically rich visual outputs. To unveil the potential of this framework, we investigate three candidate strategies, zero-shot prompting, supervised fine-tuning (SFT) on our curated TwiG-50K dataset, and reinforcement learning (RL) via a customized TwiG-GRPO strategy, each offering unique insights into the dynamics of interleaved reasoning. We hope this work inspires further research into interleaving textual reasoning for enhanced visual generation. Code will be released at: https://github.com/ZiyuGuo99/Thinking-while-Generating.</p> https://arxiv.org/abs/2511.16671 Thu, 20 Nov 2025 18:59:52 +0000