中文
相关论文

相关论文: Video-Thinker: Sparking "Thinking with Videos" via…

200 篇论文

Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Sicheng Tao , Jungang Li , Yibo Yan , Junyan Zhang , Yubo Gao , Hanqian Li , ShuHang Xun , Yuxuan Fan , Hong Chen , Jianxiang He , Xuming Hu

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilities of multimodal…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Ce Zhang , Yan-Bo Lin , Ziyang Wang , Mohit Bansal , Gedas Bertasius

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Byungwoo Jeon , Yoonwoo Jeong , Hyunseok Lee , Minsu Cho , Jinwoo Shin

The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly focus on…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Kejian Zhu , Zhuoran Jin , Hongbang Yuan , Jiachun Li , Shangqing Tu , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, contemporary methods still face challenges in bridging the…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Feng Han , Yang Jiao , Shaoxiang Chen , Junhao Xu , Jingjing Chen , Yu-Gang Jiang

Recent advances in CoT reasoning and RL post-training have been reported to enhance video reasoning capabilities of MLLMs. This progress naturally raises a question: can these models perform complex video reasoning in a manner comparable to…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Junhao Cheng , Yuying Ge , Teng Wang , Yixiao Ge , Jing Liao , Ying Shan

Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large…

We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of long video reasoning by integrating three critical…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Yukang Chen , Wei Huang , Baifeng Shi , Qinghao Hu , Hanrong Ye , Ligeng Zhu , Zhijian Liu , Pavlo Molchanov , Jan Kautz , Xiaojuan Qi , Sifei Liu , Hongxu Yin , Yao Lu , Song Han

Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Baoqi Pei , Yifei Huang , Jilan Xu , Yuping He , Guo Chen , Fei Wu , Yu Qiao , Jiangmiao Pang

Large language models (LLMs) have recently shown strong reasoning abilities in domains like mathematics, coding, and scientific problem-solving, yet their potential for ranking tasks, where prime examples include retrieval, recommender…

信息检索 · 计算机科学 2025-10-17 Tao Feng , Zhigang Hua , Zijie Lei , Yan Xie , Shuang Yang , Bo Long , Jiaxuan You

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…

计算机视觉与模式识别 · 计算机科学 2025-12-05 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

Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render…

计算机视觉与模式识别 · 计算机科学 2025-06-23 Zeyuan Yang , Xueyang Yu , Delin Chen , Maohao Shen , Chuang Gan

Recent advancements in Large Language Models (LLMs) have leveraged increased test-time computation to enhance reasoning capabilities, a strategy that, while effective, incurs significant latency and resource costs, limiting their…

机器学习 · 计算机科学 2025-09-01 Hao Wen , Xinrui Wu , Yi Sun , Feifei Zhang , Liye Chen , Jie Wang , Yunxin Liu , Yunhao Liu , Ya-Qin Zhang , Yuanchun Li

Long video understanding is essential for human-like intelligence, enabling coherent perception and reasoning over extended temporal contexts. While the emerging thinking-with-frames paradigm, which alternates between global temporal…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Pengfei Hu , Meng Cao , Yingyao Wang , Yi Wang , Jiahua Dong , Jun Song , Yu Cheng , Bo Zheng , Xiaodan Liang

Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Qizhong Tan , Zhuotao Tian , Guangming Lu , Jun Yu , Wenjie Pei

Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reasoning in language modeling, the development of video models…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Cheng Yang , Haiyuan Wan , Yiran Peng , Xin Cheng , Zhaoyang Yu , Jiayi Zhang , Junchi Yu , Xinlei Yu , Xiawu Zheng , Dongzhan Zhou , Chenglin Wu

Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated strong semantic understanding capabilities, but struggles to perform precise spatio-temporal understanding. Existing spatio-temporal methods primarily focus on the…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Chengzhi Liu , Yuzhe Yang , Yue Fan , Qingyue Wei , Sheng Liu , Xin Eric Wang

Video quality assessment (VQA) aims to objectively quantify perceptual quality degradation in alignment with human visual perception. Despite recent advances, existing VQA models still suffer from two critical limitations: \textit{poor…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Linhan Cao , Wei Sun , Weixia Zhang , Xiangyang Zhu , Jun Jia , Kaiwei Zhang , Dandan Zhu , Guangtao Zhai , Xiongkuo Min

Large Language Models exhibit impressive reasoning capabilities across diverse tasks, motivating efforts to distill these capabilities into smaller models through generated reasoning data. However, direct training on such synthesized…

计算与语言 · 计算机科学 2025-02-05 Shengmin Piao , Sanghyun Park