中文
相关论文

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

200 篇论文

When large vision-language models are applied to the field of robotics, they encounter problems that are simple for humans yet error-prone for models. Such issues include confusion between third-person and first-person perspectives and a…

计算机视觉与模式识别 · 计算机科学 2026-01-30 Baiyu Pan , Daqin Luo , Junpeng Yang , Jiyuan Wang , Yixuan Zhang , Hailin Shi , Jichao Jiao

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient…

Recent advances in large reasoning models have been driven by reinforcement learning and test-time scaling, accompanied by growing interest in latent rather than purely textual reasoning. However, existing latent reasoning methods lack…

计算与语言 · 计算机科学 2026-04-21 Shengmin Piao , Sanghyun Park

Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat this task as a black-box classification, often confusing physically distinct motions by relying on…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Hang Wu , Yujun Cai , Zehao Li , Haonan Ge , Bowen Sun , Junsong Yuan , Yiwei Wang

Large vision-language models (VLMs) have made significant strides in 2D visual understanding tasks, sparking interest in extending these capabilities to 3D scene understanding. However, current 3D VLMs often struggle with robust reasoning…

计算机视觉与模式识别 · 计算机科学 2025-08-01 Ting Huang , Zeyu Zhang , Hao Tang

Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-training have enabled LLMs to perform step-wise reasoning, they…

人工智能 · 计算机科学 2026-05-08 Yuan Sui , Yufei He , Tri Cao , Simeng Han , Yulin Chen , Bryan Hooi

Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in…

计算机视觉与模式识别 · 计算机科学 2025-05-21 Sule Bai , Mingxing Li , Yong Liu , Jing Tang , Haoji Zhang , Lei Sun , Xiangxiang Chu , Yansong Tang

Recent advances in Large Language Models (LLMs) have been driven by test-time compute scaling - a strategy that improves reasoning by generating longer, sequential thought processes. While effective, this approach encounters a significant…

计算与语言 · 计算机科学 2025-09-08 Hao Wen , Yifan Su , Feifei Zhang , Yunxin Liu , Yunhao Liu , Ya-Qin Zhang , Yuanchun Li

Recent work has shown that eliciting Large Language Models (LLMs) to generate reasoning traces in natural language before answering the user's request can significantly improve their performance across tasks. This approach has been extended…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Sara Ghazanfari , Francesco Croce , Nicolas Flammarion , Prashanth Krishnamurthy , Farshad Khorrami , Siddharth Garg

Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models. The various inconsistencies and defects observed in such videos…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Rui Chen , Lei Sun , Jing Tang , Geng Li , Xiangxiang Chu

Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent video streams remains poorly understood. Existing multi-video benchmarks rely largely…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Sara Ghazanfari , Siddharth Garg , Prashanth Krishnamurthy , Farshad Khorrami

Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Yuhao Dong , Zuyan Liu , Shulin Tian , Yongming Rao , Ziwei Liu

Vision-language models (VLMs) show promise for autonomous driving but often lack transparent reasoning capabilities that are critical for safety. We investigate whether explicitly modeling reasoning during fine-tuning enhances VLM…

计算机视觉与模式识别 · 计算机科学 2025-04-16 Amirhosein Chahe , Lifeng Zhou

Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Hung-Ting Su , Chun-Tong Chao , Ya-Ching Hsu , Xudong Lin , Yulei Niu , Hung-Yi Lee , Winston H. Hsu

Large Vision-Language Models excel at multimodal understanding but struggle to deeply integrate visual information into their predominantly text-based reasoning processes, a key challenge in mirroring human cognition. To address this, we…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Ziwei Zheng , Michael Yang , Jack Hong , Chenxiao Zhao , Guohai Xu , Le Yang , Chao Shen , Xing Yu

Large Vision Language Models (LVLMs) possess extensive text knowledge but struggles to utilize this knowledge for fine-grained image recognition, often failing to differentiate between visually similar categories. Existing fine-tuning…

计算机视觉与模式识别 · 计算机科学 2026-01-28 Raja Kumar , Arka Sadhu , Ram Nevatia

Despite the empirical success of extensive, step-by-step reasoning in large multimodal models, long reasoning processes inevitably incur substantial computational overhead, i.e., in terms of higher token costs and increased response time,…

计算机视觉与模式识别 · 计算机科学 2026-01-07 Ruiyang Zhang , Dongzhan Zhou , Zhedong Zheng

Currently, utilizing large language models to understand the 3D world is becoming popular. Yet existing 3D-aware LLMs act as black boxes: they output bounding boxes or textual answers without revealing how those decisions are made, and they…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Zhihao Yuan , Shuyi Jiang , Chun-Mei Feng , Yaolun Zhang , Shuguang Cui , Zhen Li , Na Zhao

Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Medical VLMs often rely…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Meng Lu , Yuxing Lu , Yuchen Zhuang , Megan Mullins , Yang Xie , Guanghua Xiao , Charles Fleming , Wenqi Shi , Xuan Wang

The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning…

计算机视觉与模式识别 · 计算机科学 2025-08-18 Jianlong Wu , Wei Liu , Ye Liu , Meng Liu , Liqiang Nie , Zhouchen Lin , Chang Wen Chen