中文
相关论文

相关论文: VChain: Chain-of-Visual-Thought for Reasoning in V…

200 篇论文

Recent advances in large language models elicit reasoning in a chain-of-thought that allows models to decompose problems in a human-like fashion. Though this paradigm improves multi-step reasoning ability in language models, it is limited…

Multi-hop Question Generation (QG) effectively evaluates reasoning but remains confined to text; Video Question Generation (VideoQG) is limited to zero-hop questions over single segments. To address this, we introduce VideoChain, a novel…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Arpan Phukan , Anupam Pandey , Deepjyoti Bodo , Asif Ekbal

Despite exciting recent results showing vision-language systems' capacity to reason about images using natural language, their capacity for video reasoning remains under-explored. We motivate framing video reasoning as the sequential…

Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage…

机器学习 · 计算机科学 2025-07-04 Anurag Arnab , Ahmet Iscen , Mathilde Caron , Alireza Fathi , Cordelia Schmid

We propose a novel cognitively-inspired method to improve and interpret physical simulation in vision-language models. Our ``Chain of Time" method involves generating a series of intermediate images during a simulation, and it is motivated…

计算机视觉与模式识别 · 计算机科学 2025-11-04 YingQiao Wang , Eric Bigelow , Boyi Li , Tomer Ullman

Chain of thought reasoning has demonstrated remarkable success in large language models, yet its adaptation to vision-language reasoning remains an open challenge with unclear best practices. Existing attempts typically employ reasoning…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Honghao Chen , Xingzhou Lou , Xiaokun Feng , Kaiqi Huang , Xinlong Wang

Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often…

计算机视觉与模式识别 · 计算机科学 2025-06-12 Danae Sánchez Villegas , Ingo Ziegler , Desmond Elliott

Physically Plausible Video Generation (PPVG) has emerged as a promising avenue for modeling real-world physical phenomena. PPVG requires an understanding of commonsense knowledge, which remains a challenge for video diffusion models.…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Zixuan Wang , Yixin Hu , Haolan Wang , Feng Chen , Yan Liu , Wen Li , Yinjie Lei

Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines. Existing solutions either rely on extensive manual scripting/editing or…

计算机视觉与模式识别 · 计算机科学 2025-10-03 Mingzhe Zheng , Yongqi Xu , Haojian Huang , Xuran Ma , Yexin Liu , Wenjie Shu , Yatian Pang , Feilong Tang , Qifeng Chen , Harry Yang , Ser-Nam Lim

Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines. Existing solutions either rely on extensive manual scripting/editing or…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Mingzhe Zheng , Yongqi Xu , Haojian Huang , Xuran Ma , Yexin Liu , Wenjie Shu , Yatian Pang , Feilong Tang , Qifeng Chen , Harry Yang , Ser-Nam Lim

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…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Yang Luo , Xuanlei Zhao , Baijiong Lin , Lingting Zhu , Liyao Tang , Yuqi Liu , Ying-Cong Chen , Shengju Qian , Xin Wang , Yang You

Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Ruiqi Yang , Tian Yun , Zihan Wang , Ellie Pavlick

Vision-language models (VLMs) show strong multimodal capabilities but still struggle with fine-grained vision-language reasoning. We find that long chain-of-thought (CoT) reasoning exposes diverse failure modes, including perception,…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Shenzhi Wang , Shixuan Liu , Jing Zhou , Chang Gao , Xiong-Hui Chen , Binghai Wang , An Yang , Shiji Song , Bowen Yu , Gao Huang , Junyang Lin

Visual Chain-of-Thought (VCoT) has emerged as a promising paradigm for enhancing multimodal reasoning by integrating visual perception into intermediate reasoning steps. However, existing VCoT approaches are largely confined to static…

计算机视觉与模式识别 · 计算机科学 2026-02-12 Junhua Liu , Zhangcheng Wang , Zhike Han , Ningli Wang , Guotao Liang , Kun Kuang

Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the dynamics required for complex visual reasoning. In this work,…

Current image generation and editing methods primarily process textual prompts as direct inputs without reasoning about visual composition and explicit operations. We present Generation Chain-of-Thought (GoT), a novel paradigm that enables…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Rongyao Fang , Chengqi Duan , Kun Wang , Linjiang Huang , Hao Li , Shilin Yan , Hao Tian , Xingyu Zeng , Rui Zhao , Jifeng Dai , Xihui Liu , Hongsheng Li

Chain-of-thought (CoT) reasoning has been highly successful in solving complex tasks in natural language processing, and recent multimodal large language models (MLLMs) have extended this paradigm to video reasoning. However, these models…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Yiwu Zhong , Zi-Yuan Hu , Yin Li , Liwei Wang

Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theories of humor suggest…

计算与语言 · 计算机科学 2026-03-25 Jiajun Zhang , Shijia Luo , Ruikang Zhang , Qi Su

Video generation has seen remarkable progress thanks to advancements in generative deep learning. However, generating long sequences remains a significant challenge. Generated videos should not only display coherent and continuous movement…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Jingbo Yang , Adrian G. Bors

Faithful reasoning in medical vision-language models (VLMs) requires not only accurate predictions but also transparent alignment between textual rationales and visual evidence. While Chain-of-Thought (CoT) prompting has shown promise in…

‹ 上一页 1 2 3 10 下一页 ›