中文
相关论文

相关论文: Journey Before Destination: On the importance of V…

200 篇论文

Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack of visual perception as opposed to reasoning itself. In this…

计算与语言 · 计算机科学 2026-05-20 Juncheng Wu , Hardy Chen , Haoqin Tu , Xianfeng Tang , Freda Shi , Hui Liu , Hanqing Lu , Cihang Xie , Yuyin Zhou

Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can parse natural queries about the visual content and generate human-like outputs. In this work, we explore the ability of these models to…

计算与语言 · 计算机科学 2024-03-21 Yangyi Chen , Karan Sikka , Michael Cogswell , Heng Ji , Ajay Divakaran

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Jing Bi , Junjia Guo , Susan Liang , Guangyu Sun , Luchuan Song , Yunlong Tang , Jinxi He , Jiarui Wu , Ali Vosoughi , Chen Chen , Chenliang Xu

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

Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments. Recent advances in Vision Language Models (VLMs) and Vision Language Action…

人工智能 · 计算机科学 2026-04-14 Anshul Nayak , Shahil Shaik , Yue Wang

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Weihao Xuan , Qingcheng Zeng , Heli Qi , Junjue Wang , Naoto Yokoya

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

计算与语言 · 计算机科学 2025-11-04 Sriram Balasubramanian , Samyadeep Basu , Soheil Feizi

Reinforcement learning from verifiable rewards (RLVR) has recently been extended from text-only LLMs to vision-language models (VLMs) to elicit long-chain multimodal reasoning. However, RLVR-trained VLMs still exhibit two persistent failure…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Hoang Anh Just , Yifei Fan , Handong Zhao , Jiuxiang Gu , Ruiyi Zhang , Simon Jenni , Kushal Kafle , Ruoxi Jia , Jing Shi

During reasoning in vision-language models (VLMs), false positive (FP) reasoning occurs when a model produces the correct answer but follows an incorrect reasoning path, resulting in undermined reasoning reliability. Existing approaches…

计算机视觉与模式识别 · 计算机科学 2025-11-06 Ben Zhang , LuLu Yu , Lei Gao , QuanJiang Guo , Jing Liu , Hui Gao

Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Xuchen Li , Xuzhao Li , Renjie Pi , Shiyu Hu , Jian Zhao , Jiahui Gao

Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical…

计算机视觉与模式识别 · 计算机科学 2025-09-16 Pu Jian , Junhong Wu , Wei Sun , Chen Wang , Shuo Ren , Jiajun Zhang

Although contemporary large language models (LMs) demonstrate impressive question-answering capabilities, their answers are typically the product of a single call to the model. This entails an unwelcome degree of opacity and compromises…

人工智能 · 计算机科学 2022-08-31 Antonia Creswell , Murray Shanahan

Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Changpeng Wang , Haozhe Wang , Xi Chen , Junhan Liu , Taofeng Xue , Chong Peng , Donglian Qi , Fangzhen Lin , Yunfeng Yan

Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using outcome-level verification signals, such as unit tests for code or exact-match checks for…

计算与语言 · 计算机科学 2026-01-27 Massimiliano Pronesti , Anya Belz , Yufang Hou

Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reasoning via chain-of-thought (CoT) prompting or…

机器学习 · 计算机科学 2026-03-18 Robert Welch , Emir Konuk , Kevin Smith

Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains challenging. We first show that prompting MLLMs to reason before prediction does not…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Naeun Lee , Hyunjong Kim , Sunghwan Choi , Injin Kong , Yohan Jo

Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT). However, we observe that the visual information incorporated in MCoT is often inaccurate,…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Zujing Liu , Junwen Pan , Qi She , Yuan Gao , Guisong Xia

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Tianyi Bai , Zengjie Hu , Fupeng Sun , Jiantao Qiu , Yizhen Jiang , Guangxin He , Bohan Zeng , Conghui He , Binhang Yuan , Wentao Zhang

Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or agentic workflows. However, these approaches are often…

人工智能 · 计算机科学 2026-05-15 Haozhe Wang , Qixin Xu , Changpeng Wang , Taofeng Xue , Chong Peng , Wenhu Chen , Fangzhen Lin

Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual evidence. Recent approaches typically rely on external…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Zeru Shi , Kai Mei , Yihao Quan , Dimitris N. Metaxas , Ruixiang Tang
‹ 上一页 1 2 3 10 下一页 ›