中文
相关论文

相关论文: Less Redundancy: Boosting Practicality of Vision L…

200 篇论文

Approximately 200 million individuals around the world suffer from varying degrees of visual impairment, making it crucial to leverage AI technology to offer walking assistance for these people. With the recent progress of vision-language…

计算机视觉与模式识别 · 计算机科学 2025-03-05 Zhiqiang Yuan , Ting Zhang , Ying Deng , Jiapei Zhang , Yeshuang Zhu , Zexi Jia , Jie Zhou , Jinchao Zhang

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Dingchen Yang , Bowen Cao , Anran Zhang , Weibo Gu , Winston Hu , Guang Chen

Recent advancements in visual language models (VLMs) have notably enhanced their capabilities in handling complex Graphical User Interface (GUI) interaction tasks. Despite these improvements, current frameworks often struggle to generate…

计算与语言 · 计算机科学 2025-04-23 Zhiyuan Hu , Shiyun Xiong , Yifan Zhang , See-Kiong Ng , Anh Tuan Luu , Bo An , Shuicheng Yan , Bryan Hooi

Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using…

计算机视觉与模式识别 · 计算机科学 2025-02-03 Chenglong Wang , Yang Gan , Yifu Huo , Yongyu Mu , Murun Yang , Qiaozhi He , Tong Xiao , Chunliang Zhang , Tongran Liu , Quan Du , Di Yang , Jingbo Zhu

Vision capabilities in vision large language models (VLLMs) have consistently lagged behind their linguistic capabilities. In particular, numerous benchmark studies have demonstrated that VLLMs struggle when fine-grained visual information…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Darryl Hannan , John Cooper , Dylan White , Yijing Watkins

Natural language can offer a concise and human-interpretable means of specifying reinforcement learning (RL) tasks. The ability to extract rewards from a language instruction can enable the development of robotic systems that can learn from…

机器学习 · 计算机科学 2025-12-15 Alexey Zakharov , Shimon Whiteson

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

计算机视觉与模式识别 · 计算机科学 2025-10-03 Xuchen Li , Xuzhao Li , Jiahui Gao , Renjie Pi , Shiyu Hu , Wentao Zhang

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

计算与语言 · 计算机科学 2024-10-16 Jingyuan Qi , Zhiyang Xu , Rulin Shao , Yang Chen , Jin Di , Yu Cheng , Qifan Wang , Lifu Huang

Despite tremendous recent advances in large model reasoning ability, vision-language models (VLMs) still struggle with detailed visual reasoning, especially when compute resources are limited. To address this challenge, we draw inspiration…

机器学习 · 计算机科学 2025-08-06 Sunil Kumar , Bowen Zhao , Leo Dirac , Paulina Varshavskaya

Visual impairment affects hundreds of millions of people worldwide, severely limiting their ability to navigate urban environments safely and independently. While wearable assistive devices offer a promising platform for real-time hazard…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Antoni Valls , Jordi Sanchez-Riera

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Feiding , Yongkang Zhang , Yuhao Liao , Zijian Zeng , Chunzheng Zhu , Yaozong Zheng , Yafei Liu , Yeling Peng , Youwei Wang , Sibo Wang , Huiming Yang , Linglin Liao , Shunzhi Yang

Current Multimodal Large Language Model (MLLM) architectures face a critical tradeoff between performance and efficiency: decoder-only architectures achieve higher performance but lower efficiency, while cross-attention-based architectures…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Hongliang Li , Jiaxin Zhang , Wenhui Liao , Dezhi Peng , Kai Ding , Lianwen Jin

Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…

计算机视觉与模式识别 · 计算机科学 2025-10-23 Simone Alghisi , Gabriel Roccabruna , Massimo Rizzoli , Seyed Mahed Mousavi , Giuseppe Riccardi

Introduction: Data from wearable devices collected in free-living settings, and labelled with physical activity behaviours compatible with health research, are essential for both validating existing wearable-based measurement approaches and…

计算机视觉与模式识别 · 计算机科学 2025-05-07 Abram Schonfeldt , Benjamin Maylor , Xiaofang Chen , Ronald Clark , Aiden Doherty

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Lei Li , Yuancheng Wei , Zhihui Xie , Xuqing Yang , Yifan Song , Peiyi Wang , Chenxin An , Tianyu Liu , Sujian Li , Bill Yuchen Lin , Lingpeng Kong , Qi Liu

This paper investigates the potential of vision-language models (VLMs) to assist people with blindness and low vision (pBLV) in navigation tasks. We evaluate state-of-the-art closed-source models, including GPT-4V, GPT-4o, Gemini-1.5-Pro,…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Yu Li , Yuchen Zheng , Giles Hamilton-Fletcher , Marco Mezzavilla , Yao Wang , Sundeep Rangan , Maurizio Porfiri , Zhou Yu , John-Ross Rizzo

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in computer vision have produced powerful models for various…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Zetong Zhou , Dongping Chen , Zixian Ma , Zhihan Hu , Mingyang Fu , Sinan Wang , Yao Wan , Zhou Zhao , Ranjay Krishna

Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. However, such fine-tuning relies…

计算机视觉与模式识别 · 计算机科学 2025-02-03 Joshua R. Waite , Md. Zahid Hasan , Qisai Liu , Zhanhong Jiang , Chinmay Hegde , Soumik Sarkar

Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lean more on textual cues than visual evidence and the risk of…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Shizhan Gong , Minda Hu , Qiyuan Zhang , Chen Ma , Qi Dou
‹ 上一页 1 2 3 10 下一页 ›