视觉大模型 / VLM - arXivDaily 专题

2505.03654 2025-05-20 cs.CV cs.AI 84%

ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant

Yifan Xiang, Zhenxi Zhang, Bin Li, Yixuan Weng, Shoujun Zhou, Yangfan He, Keqin Li

机构 * Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）； School of Engineering, Westlake University（西湖大学工程学院）； University of Minnesota – Twin Cities（明尼苏达大学双城分校）； University of Toronto（多伦多大学）

专题命中视觉推理：LLaVA(title,abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

Comments Work in progress

2505.00150 2025-05-02 cs.CV cs.AI cs.CL 84%

Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models

Minh-Hao Van, Xintao Wu

机构 * Department of EECS University of Arkanasas Fayetteville（电子工程与科学系阿肯色大学法洛维尔分校）

专题命中视觉推理：vision-language model(title,abstract)；LLaVA(abstract)；分类 cs.CV、cs.AI

2504.08772 2025-04-15 cs.LG cs.AI 84%

Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning

Younghwan Lee, Tung M. Luu, Donghoon Lee, Chang D. Yoo

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.AI、cs.LG

Comments 5 pages, ICASSP 2025. First two authors are equally contributed

2504.03164 2025-04-08 cs.CV cs.AI 84%

NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving

Kexin Tian, Jingrui Mao, Yunlong Zhang, Jiwan Jiang, Yang Zhou, Zhengzhong Tu

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.AI

2504.00938 2025-04-02 cs.AI cs.LG 84%

AI Judges in Design: Statistical Perspectives on Achieving Human Expert Equivalence With Vision-Language Models

Kristen M. Edwards, Farnaz Tehranchi, Scarlett R. Miller, Faez Ahmed

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.AI、cs.LG

Comments 21 pages, 8 tables, 6 figures, 8 tables in the appendix

2503.17142 2025-03-24 cs.CV cs.LG 84%

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

Davide Berasi, Matteo Farina, Massimiliano Mancini, Elisa Ricci, Nicola Strisciuglio

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.LG

Comments Camera-ready version for CVPR 2025 (with Supp.Mat.)

2503.06026 2025-03-11 cs.RO cs.AI cs.CV 84%

Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models

Masaru Yajima, Kei Ota, Asako Kanezaki, Rei Kawakami

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.AI

Comments Under submission

2503.03840 2025-03-07 cs.CV cs.LG 84%

Decoupling the components of geometric understanding in Vision Language Models

Eliza Kosoy, Annya Dahmani, Andrew K. Lampinen, Iulia M. Comsa, Soojin Jeong, Ishita Dasgupta, Kelsey Allen

专题命中视觉推理：vision language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.LG

Comments 8 pages

2405.15683 2025-03-07 cs.CV cs.AI cs.CL 84%

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, Dinesh Manocha

专题命中视觉推理：grounding(title)；vision-language model(abstract)；visual reasoning(abstract)；分类 cs.CV、cs.AI

Comments Accepted to ICLR 2025. Project: https://sreyan88.github.io/VDGD/

2502.16707 2025-02-25 cs.RO cs.AI cs.LG 84%

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

Yunhai Feng, Jiaming Han, Zhuoran Yang, Xiangyu Yue, Sergey Levine, Jianlan Luo

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.AI、cs.LG

2502.16428 2025-02-25 cs.CV cs.AI 84%

Visual Reasoning Evaluation of Grok, Deepseek Janus, Gemini, Qwen, Mistral, and ChatGPT

Nidhal Jegham, Marwan Abdelatti, Abdeltawab Hendawi

专题命中视觉推理：visual reasoning(title,abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

2309.09809 2025-02-25 cs.CV cs.AI 84%

A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks

Wentao Wan, Nan Kang, Zeqing Wang, Zhuojie Yang, Liang Lin, Keze Wang

专题命中视觉推理：visual reasoning(title,abstract)；vision-language model(abstract)；分类 cs.CV、cs.AI

2402.18409 2025-02-14 cs.AI cs.CL cs.CV 84%

A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models

Xiujie Song, Mengyue Wu, Kenny Q. Zhu, Chunhao Zhang, Yanyi Chen

专题命中视觉推理：vision-language model(title,abstract)；visual question answering(abstract)；分类 cs.CV、cs.AI

2412.15606 2025-02-04 cs.AI cs.CV 84%

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaojian Ma, Tao Yuan, Yue Fan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li

专题命中视觉推理：VLM(title,abstract)；vision-language model(abstract)；分类 cs.CV、cs.AI

Comments ICLR 2025, https://mat-agent.github.io/

2412.13187 2024-12-19 cs.CV cs.LG 84%

HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction

Chen Bao, Jiarui Xu, Xiaolong Wang, Abhinav Gupta, Homanga Bharadhwaj

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.LG

Comments Preprint. Under Review

2409.18938 2024-12-04 cs.CV cs.AI 84%

From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding

Heqing Zou, Tianze Luo, Guiyang Xie, Victor, Zhang, Fengmao Lv, Guangcong Wang, Junyang Chen, Zhuochen Wang, Hansheng Zhang, Huaijian Zhang

专题命中视觉推理：multimodal large language model(title,abstract)；visual reasoning(abstract)；分类 cs.CV、cs.AI

Comments 11 pages

2411.15201 2024-11-26 cs.CV cs.AI 84%

Beyond Visual Understanding: Introducing PARROT-360V for Vision Language Model Benchmarking

Harsha Vardhan Khurdula, Basem Rizk, Indus Khaitan, Janit Anjaria, Aviral Srivastava, Rajvardhan Khaitan

专题命中视觉推理：vision language model(title,abstract)；visual reasoning(abstract)；分类 cs.CV、cs.AI

Comments 7 pages, 4 figures, Accepted at COLING 2025

2406.11548 2024-11-19 cs.RO cs.AI cs.CV 84%

AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation

Chuyan Xiong, Chengyu Shen, Xiaoqi Li, Kaichen Zhou, Jeremy Liu, Ruiping Wang, Hao Dong

专题命中视觉推理：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

2410.16198 2024-10-22 cs.AI cs.CV 84%

Improve Vision Language Model Chain-of-thought Reasoning

Ruohong Zhang, Bowen Zhang, Yanghao Li, Haotian Zhang, Zhiqing Sun, Zhe Gan, Yinfei Yang, Ruoming Pang, Yiming Yang

专题命中视觉推理：vision language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.AI

Comments 10 pages + appendix

2410.03551 2024-10-07 cs.CV cs.AI cs.HC 84%

Constructive Apraxia: An Unexpected Limit of Instructible Vision-Language Models and Analog for Human Cognitive Disorders

David Noever, Samantha E. Miller Noever

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.AI

2407.21439 2024-09-26 cs.AI cs.CL cs.LG 84%

MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training

Zhanpeng Chen, Chengjin Xu, Yiyan Qi, Jian Guo

专题命中视觉推理：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.AI、cs.LG

2408.15769 2024-08-29 cs.CV cs.AI cs.CL 84%

A Survey on Evaluation of Multimodal Large Language Models

Jiaxing Huang, Jingyi Zhang

专题命中视觉推理：multimodal large language model(title,abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

2308.03729 2024-08-13 cs.CV cs.AI 84%

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models

Wenqi Shao, Meng Lei, Yutao Hu, Peng Gao, Kaipeng Zhang, Fanqing Meng, Peng Xu, Siyuan Huang, Hongsheng Li, Yu Qiao, Ping Luo

专题命中视觉推理：vision-language model(title,abstract)；visual reasoning(abstract)；分类 cs.CV、cs.AI

Comments accepted to IEEE Transactions on Big Data. Project Page: http://lvlm-ehub.opengvlab.com/

2404.07922 2024-07-17 cs.CL cs.CV cs.LG 84%

LaVy: Vietnamese Multimodal Large Language Model

Chi Tran, Huong Le Thanh

专题命中视觉推理：multimodal large language model(title,abstract)；MLLM(abstract)；分类 cs.CV、cs.LG

Comments 5 pages

2406.11069 2024-06-18 cs.CV cs.AI cs.CL 84%

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

Yujie Lu, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, Bill Yuchen Lin

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV、cs.AI

Comments link: https://hf.co/spaces/WildVision/vision-arena

2309.04461 2024-03-21 cs.CL cs.CV cs.LG 84%

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models

Yangyi Chen, Karan Sikka, Michael Cogswell, Heng Ji, Ajay Divakaran

专题命中视觉推理：vision-language model(title,abstract)；visual reasoning(abstract)；分类 cs.CV、cs.LG

Comments NAACL 2024 Main Conference. The data is released at https://github.com/Yangyi-Chen/CoTConsistency

2310.12921 2024-03-15 cs.LG cs.AI 84%

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

Juan Rocamonde, Victoriano Montesinos, Elvis Nava, Ethan Perez, David Lindner

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.AI、cs.LG

Comments Presented at International Conference on Learning Representations (ICLR) 2024

2308.09778 2024-03-07 cs.CV cs.CL cs.LG 84%

Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models

Navid Rajabi, Jana Kosecka

专题命中视觉推理：vision language model(title)；visual question answering(abstract)；grounding(abstract)；分类 cs.CV、cs.LG

Comments Accepted to DMLR @ ICLR 2024

2312.17661 2024-01-01 cs.CL cs.AI cs.CV 84%

Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models

Yuqing Wang, Yun Zhao

专题命中视觉推理：multimodal large language model(title,abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

Comments Data and results are available at: https://github.com/EternityYW/Gemini-Commonsense-Evaluation/

2212.10292 2022-12-21 cs.CV cs.AI 84%

Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?

Monika Wysoczańska, Tom Monnier, Tomasz Trzciński, David Picard

专题命中视觉推理：visual reasoning(title,abstract)；visual question answering(abstract)；分类 cs.CV、cs.AI

1. 视觉推理 4478 篇

ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant

Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models

Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning

NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving

AI Judges in Design: Statistical Perspectives on Achieving Human Expert Equivalence With Vision-Language Models

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models

Decoupling the components of geometric understanding in Vision Language Models

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

Visual Reasoning Evaluation of Grok, Deepseek Janus, Gemini, Qwen, Mistral, and ChatGPT

A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks

A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction

From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding

Beyond Visual Understanding: Introducing PARROT-360V for Vision Language Model Benchmarking

AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation

Improve Vision Language Model Chain-of-thought Reasoning

Constructive Apraxia: An Unexpected Limit of Instructible Vision-Language Models and Analog for Human Cognitive Disorders

MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training

A Survey on Evaluation of Multimodal Large Language Models

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models

LaVy: Vietnamese Multimodal Large Language Model

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models

Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models

Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?