视觉大模型 / VLM

ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judges

Yue Zhou, Yi Chang, Yuan Wu

专题命中 幻觉与鲁棒性 ：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.AI

HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents

Yibin Liu, Zhixuan Liang, Zanxin Chen, Tianxing Chen, Mengkang Hu, Wanxi Dong, Congsheng Xu, Zhaoming Han, Yusen Qin, Yao Mu

专题命中 幻觉与鲁棒性 ：vision-language model(abstract)；VLM(abstract)；grounding(abstract)；multimodal large language model(abstract)

Comments Accepted to ICCV 2025 Workshop on Multi-Modal Reasoning for Agentic Intelligence

Analyzing and Mitigating Object Hallucination: A Training Bias Perspective

Yifan Li, Kun Zhou, Wayne Xin Zhao, Lei Fang, Ji-Rong Wen

专题命中 幻觉与鲁棒性 ：vision-language model(abstract)；分类 cs.CV

Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks

Yurun Chen, Xavier Hu, Keting Yin, Juncheng Li, Shengyu Zhang

机构 * School of Software Technology Zhejiang University Hangzhou Zhejiang China（软件技术学院浙江大学杭州浙江中国） ； Zhejiang University（浙江大学） 纠错

专题命中 幻觉与鲁棒性 ：MLLM(abstract)

Comments Accepted at ACM MM 2025 Main Conference

AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity

Zhibin Lan, Liqiang Niu, Fandong Meng, Wenbo Li, Jie Zhou, Jinsong Su

机构 * School of Informatics, Xiamen University, China（厦门大学信息学院） ； Pattern Recognition Center, WeChat AI, Tencent Inc, China（腾讯人工智能研究院） ； Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室） ； Shanghai Artificial Intelligence Laboratory, China（上海人工智能实验室） 纠错

专题命中 VLM训练与架构 ：LLaVA(title,abstract)；分类 cs.CV、cs.AI

Comments Accepted by ACL 2025 Findings

Can Sound Replace Vision in LLaVA With Token Substitution?

Ali Vosoughi, Jing Bi, Pinxin Liu, Yunlong Tang, Chenliang Xu

专题命中 VLM训练与架构 ：LLaVA(title)；vision-language model(abstract)

Comments Project page: https://ali-vosoughi.github.io/SoundCLIP/

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay

Jun Zhang, Desen Meng, Zhengming Zhang, Zhenpeng Huang, Tao Wu, Limin Wang

机构 * State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室） ； China Mobile Research Institute（中国移动研究院） ； Shanghai AI Lab（上海AI实验室） 纠错

专题命中 VLM训练与架构 ：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025; Code released at https://github.com/MCG-NJU/p-MoD

True Multimodal In-Context Learning Needs Attention to the Visual Context

Shuo Chen, Jianzhe Liu, Zhen Han, Yan Xia, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu

机构 * LMU Munich（慕尼黑大学） ； Technical University of Munich（慕尼黑技术大学） ； Siemens AG（西门子股份公司） ； University of Science and Technology of China（中国科学技术大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； Konrad Zuse School of Excellence in Reliable AI (relAI)（Konrad Zuse可靠性人工智能卓越学院） ； University of Oxford（牛津大学） 纠错

专题命中 VLM训练与架构 ：multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments Accepted to COLM 2025

RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case

Baihui Xiao, Chengjian Feng, Zhijian Huang, Feng yan, Yujie Zhong, Lin Ma

机构 * Meituan（美团） ； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区） 纠错

专题命中 VLM训练与架构 ：multimodal large language model(abstract)；分类 cs.CV

Comments ICCV 2025

Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation

Claudio Pomo, Matteo Attimonelli, Danilo Danese, Fedelucio Narducci, Tommaso Di Noia

机构 * Sapienza University of Rome（罗马大学） 纠错

专题命中 VLM训练与架构 ：vision-language model(abstract)；分类 cs.LG

Comments Accepted as Full Research Papers at CIKM 2025

FrEVL: Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding

Emmanuelle Bourigault, Pauline Bourigault

机构 * Department of Engineering Science, University of Oxford（牛津大学工程科学系） ； Department of Electrical Engineering, Imperial College London（伦敦帝国学院电子工程系） 纠错

专题命中 VLM训练与架构 ：vision-language model(abstract)；分类 cs.CV

Comments 8 pages, 4 figures

Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment

Lubin Gan, Jing Zhang, Linhao Qu, Yijun Wang, Siying Wu, Xiaoyan Sun

机构 * University of Science and Technology of China（科学技术大学） ； Fudan University（复旦大学） 纠错

专题命中 VLM训练与架构 ：vision-language model(abstract)；分类 cs.CV

From Learning to Unlearning: Biomedical Security Protection in Multimodal Large Language Models

Dunyuan Xu, Xikai Yang, Yaoqian Li, Jinpeng Li, Pheng-Ann Heng

专题命中 其他VLM ：multimodal large language model(title,abstract)；分类 cs.CV

Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval

Yifan Wang, Tao Wang, Chenwei Tang, Caiyang Yu, Zhengqing Zang, Mengmi Zhang, Shudong Huang, Jiancheng Lv

机构 * College of Computer Science, Sichuan University（四川大学计算机学院） ； Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Chengdu, China（教育部机器学习与产业智能工程研究中心） ； Deep NeuroCognition Lab, I2R and CFAR, Agency for Science, Technology and Research, Singapore（深度神经认知实验室，I2R和CFAR，科技研究局，新加坡） 纠错

专题命中 其他VLM ：vision-language model(title,abstract)；分类 cs.CV

Comments 10 pages, 7figures

CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP

Zhenchen Tang, Zichuan Wang, Bo Peng, Jing Dong

机构 * New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（模式识别新实验室，自动化研究所，中国科学院） 纠错

专题命中 其他VLM ：visual language model(abstract)；分类 cs.CV

Comments accepted by ICPR2024