视觉大模型 / VLM

FinCap: Topic-Aligned Captions for Short-Form Financial YouTube Videos

Siddhant Sukhani, Yash Bhardwaj, Riya Bhadani, Veer Kejriwal, Michael Galarnyk, Sudheer Chava

机构 * Stanford University（斯坦福大学） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

专题命中 视觉定位与Grounding ：grounding(abstract)；multimodal large language model(abstract)；分类 cs.CV

Comments ICCV Short Video Understanding Workshop Paper

MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling

Yifan Cheng, Ruoyi Zhang, Jiatong Shi

机构 * Santa Clara, CA, USA（美国圣克拉拉） ； Carnegie Mellon University（卡内基梅隆大学） ； Huazhong University of Science and Technology（华中科技大学） ； Nanjing University of Information Science and Technology（南京信息工程大学） 纠错

专题命中 视觉定位与Grounding ：multimodal large language model(abstract)；MLLM(abstract)

Comments Accepted by Interspeech

Journal ref Proc. of Interspeech2025

Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation

Yogesh Verma, Markus Heinonen, Vikas Garg

机构 * Aalto University（阿alto大学） 纠错

专题命中 视觉定位与Grounding ：grounding(abstract)；分类 cs.AI、cs.LG

TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos

Ioannis Kontostathis, Evlampios Apostolidis, Vasileios Mezaris

机构 * IEEE CBMI 2025 纠错

专题命中 视觉定位与Grounding ：vision-language model(abstract)；分类 cs.CV

Comments IEEE CBMI 2025. This is the authors' accepted version. The final publication is available at https://ieeexplore.ieee.org/

DGM4+: Dataset Extension for Global Scene Inconsistency

Gagandeep Singh, Samudi Amarsinghe, Priyanka Singh, Xue Li

专题命中 视觉定位与Grounding ：grounding(abstract)；分类 cs.CV

Comments 8 pages, 3 figures

Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation

Longzhen Yang, Zhangkai Ni, Ying Wen, Yihang Liu, Lianghua He, Heng Tao Shen

机构 * Tongji University（同济大学） ； East China Normal University（华东师范大学） ； Shanghai Eye Disease Prevention and Treatment Center（上海眼病防治中心） 纠错

专题命中 视觉定位与Grounding ：grounding(abstract)；分类 cs.CV

Where LLM Agents Fail and How They can Learn From Failures

Kunlun Zhu, Zijia Liu, Bingxuan Li, Muxin Tian, Yingxuan Yang, Jiaxun Zhang, Pengrui Han, Qipeng Xie, Fuyang Cui, Weijia Zhang, Xiaoteng Ma, Xiaodong Yu, Gowtham Ramesh, Jialian Wu, Zicheng Liu, Pan Lu, James Zou, Jiaxuan You

专题命中 视觉定位与Grounding ：grounding(abstract)；分类 cs.AI

How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads

Ingeol Baek, Hwan Chang, Sunghyun Ryu, Hwanhee Lee

专题命中 文档图表理解 ：vision-language model(title)；vision language model(abstract)；分类 cs.CV

Comments EMNLP 2025 Oral

UI-UG: A Unified MLLM for UI Understanding and Generation

Hao Yang, Weijie Qiu, Ru Zhang, Zhou Fang, Ruichao Mao, Xiaoyu Lin, Maji Huang, Zhaosong Huang, Teng Guo, Shuoyang Liu, Hai Rao

专题命中 GUI与屏幕智能体 ：MLLM(title,abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

Zhen Yang, Zi-Yi Dou, Di Feng, Forrest Huang, Anh Nguyen, Keen You, Omar Attia, Yuhao Yang, Michael Feng, Haotian Zhang, Ram Ramrakhya, Chao Jia, Jeffrey Nichols, Alexander Toshev, Yinfei Yang, Zhe Gan

机构 * Apple（苹果公司） 纠错

专题命中 GUI与屏幕智能体 ：grounding(abstract)；分类 cs.CV、cs.LG

WorldGym: World Model as An Environment for Policy Evaluation

Julian Quevedo, Ansh Kumar Sharma, Yixiang Sun, Varad Suryavanshi, Percy Liang, Sherry Yang

机构 * Stanford University（斯坦福大学） ； NYU（纽约大学） ； Google DeepMind（谷歌DeepMind） 纠错

专题命中 GUI与屏幕智能体 ：vision-language model(abstract)；分类 cs.AI

Comments https://world-model-eval.github.io

UAV-VLN: End-to-End Vision Language guided Navigation for UAVs

Pranav Saxena, Nishant Raghuvanshi, Neena Goveas

机构 * Birla Institute of Technology and Science Pilani, K.K Birla Goa Campus（比拉理工学院和科学学院，K.K比拉果阿校区） 纠错

专题命中 GUI与屏幕智能体 ：grounding(abstract)；分类 cs.CV

Journal ref Proc. European Conference on Mobile Robots (ECMR), 2025, pp. 1-6

AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding

Chaeyoung Jung, Youngjoon Jang, Joon Son Chung

机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院） 纠错

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

Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation

Jianjiang Yang, Ziyan Huang, Yanshu li, Da Peng, Huaiyuan Yao

机构 * University of Bristol（布里斯托大学） ； South China University of Technology（华南理工大学） ； Brown University（布朗大学） ； Xi’an Jiaotong University（西安交通大学） ； Arizona State University（亚利桑那州立大学） 纠错

专题命中 幻觉与鲁棒性 ：grounding(abstract)；分类 cs.CV

Comments 9 pages,6 figures,7 tables

LFTR: Learning-Free Token Reduction for Multimodal Large Language Models

Zihui Zhao, Yingxin Li, Yang Li

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

Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization

Seongjae Kang, Dong Bok Lee, Hyungjoon Jang, Sung Ju Hwang

机构 * VUNO Inc.（VUNO公司） ； KAIST（韩国科学技术院） 纠错

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

Comments 38 pages, 17 figures, preprint

Probing the Limits of Stylistic Alignment in Vision-Language Models

Asma Farajidizaji, Akash Gupta, Vatsal Raina

机构 * Imperial College London（伦敦帝国学院） ； Apta AI 纠错

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

Comments 5 pages, 1 figure, 3 tables

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing

Yuxin Song, Wenkai Dong, Shizun Wang, Qi Zhang, Song Xue, Tao Yuan, Hu Yang, Haocheng Feng, Hang Zhou, Xinyan Xiao, Jingdong Wang

机构 * Baidu VIS（百度视觉） ； National University of Singapore（新加坡国立大学） 纠错

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

Comments 23 pages, 10 figures

Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking

Dengming Zhang, Xiaowen Ma, Zhenliang Ni, Zhenkai Wu, Han Shu, Xin Jiang, Xinghao Chen

机构 * Zhejiang University（浙江大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

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

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training

Junlin Han, Shengbang Tong, David Fan, Yufan Ren, Koustuv Sinha, Philip Torr, Filippos Kokkinos

机构 * Meta Superintelligence Labs（Meta 超智能实验室） ； University of Oxford（牛津大学） 纠错

专题命中 VLM训练与架构 ：visual reasoning(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Project page: https://junlinhan.github.io/projects/lsbs/

MMPB: It's Time for Multi-Modal Personalization

Jaeik Kim, Woojin Kim, Woohyeon Park, Jaeyoung Do

机构 * AIDAS Laboratory（AIDAS实验室） ； IPAI ； ECE（电子工程系） ； Seoul National University（首尔国立大学） 纠错

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

Comments Accepted in NeurIPS 2025

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

Jiayi Guo, Chuanhao Yan, Xingqian Xu, Yulin Wang, Kai Wang, Gao Huang, Humphrey Shi

机构 * Tsinghua University（清华大学） 纠错

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

Comments ICCV 2025

Zero-Shot Decentralized Federated Learning

Alessio Masano, Matteo Pennisi, Federica Proietto Salanitri, Concetto Spampinato, Giovanni Bellitto

机构 * University of Catania（卡塔尼亚大学） ； PeRCeiVe Lab, University of Catania（PeRCeiVe实验室，卡塔尼亚大学） 纠错

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

Comments Accepted at International Joint Conference on Neural Networks (IJCNN) 2025. Code available at https://github.com/perceivelab/ZeroDFL

An Experimental Study on Generating Plausible Textual Explanations for Video Summarization

Thomas Eleftheriadis, Evlampios Apostolidis, Vasileios Mezaris

机构 * IEEE CBMI 2025 纠错

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

Comments IEEE CBMI 2025. This is the authors' accepted version. The final publication is available at https://ieeexplore.ieee.org/

Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization

Xintong Li, Chuhan Wang, Junda Wu, Rohan Surana, Tong Yu, Julian McAuley, Jingbo Shang

机构 * University of California, San Diego（加州大学圣迭戈分校） ； Adobe Research（Adobe研究） 纠错

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

Comments Preprint

UniVid: The Open-Source Unified Video Model

Jiabin Luo, Junhui Lin, Zeyu Zhang, Biao Wu, Meng Fang, Ling Chen, Hao Tang

机构 * Peking University（北京大学） ； AI Geeks ； Australian Artificial Intelligence Institute（澳大利亚人工智能研究所） 纠错

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

Optimizing Speech Language Models for Acoustic Consistency

Morteza Rohanian, Michael Krauthammer

专题命中 VLM训练与架构 ：grounding(abstract)

MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs

Feilong Chen, Yijiang Liu, Yi Huang, Hao Wang, Miren Tian, Ya-Qi Yu, Minghui Liao, Jihao Wu

机构 * Huawei Technologies Co., Ltd.（华为技术有限公司） 纠错

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

90% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Development

Runxin Yang, Yuxuan Wan, Shuqing Li, Michael R. Lyu

机构 * The Chinese University of Hong Kong（香港中文大学） 纠错

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

VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions

Kazuki Matsuda, Yuiga Wada, Shinnosuke Hirano, Seitaro Otsuki, Komei Sugiura

机构 * Keio University（庆应大学） 纠错

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

Comments EMNLP 2025 Main Conference