视觉大模型 / VLM

What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs

Zhihan Ren, Lijun He, Jiaxi Liang, Xinzhu Fu, Haixia Bi, Fan Li

机构 * Xi’an Jiaotong University（西安交通大学） 纠错

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

Point Cloud Quantization through Multimodal Prompting for 3D Understanding

Hongxuan Li, Wencheng Zhu, Huiying Xu, Xinzhong Zhu, Pengfei Zhu

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

Comments Accepted by AAAI 2026. 11 pages, 7 figures

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance

Duo Li, Zuhao Yang, Xiaoqin Zhang, Ling Shao, Shijian Lu

机构 * CCDS, NTU, Singapore（南洋理工大学新加坡分校） ； CCST, ZJUT, China（浙江工业大学计算机科学与技术学院） ； Terminus AI Lab, UCAS, China（中国科学院大学人工智能实验室） 纠错

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

Comments 19 pages, 6 figures

CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs

Jingyu Lei, Gaoang Wang, Der-Horng Lee

机构 * Zhejiang University（浙江大学） 纠错

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

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models

Xuyang Liu, Yiyu Wang, Junpeng Ma, Linfeng Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Sichuan University（四川大学） ； Fudan University（复旦大学） 纠错

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

Comments EMNLP 2025 main

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image

Ziang Cao, Fangzhou Hong, Zhaoxi Chen, Liang Pan, Ziwei Liu

机构 * S-Lab, Nanyang Technological University（南洋理工大学S实验室） ； Shanghai AI Lab（上海人工智能实验室） 纠错

专题命中 VLM训练与架构 ：VLM(abstract)；分类 cs.CV

Comments Project page: https://physx-anything.github.io/

CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding

Shrenik Patel, Daivik Patel

机构 * Rutgers University（罗切斯特大学） 纠错

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

CreBench: Human-Aligned Creativity Evaluation from Idea to Process to Product

Kaiwen Xue, Chenglong Li, Zhonghong Ou, Guoxin Zhang, Kaoyan Lu, Shuai Lyu, Yifan Zhu, Ping Zong Junpeng Ding, Xinyu Liu, Qunlin Chen, Weiwei Qin, Yiran Shen, Jiayi Cen

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

Comments 13 pages, 3 figures,The 40th Annual AAAI Conference on Artificial Intelligence(AAAI 2026),Paper has been accepted for a poster presentation

Medical Knowledge Intervention Prompt Tuning for Medical Image Classification

Ye Du, Nanxi Yu, Shujun Wang

机构 * The Hong Kong Polytechnic University（香港理工大学） 纠错

专题命中 VLM训练与架构 ：VLM(abstract)；分类 cs.CV

Comments IEEE Transactions on Medical Imaging (Early Access) July 2025

DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions

Xiaoyu Lin, Aniket Ghorpade, Hansheng Zhu, Justin Qiu, Dea Rrozhani, Monica Lama, Mick Yang, Zixuan Bian, Ruohan Ren, Alan B. Hong, Jiatao Gu, Chris Callison-Burch

机构 * University of Pennsylvania（宾夕法尼亚大学） 纠错

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

BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages

Guduru Manoj, Neel Prabhanjan Rachamalla, Ashish Kulkarni, Gautam Rajeev, Jay Piplodiya, Arul Menezes, Shaharukh Khan, Souvik Rana, Manya Sah, Chandra Khatri, Shubham Agarwal

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

SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs

Haiduo Huang, Jiangcheng Song, Yadong Zhang, Pengju Ren

机构 * Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院） 纠错

专题命中 VLM训练与架构 ：VLM(abstract)；分类 cs.AI

Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translation

Julian Spravil, Sebastian Houben, Sven Behnke

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

Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models

Tianfan Peng, Yuntao Du, Pengzhou Ji, Shijie Dong, Kailin Jiang, Mingchuan Ma, Yijun Tian, Jinhe Bi, Qian Li, Wei Du, Feng Xiao, Lizhen Cui

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

APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval

Hong Gao, Yiming Bao, Xuezhen Tu, Bin Zhong, Linan Yue, Minling Zhang

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

Comments Accepted by AAAI 2026

Discovering Meaningful Units with Visually Grounded Semantics from Image Captions

Melika Behjati, James Henderson

机构 * Idiap Research Institute（日内瓦研究所） 纠错

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

Frequency-Aware Vision-Language Multimodality Generalization Network for Remote Sensing Image Classification

Junjie Zhang, Feng Zhao, Hanqiang Liu, Jun Yu

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

HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment

Ruijia Wu, Ping Chen, Fei Shen, Shaoan Zhao, Qiang Hui, Huanlin Gao, Ting Lu, Zhaoxiang Liu, Fang Zhao, Kai Wang, Shiguo Lian

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

Comments Accepted by AAAI 2026 as an Oral Presentation (13 pages, 7 figures, 7 tables)

Journal ref AAAI2026

Bridging the gap to real-world language-grounded visual concept learning

Whie Jung, Semin Kim, Junee Kim, Seunghoon Hong

机构 * School of Computing, KAIST（计算机学院，韩国科学技术院） 纠错

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

Journal ref Advances in Neural Information Processing Systems (NeurIPS), 2025

MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition

Shu Zhao, Nilesh Ahuja, Tan Yu, Tianyi Shen, Vijaykrishnan Narayanan

机构 * The Pennsylvania State University（宾夕法尼亚州立大学） ； Intel（英特尔） ； NVIDIA（英伟达） 纠错

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

X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning

Jian Ma, Xujie Zhu, Zihao Pan, Qirong Peng, Xu Guo, Chen Chen, Haonan Lu

机构 * OPPO AI Center（OPPO人工智能中心） 纠错

专题命中 VLM训练与架构 ：VLM(abstract)；分类 cs.CV

Comments Accepted to AAAI 2026

Revealing emergent human-like conceptual representations from language prediction

Ningyu Xu, Qi Zhang, Chao Du, Qiang Luo, Xipeng Qiu, Xuanjing Huang, Menghan Zhang

机构 * College of Computer Science and Artificial Intelligence（计算机科学与人工智能学院） ； Fudan University（复旦大学） ； Institute of Modern Languages and Linguistics（现代语言与语言学研究所） ； Shanghai Key Laboratory of Intelligent Information Processing（上海智能信息处理重点实验室） ； Research Institute of Intelligent Complex Systems（智能复杂系统研究所） ； Institute of Trustworthy Embodied Artificial Intelligence（可信具身人工智能研究所） ； State Key Laboratory of Genetics and Development of Complex Phenotypes（复杂表型遗传与发育国家重点实验室） 纠错

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

Comments 66 pages. Accepted manuscript. Final version published in Proceedings of the National Academy of Sciences (PNAS): https://www.pnas.org/doi/10.1073/pnas.2512514122

Journal ref Proceedings of the National Academy of Sciences, U.S.A., 122 (44) e2512514122 (2025)

Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval

Janet Jenq, Hongda Shen

机构 * PitchBook USA（PitchBook美国公司） 纠错

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

Role-SynthCLIP: A Role Play Driven Diverse Synthetic Data Approach

Yuanxiang Huangfu, Chaochao Wang, Weilei Wang

机构 * PatSnap Co., LTD.（PatSnap公司） 纠错

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

PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning

Yicheng Xiao, Yu Chen, Haoxuan Ma, Jiale Hong, Caorui Li, Lingxiang Wu, Haiyun Guo, Jinqiao Wang

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

DashCLIP: Leveraging multimodal models for generating semantic embeddings for DoorDash

Omkar Gurjar, Kin Sum Liu, Praveen Kolli, Utsaw Kumar, Mandar Rahurkar

机构 * DoorDash, Inc.（DoorDash公司） 纠错

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

Text to Sketch Generation with Multi-Styles

Tengjie Li, Shikui Tu, Lei Xu

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳）） 纠错

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

Comments Accepted by NeurIPS 2025

SCALE-VLP: Soft-Weighted Contrastive Volumetric Vision-Language Pre-training with Spatial-Knowledge Semantics

Ailar Mahdizadeh, Puria Azadi Moghadam, Xiangteng He, Shahriar Mirabbasi, Panos Nasiopoulos, Leonid Sigal

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Vector Institute for AI（人工智能向量研究所） 纠错

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

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit

Valérie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams, Demba Ba

机构 * EPFL（瑞士联邦理工学院） ； Kempner Institute, Harvard University（哈佛大学凯普纳研究所） ； CBS-NTT Program in Physics of Intelligence, Harvard University（哈佛大学物理智能CBSTNTT项目） ； Physics of Artificial Intelligence Group, NTT Research, Inc., Sunnyvale, CA, USA（NTT研究公司人工智能物理研究组） ； University of Alberta（阿尔伯塔大学） ； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔人工智能研究所） ； SEAS, Harvard University（哈佛大学工程与应用科学学院） 纠错

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

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Automated Reward Design for Gran Turismo

Michel Ma, Takuma Seno, Kaushik Subramanian, Peter R. Wurman, Peter Stone, Craig Sherstan

机构 * Mila, University of Montreal（蒙特利尔大学Mila） ； Turing Inc.（图灵公司） ； Sony AI（索尼人工智能） ； Sony AI, UT Austin（索尼人工智能、得克萨斯大学奥斯汀分校） 纠错

专题命中 VLM训练与架构 ：VLM(abstract)；分类 cs.AI