视觉大模型 / VLM

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

Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings

Abderrazek Abid, Thanh-Cong Ho, Fakhri Karray

机构 * MBZUAI ； University of Waterloo（滑铁卢大学） 纠错

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

Journal ref In: Rojas I., Ortuño F., Rojas Ruiz F., Herrera L.J., Valenzuela O., Escobar J.J. (eds) Bioinformatics and Biomedical Engineering. IWBBIO 2026. Lecture Notes in Bioinformatics, vol 15561. Springer, Cham

Multi-Agent Multimodal Large Language Model Framework for Automated Interpretation of Fuel Efficiency Analytics in Public Transportation

Zhipeng Ma, Ali Rida Bahja, Andreas Burgdorf, André Pomp, Tobias Meisen, Bo Nørregaard Jørgensen, Zheng Grace Ma

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

Journal ref Applied Sciences, 2025, 15(21), 11619

Prompt Triage: Structured Optimization Enhances Vision-Language Model Performance on Medical Imaging Benchmarks

Arnav Singhvi, Vasiliki Bikia, Asad Aali, Akshay Chaudhari, Roxana Daneshjou

机构 * Stanford University, Department of Computer Science, Stanford, CA, USA（斯坦福大学计算机科学系） ； Stanford University, Department of Biomedical Data Science, Stanford, CA, USA（斯坦福大学生物医学数据科学系） ； Stanford University, Stanford Institute for Human-Centered Artificial Intelligence, Stanford, CA, USA（斯坦福大学人类中心人工智能研究所） ； Stanford University, School of Medicine, Department of Dermatology, Stanford, CA, USA（斯坦福大学医学院皮肤科系） ； Stanford University, Department of Radiology, Stanford, CA, USA（斯坦福大学放射科） 纠错

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

Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms

Tyler Loakman, Joseph James, Chenghua Lin

机构 * Department of Computer Science, University of Sheffield, UK（谢菲尔德大学计算机科学系） ； Department of Computer Science, University of Manchester, UK（曼彻斯特大学计算机科学系） 纠错

专题命中 其他VLM ：vision language model(title)

Comments Accepted to IJCNLP-AACL 2025

Use as Many Surrogates as You Want: Selective Ensemble Attack to Unleash Transferability without Sacrificing Resource Efficiency

Bo Yang, Hengwei Zhang, Jindong Wang, Yuchen Ren, Chenhao Lin, Chao Shen, Zhengyu Zhao

机构 * Information Engineering University（信息工程大学） ； Xi’an Jiaotong University（西安交通大学） 纠错

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

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs

Shuhan Xu, Siyuan Liang, Hongling Zheng, Aishan Liu, Xinbiao Wang, Yong Luo, Fu Lin, Leszek Rutkowski, Dacheng Tao

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

Comments AAAI2026

SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images

Xinyuan Hu, Changyue Shi, Chuxiao Yang, Minghao Chen, Jiajun Ding, Tao Wei, Chen Wei, Zhou Yu, Min Tan

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

Comments AAAI2026-Oral. Project Page: https://xinyuanhu66.github.io/SRSplat/