Minxin Dai — accepted AI-conference papers

2026

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

Caorui Li, Yu Chen, Yiyan Ji, Jin Xu, Zhenyu Cui, Shihao Li +36

ICLR 2026poster

Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modaliti…

Cited by 0 Source ↗code ↗Scholar ↗

2026

UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing

Yunkai Dang, Minxin Dai, Yuekun Yang, Zhangnanli, Wenbin Li, Feng Miao +1

ICML 2026poster

Ultra-high-resolution (UHR) remote sensing imagery couples kilometer-scale context with query-critical evidence that may occupy only a few pixels. Such vast spatial scale leads to a quadratic explosion of visual tokens and hinders the extraction of information from small objects. Previous works util…

Cited by 0 Source ↗Scholar ↗