Jiadi Su — accepted AI-conference papers

2026

Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight

Yi Yang, Xueqi Li, Yiyang Chen, Jin Song, Yihan Wang, Zipeng Xiao +4

CVPR 2026

Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict high-dimensional visual states can distribute model capacity and incur prohibitive training cost, while compressing visu

Cited by 0 Source ↗code ↗Scholar ↗

2024

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

Zhen Huang, Zengzhi Wang, Shijie Xia, Xuefeng Li, Haoyang Zou, Ruijie Xu +22

NeurIPS 2024poster

The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i.e., AI4Science) once exclus…

Cited by 18 Source ↗PDF ↗code ↗Scholar ↗