Maijunxian Wang — accepted AI-conference papers

2026

A Very Big Video Reasoning Suite

Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer, Qingying Gao +49

ICML 2026poster

Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over motion, interaction, and causality. Rapid progress in video models has focused primarily on visual quality. Systematically studyin…

Cited by 18 Source ↗Scholar ↗

2026

Vision Language Models Cannot Reason About Physical Transformation

Dezhi Luo, Yijiang Li, Maijunxian Wang, Tianwei Zhao, Bingyang Wang, siheng wang +4

ICML 2026poster

Understanding physical transformations is fundamental for reasoning in dynamic environments. While Vision Language Models (VLMs) show promise in embodied applications, whether they genuinely understand physical transformations remains unclear. We introduce ***ConservationBench*** evaluating ***conse…

Cited by 0 Source ↗Scholar ↗