arxiv:2608.26105
Zhongang Cai
caizhongang
AI & ML interests
Multimodal, Video Reasoning, Spatial Intelligence, Virtual Humans.
Recent Activity
authored a paper 2 days ago
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning authored a paper 2 days ago
Apple-$π$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence authored a paper 2 days ago
From Pixels to Words -- Towards Native One-Vision Models at ScaleOrganizations
arxiv:2607.16401
arxiv:2607.06560
arxiv:2605.28820
arxiv:2605.12500
arxiv:2603.19227
arxiv:2603.16870
arxiv:2602.20159
arxiv:2511.18333
arxiv:2511.13719
arxiv:2510.26794
arxiv:2508.13142
arxiv:2508.00599
arxiv:2506.03119
arxiv:2503.03803
arxiv:2501.13335
arxiv:2501.09782
arxiv:2412.00174
arxiv:2409.17280
arxiv:2406.10163
arxiv:2404.01284
arxiv:2403.17934
arxiv:2403.12959
arxiv:2312.04547
arxiv:2311.14521
arxiv:2311.07446
arxiv:2309.17448
arxiv:2308.11473
arxiv:2307.10173
arxiv:2304.01116
arxiv:2303.17368
arxiv:2303.13796
arxiv:2301.11233
arxiv:2208.15001
arxiv:2204.13686
arxiv:2110.07588
