arxiv:2508.04700
Xiaoyi Dong
LightDong
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding authored a paper 10 months ago
Bootstrap3D: Improving 3D Content Creation with Synthetic Data authored a paper 10 months ago
ShareGPT4Video: Improving Video Understanding and Generation with Better
CaptionsOrganizations
None yet
arxiv:2508.00819
arxiv:2507.15852
arxiv:2506.19848
arxiv:2506.04997
arxiv:2502.13128
arxiv:2502.08590
arxiv:2502.05173
arxiv:2501.12368
arxiv:2501.05510
arxiv:2501.03226
arxiv:2501.03218
arxiv:2412.09596
arxiv:2412.01824
arxiv:2412.00131
arxiv:2410.17637
arxiv:2410.17247
arxiv:2410.16268
arxiv:2410.07167
arxiv:2410.06241
arxiv:2407.11691
arxiv:2407.03320
arxiv:2407.01523
arxiv:2406.11833
arxiv:2406.11739
arxiv:2406.05338
arxiv:2406.04325
arxiv:2406.00093
arxiv:2405.16009
arxiv:2404.16821
arxiv:2404.06512
arxiv:2403.20330
arxiv:2403.17297
arxiv:2403.15378
arxiv:2402.17645
arxiv:2402.14767
arxiv:2401.16420
arxiv:2311.17911
arxiv:2311.16839
arxiv:2311.12793
arxiv:2309.15112
arxiv:2308.13566
arxiv:2308.12714
arxiv:2308.10315
arxiv:2303.08138
arxiv:2212.06138
arxiv:2107.00652
