arxiv:2607.12800
Xiangtai Li
LXT
AI & ML interests
Computer Vision, Multi-Modal Understanding, Generative AI
Recent Activity
upvoted a paper about 2 hours ago
VideoMemBench: How Well Do MLLMs Remember in Video Conversations? upvoted a paper 22 days ago
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal EvidenceOrganizations
arxiv:2603.08403
arxiv:2602.01842
arxiv:2601.16093
arxiv:2512.16760
arxiv:2512.13421
arxiv:2512.11715
arxiv:2512.10958
arxiv:2511.09611
arxiv:2511.05491
arxiv:2510.26802
arxiv:2510.25682
arxiv:2510.20668
arxiv:2510.20579
arxiv:2510.18876
arxiv:2510.11712
arxiv:2510.11063
arxiv:2509.16972
arxiv:2509.04444
arxiv:2508.12081
arxiv:2507.07999
arxiv:2506.24102
arxiv:2506.13691
arxiv:2506.07971
arxiv:2506.03144
arxiv:2505.24164
arxiv:2505.23727
arxiv:2505.23606
arxiv:2505.21541
arxiv:2505.18660
arxiv:2505.16862
arxiv:2505.12620
arxiv:2505.04620
arxiv:2504.14906
arxiv:2504.12080
arxiv:2504.11326
arxiv:2504.10465
arxiv:2504.10462
arxiv:2504.05979
arxiv:2503.17350
arxiv:2502.13071
arxiv:2501.04670
arxiv:2501.04001
arxiv:2412.07589
arxiv:2412.06674
arxiv:2412.04292
arxiv:2412.04280
arxiv:2412.03255
arxiv:2410.23280
arxiv:2410.10676
arxiv:2410.08261
arxiv:2410.04733
arxiv:2409.15179
arxiv:2407.19409
arxiv:2406.20085
arxiv:2406.19389
arxiv:2406.19369
arxiv:2406.17770
arxiv:2406.17758
arxiv:2406.05127
arxiv:2405.20282
arxiv:2405.12970
arxiv:2404.06564
arxiv:2312.07526
arxiv:2404.00086
arxiv:2403.12003
arxiv:2403.00762
arxiv:2402.02555
arxiv:2401.10229
arxiv:2401.10228
arxiv:2401.10226
arxiv:2401.02955
arxiv:2401.02361
arxiv:2312.06660
arxiv:2311.17058
arxiv:2310.14374
arxiv:2310.01403
arxiv:2309.13042
arxiv:2306.15880
arxiv:2301.01146
arxiv:2301.00805
arxiv:2204.04654
arxiv:2103.06255
