arxiv:2607.21556
William Li PRO
williamium
AI & ML interests
Learning AI efficiently and robustly in interactive, multi-modal and embodied environment.
Recent Activity
authored a paper about 12 hours ago
Visual Contrastive Self-Distillation authored a paper about 12 hours ago
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models authored a paper about 12 hours ago
SPACENUM: Revisiting Spatial Numerical Understanding in VLMsOrganizations
arxiv:2607.06553
arxiv:2605.04733
arxiv:2605.23898
arxiv:2605.09725
arxiv:2605.07825
arxiv:2604.11201
arxiv:2603.22281
arxiv:2603.20169
arxiv:2603.07109
arxiv:2602.20159
arxiv:2602.12670
arxiv:2602.10388
arxiv:2602.07274
arxiv:2601.13029
arxiv:2510.08529
arxiv:2509.02547
arxiv:2508.15126
arxiv:2507.21035
arxiv:2506.23639
arxiv:2506.12258
arxiv:2506.05412
arxiv:2411.16156
arxiv:2410.10855
arxiv:2410.03122
arxiv:2410.02155
arxiv:2410.00324
arxiv:2403.10476
arxiv:2403.10045
arxiv:2403.05523
arxiv:2402.12391
arxiv:2311.18531
arxiv:2308.09281
arxiv:2303.06601
arxiv:2209.01589
arxiv:2106.10637
