Trials, Errors, and Breakthroughs: Our Rocky Road to OVD SOTA with Reinforcement Learning
• 2
AI & ML interests
Multimodal AI, Agents
Recent Activity
View all activity
Papers
Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models
VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs
Articles
omlab/SARDet_REC6_NORM-FS
Viewer • Updated • 968 • 16
omlab/SARDet_REC6-FS
Viewer • Updated • 968 • 6
omlab/SARDet3-FS
Viewer • Updated • 270 • 20
omlab/Cross_DIOR-RSVG
Viewer • Updated • 7.42k • 67
omlab/Cross_RRSIS-D
Viewer • Updated • 3.48k • 24
omlab/VRSBench-FS
Viewer • Updated • 16.6k • 295 • 1
omlab/NWPU-FS
Viewer • Updated • 39 • 33
omlab/EarthReason-FS
Viewer • Updated • 3.39k • 14
omlab/VLM-R1
Preview • Updated • 368 • 18
omlab/RS5M
Viewer • Updated • 7.25M • 2.6k • 1
omlab/zoom_eye_data
Viewer • Updated • 591 • 17
omlab/OVDEval
Updated • 214 • 3