Trials, Errors, and Breakthroughs: Our Rocky Road to OVD SOTA with Reinforcement Learning
•
2
AI & ML interests
Multimodal AI, Agents
Recent Activity
Papers
View all Papers Articles
Organization Card
Om AI Lab is a passionate group building multimodal AI agents that reshape our work and life.
spaces 5
pinned
Running
17
Open Agent Leaderboard
🥇
Open Agent Leaderboard
Runtime error
72
VLM R1 Referral Expression
💬
Mark regions in images based on text descriptions
Sleeping
1
OmAgent
💬
Process and answer questions about webpage videos
Runtime error
19
VLM R1 OVD
👁
VLM-R1 model for Open-Vocabulary Object Detection
models 9
omlab/opentrackvla-qwen06b
Other • 0.6B • Updated • 180 • 3
omlab/VLM-FO1_Qwen2.5-VL-3B-v01
Object Detection • 4B • Updated • 226 • 13
omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321
Image-Text-to-Text • 4B • Updated • 287 • 24
omlab/ImageRAG
Updated • 1
omlab/VLM-R1-Qwen2.5VL-3B-Math-0305
Visual Question Answering • 4B • Updated • 21 • 8
omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps
Zero-Shot Object Detection • 4B • Updated • 60 • 23
omlab/omdet-turbo-swin-tiny-hf
Zero-Shot Object Detection • 0.1B • Updated • 8.02k • 40
omlab/omchat-v2.0-13B-single-beta_hf
13B • Updated • 18 • 5
omlab/OmDet-Turbo_tiny_SWIN_T
Zero-Shot Object Detection • Updated • 8
datasets 12
omlab/SARDet_REC6_NORM-FS
Viewer • Updated • 968 • 10
omlab/SARDet_REC6-FS
Viewer • Updated • 968 • 13
omlab/SARDet3-FS
Viewer • Updated • 270 • 10
omlab/Cross_DIOR-RSVG
Viewer • Updated • 7.42k • 31
omlab/Cross_RRSIS-D
Viewer • Updated • 3.48k • 10
omlab/VRSBench-FS
Viewer • Updated • 16.6k • 58 • 1
omlab/NWPU-FS
Viewer • Updated • 39 • 10
omlab/EarthReason-FS
Viewer • Updated • 3.39k • 30
omlab/VLM-R1
Preview • Updated • 355 • 18
omlab/RS5M
Viewer • Updated • 7.25M • 607 • 1