Trials, Errors, and Breakthroughs: Our Rocky Road to OVD SOTA with Reinforcement Learning
• 2
AI & ML interests
Multimodal AI, VLM, VLA, VAM, etc
Recent 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
Organization Card
Om AI Lab is a passionate group building multimodal AI agents that reshape our work and life.
spaces 5
pinned
Running
Agents
17
Open Agent Leaderboard
🥇
Open Agent Leaderboard
Runtime error
Agents
72
VLM R1 Referral Expression
💬
Mark regions in images based on text descriptions
Sleeping
Agents
1
OmAgent
💬
Process and answer questions about webpage videos
Runtime error
Agents
19
VLM R1 OVD
👁
VLM-R1 model for Open-Vocabulary Object Detection
models 9
omlab/OmTrackVLA-0.6B
Other • 0.6B • Updated • 129 • 4
omlab/VLM-FO1-3B-v01
Object Detection • 4B • Updated • 263 • 16
omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321
Image-Text-to-Text • 4B • Updated • 133 • 24
omlab/ImageRAG
Updated • 1
omlab/VLM-R1-Qwen2.5VL-3B-Math-0305
Visual Question Answering • 4B • Updated • 29 • 8
omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps
Zero-Shot Object Detection • 4B • Updated • 56 • 25
omlab/omdet-turbo-swin-tiny-hf
Zero-Shot Object Detection • 0.1B • Updated • 11.5k • 41
omlab/omchat-v2.0-13B-single-beta_hf
13B • Updated • 8 • 5
omlab/OmDet-Turbo_tiny_SWIN_T
Zero-Shot Object Detection • Updated • 8
datasets 12
omlab/SARDet_REC6_NORM-FS
Viewer • Updated • 968 • 16
omlab/SARDet_REC6-FS
Viewer • Updated • 968 • 7
omlab/SARDet3-FS
Viewer • Updated • 270 • 11
omlab/Cross_DIOR-RSVG
Viewer • Updated • 7.42k • 69
omlab/Cross_RRSIS-D
Viewer • Updated • 3.48k • 15
omlab/VRSBench-FS
Viewer • Updated • 16.6k • 116 • 1
omlab/NWPU-FS
Viewer • Updated • 39 • 7
omlab/EarthReason-FS
Viewer • Updated • 3.39k • 18
omlab/VLM-R1
Preview • Updated • 326 • 18
omlab/RS5M
Viewer • Updated • 7.25M • 207 • 1