Trials, Errors, and Breakthroughs: Our Rocky Road to OVD SOTA with Reinforcement Learning
β’
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
π₯
Open Agent Leaderboard
Runtime error
72
VLM R1 Referral Expression
π¬
Mark regions in images based on text descriptions
Sleeping
1
OmAgent
π¬
Process and answer questions about webpage videos
Runtime error
19
VLM R1 OVD
π
VLM-R1 model for Open-Vocabulary Object Detection
models
9
omlab/opentrackvla-qwen06b
Other
β’
0.6B
β’
Updated
β’
246
β’
2
omlab/VLM-FO1_Qwen2.5-VL-3B-v01
Object Detection
β’
4B
β’
Updated
β’
489
β’
13
omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321
Image-Text-to-Text
β’
4B
β’
Updated
β’
59
β’
24
omlab/ImageRAG
Updated
β’
1
omlab/VLM-R1-Qwen2.5VL-3B-Math-0305
Visual Question Answering
β’
4B
β’
Updated
β’
7
β’
8
omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps
Zero-Shot Object Detection
β’
4B
β’
Updated
β’
71
β’
23
omlab/omdet-turbo-swin-tiny-hf
Zero-Shot Object Detection
β’
0.1B
β’
Updated
β’
4.75k
β’
39
omlab/omchat-v2.0-13B-single-beta_hf
13B
β’
Updated
β’
14
β’
5
omlab/OmDet-Turbo_tiny_SWIN_T
Zero-Shot Object Detection
β’
Updated
β’
8
datasets
12
omlab/SARDet_REC6_NORM-FS
Viewer
β’
Updated
β’
968
β’
31
omlab/SARDet_REC6-FS
Viewer
β’
Updated
β’
968
β’
31
omlab/SARDet3-FS
Viewer
β’
Updated
β’
270
β’
40
omlab/Cross_DIOR-RSVG
Viewer
β’
Updated
β’
7.42k
β’
26
omlab/Cross_RRSIS-D
Viewer
β’
Updated
β’
3.48k
β’
13
omlab/VRSBench-FS
Viewer
β’
Updated
β’
16.6k
β’
38
β’
1
omlab/NWPU-FS
Viewer
β’
Updated
β’
39
β’
8
omlab/EarthReason-FS
Viewer
β’
Updated
β’
3.39k
β’
42
omlab/VLM-R1
Preview
β’
Updated
β’
313
β’
18
omlab/RS5M
Viewer
β’
Updated
β’
7.25M
β’
407
β’
1