Trials, Errors, and Breakthroughs: Our Rocky Road to OVD SOTA with Reinforcement Learning
•
1
Om AI Lab
Enterprise
company
AI & ML interests
Multimodal AI, Agents
Recent Activity
Articles
Organization Card
Om AI Lab is a passionate group building multimodal AI agents that reshape our work and life.
Collections
2
A collection of VLM-R1 Models
-
ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration
Paper • 2411.16044 • Published • 1 -
OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding
Paper • 2407.04923 • Published • 1 -
OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network
Paper • 2209.05946 • Published • 1 -
VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations
Paper • 2207.00221 • Published • 1
spaces
4
pinned
Running
15
Open Agent Leaderboard
🥇
Open Agent Leaderboard
Running
1
OmAgent
💬
Process and answer questions about webpage videos
Running
on
Zero
6
VLM R1 OVD
👁
VLM-R1 model for Open-Vocabulary Object Detection
Running
on
Zero
61
VLM R1 Referral Expression
💬
Highlight described objects in images
models
6
omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321
Updated
•
516
•
2
omlab/VLM-R1-Qwen2.5VL-3B-Math-0305
Updated
•
301
omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps
Updated
•
1.03k
•
21
omlab/omdet-turbo-swin-tiny-hf
Zero-Shot Object Detection
•
Updated
•
10.4k
•
33
omlab/omchat-v2.0-13B-single-beta_hf
Updated
•
14
•
5
omlab/OmDet-Turbo_tiny_SWIN_T
Zero-Shot Object Detection
•
Updated
•
6