Om AI Lab

Enterprise

company

https://github.com/om-ai-lab

OmAI_lab

om-ai-lab

Activity Feed

AI & ML interests

Multimodal AI, Agents

Recent Activity

Pome7o updated a Space 17 days ago

omlab/OmAgentVideoUnderstanding

View all activity

Articles

Trials, Errors, and Breakthroughs: Our Rocky Road to OVD SOTA with Reinforcement Learning

18 days ago

• 1

Improving Object Detection through Reinforcement Learning with VLM-R1

18 days ago

• 2

omlab's activity

Pome7o

updated a Space 17 days ago

OmAgent

💬

Process and answer questions about webpage videos

SZhanZ

updated a dataset 19 days ago

omlab/VLM-R1

Preview • Updated 19 days ago • 3.55k • 12

tianchez

published a Space 21 days ago

VLM R1 OVD

👁

VLM-R1 model for Open-Vocabulary Object Detection

qq-hzlh

updated a collection 21 days ago

VLM-R1-models

Collection

A collection of VLM-R1 Models • 7 items • Updated 21 days ago • 4

SZhanZ

updated a model 22 days ago

omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321

Updated 22 days ago • 522 • 2

qq-hzlh

updated a model 22 days ago

omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321

Updated 22 days ago • 522 • 2

qq-hzlh

updated a Space 22 days ago

VLM R1 OVD

👁

VLM-R1 model for Open-Vocabulary Object Detection

Liaojiajia

updated a model 22 days ago

omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321

Updated 22 days ago • 522 • 2

Liaojiajia

published a model 22 days ago

omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321

Updated 22 days ago • 522 • 2

Zilun

updated a dataset 26 days ago

omlab/RS5M

Viewer • Updated 26 days ago • 7.25M • 370

Zilun

published a dataset 30 days ago

omlab/RS5M

Viewer • Updated 26 days ago • 7.25M • 370

Liaojiajia

updated a collection about 1 month ago

VLM-R1-models

Collection

A collection of VLM-R1 Models • 7 items • Updated 21 days ago • 4

Liaojiajia

updated a model about 1 month ago

omlab/VLM-R1-Qwen2.5VL-3B-Math-0305

Updated Mar 5 • 302

Liaojiajia

published a model about 1 month ago

omlab/VLM-R1-Qwen2.5VL-3B-Math-0305

Updated Mar 5 • 302

Liaojiajia

updated a Space about 1 month ago

Open Agent Leaderboard

🥇

Open Agent Leaderboard

SZhanZ

updated a Space about 1 month ago

VLM R1 Referral Expression

💬

Highlight described objects in images

tianchez

posted an update about 2 months ago

Post

4263

Introducing VLM-R1!

GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks?

The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task).

https://github.com/om-ai-lab/VLM-R1