Kyusong Lee's picture

4

Kyusong Lee

kyusonglee

·

AI & ML interests

None yet

Recent Activity

liked a Space 5 days ago

omlab/VLM-R1-Referral-Expression

reacted to tianchez's post with 🚀 9 days ago

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

authored a paper about 1 month ago

OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer

View all activity

Organizations

Papers 1

arxiv:2406.16620

models

None public yet

datasets

None public yet