Tung-Lin Wu's picture

3 12 8

Tung-Lin Wu

tunglinwu

·

tunglinwood

AI & ML interests

None yet

Recent Activity

upvoted a paper 4 days ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

reacted to tianchez's post with 🔥 4 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

upvoted an article 5 days ago

What is test-time compute and how to scale it?

View all activity

Organizations

None yet

tunglinwu's activity

New activity in FreedomIntelligence/PubMedVision about 2 months ago

Missing image files

#3 opened about 2 months ago by

New activity in FreedomIntelligence/HuatuoGPT-Vision-7B 2 months ago

How to pre-process the data to finetune the model?

#8 opened 2 months ago by

New activity in BAAI/AquilaMed-RL 4 months ago

AquilaMed-RL

#2 opened 4 months ago by