Article
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
NormalUhr
• • 293Hongbo-Z
Hongbo-Z
·
AI & ML interests
LLM, VLM and Diffusion
Recent Activity
liked a dataset 3 days ago
openai/openai_humaneval liked a model 5 days ago
Qwen/Qwen3-VL-4B-Thinking liked a model 5 days ago
Qwen/Qwen3.5-4BOrganizations
None yet
upvoted 2
articles 8 months ago
Article
Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
- +2
ariG23498, merve, pcuenq, reach-vb
• • 496 upvoted an article 12 months ago
Article
~Don't~ Repeat Yourself
patrickvonplaten
• • 55 upvoted a paper almost 2 years ago