sian cao
sonald
AI & ML interests
AI, big data, OS
Recent Activity
upvoted an article about 1 month ago
SmolVLM Grows Smaller – Introducing the 256M & 500M Models! liked
a Space about 1 month ago
HuggingFaceH4/blogpost-scaling-test-time-compute upvoted a paper about 2 months ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Organizations
