Stella Xiong

Xiomghhhh

1 3

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

liked a dataset 2 months ago

nvidia/Nemotron-SFT-OpenCode-v1

liked a dataset 2 months ago

nvidia/OpenMathInstruct-2

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

Paper • 2607.10169 • Published 14 days ago • 12

liked 2 datasets 2 months ago

nvidia/Nemotron-SFT-OpenCode-v1

Preview • Updated Mar 23 • 2.66k • 57

nvidia/OpenMathInstruct-2

Viewer • Updated Nov 25, 2024 • 22M • 114k • 247

liked a Space 9 months ago

The Smol Training Playbook

The secrets to building world-class LLMs