TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning
Paper • 2610.07043 • Published • 39
Yupeng Su
YupengSu
AI & ML interests
Efficient/Low-Resources Methods for NLP, Model Edge Deployment.
Recent Activity
upvoted a paper about 18 hours ago
TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning upvoted a paper 5 months ago
MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization updated a model about 2 years ago
YupengSu/mmfreelm-370m-dirOrganizations
upvoted a paper about 18 hours ago