arxiv:2502.20545
Liu
Shiweiliuiiiiiii
AI & ML interests
LLM, pre-training, post-training, RL, efficient AI
Recent Activity
upvoted a paper 27 days ago
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs upvoted a paper 27 days ago
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts QuantizationOrganizations
None yet