arxiv:2403.15042
Nicholas Lee
nicholaslee
AI & ML interests
NLP, Speech, Efficient ML, Generative
Recent Activity
upvoted a paper 3 days ago
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts upvoted a paper 6 months ago
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation upvoted a paper 10 months ago
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache
RematerializationOrganizations
