Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Paper
•
2501.19324
•
Published
•
37
Baohao Liao
baohao
AI & ML interests
NLP
Recent Activity
new activity
11 days ago
cognitivecomputations/DeepSeek-R1-AWQ:Deployment framework
new activity
12 days ago
open-r1/README:[Experiment] Applying GRPO to DeepSeek-R1-Distill-Qwen-1.5B with LIMO
commented on
a paper
17 days ago
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Organizations
