Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Paper
•
2501.19324
•
Published
•
32
Jan-Christoph Kalo
janck
AI & ML interests
Knowledge Graphs
Information Extraction
Recent Activity
upvoted
a
paper
3 days ago
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
new activity
10 months ago
google/gemma-2b-it:Transformer Pipeline
liked
a model
about 2 years ago
ibm-research/knowgl-large
Organizations
None yet