Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Julius-L
's Collections
Generation
Long Context
Finetuning
Memory Efficient Training
Pretraining
Model Architecture
Model Merging
Sparsification
Quantization
LLM Technical Reports
Unseen Papers
Generation
updated
15 days ago
Upvote
-
Fast Best-of-N Decoding via Speculative Rejection
Paper
•
2410.20290
•
Published
21 days ago
•
9
Upvote
-
Share collection
View history
Collection guide
Browse collections