Rho-1: Not All Tokens Are What You Need
Paper
•
2404.07965
•
Published
•
84
Interesting Papers
-
-
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
Paper • 2404.05961 • Published • 64 -
Compression Represents Intelligence Linearly
Paper • 2404.09937 • Published • 27 -
Multi-Head Mixture-of-Experts
Paper • 2404.15045 • Published • 59 -
Stylus: Automatic Adapter Selection for Diffusion Models
Paper • 2404.18928 • Published • 14 -
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report
Paper • 2405.00732 • Published • 118 -
Your Transformer is Secretly Linear
Paper • 2405.12250 • Published • 150 -
Diffusion Models Are Real-Time Game Engines
Paper • 2408.14837 • Published • 121 -
Writing in the Margins: Better Inference Pattern for Long Context Retrieval
Paper • 2408.14906 • Published • 138 -
Differential Transformer
Paper • 2410.05258 • Published • 165 -
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 143