Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs Paper • 2412.21187 • Published 6 days ago • 25
HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving Paper • 2412.20735 • Published 7 days ago • 9
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper • 2402.13753 • Published Feb 21, 2024 • 114
Speculative Streaming: Fast LLM Inference without Auxiliary Models Paper • 2402.11131 • Published Feb 16, 2024 • 42