When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs Paper • 2510.07499 • Published Oct 8, 2025 • 48
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding Paper • 2502.05609 • Published Feb 8, 2025 • 18
Benchmarking LLMs for Political Science: A United Nations Perspective Paper • 2502.14122 • Published Feb 19, 2025 • 2
VideoRAG: Retrieval-Augmented Generation over Video Corpus Paper • 2501.05874 • Published Jan 10, 2025 • 75