InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU Paper • 2502.08910 • Published 11 days ago • 139
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding Paper • 2502.05609 • Published 15 days ago • 15
VideoRAG: Retrieval-Augmented Generation over Video Corpus Paper • 2501.05874 • Published Jan 10 • 67
VideoRAG: Retrieval-Augmented Generation over Video Corpus Paper • 2501.05874 • Published Jan 10 • 67
Revisiting In-Context Learning with Long Context Language Models Paper • 2412.16926 • Published Dec 22, 2024 • 30