InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU Paper • 2502.08910 • Published 4 days ago • 117
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding Paper • 2502.05609 • Published 8 days ago • 14
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
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding Paper • 2412.02186 • Published Dec 3, 2024 • 22
Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion Paper • 2311.06318 • Published Nov 10, 2023 • 2