ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
48:03
MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks
41:57
Scalable, Robust, and Hardware-aware Speculative Decoding
36:56
Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
38:45
Reflections on Models of Language: What's the Next Thing To Do? (Part 1 of 2)
48:06
Yale NLP/LLM Interest Group Session 22
6:54
Watch Samba-1 in action
12:40
Synthetic Data Generation
21:04