Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL Paper • 2410.12491 • Published 27 days ago • 4
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation Paper • 2409.12941 • Published Sep 19 • 21
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence Paper • 2404.05892 • Published Apr 8 • 31
