From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models Paper • 2406.16838 • Published Jun 24 • 3
Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL Paper • 2410.12491 • Published 19 days ago • 3
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation Paper • 2409.12941 • Published Sep 19 • 20
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence Paper • 2404.05892 • Published Apr 8 • 31
