Peng Li

Tahoe transforms Text-to-SQL by utilizing a dynamic hint optimization approach that boosts performance without retraining models.

P-RWKV achieves competitive performance in 3D point cloud representation learning while slashing computational costs and inference latency compared to traditional methods.

Text world models can transform LLM-based agents from reactive responders into proactive planners, enhancing their performance in complex interactive tasks.

LLM agents can substantially improve their task-solving abilities by treating skills as long-lived, experience-aware, and testable assets within a managed lifecycle.

LLM agents can get a ~5% performance boost and 4x memory reduction by representing workflows as graphs and adaptively instantiating them based on task semantics.