StingNing

Must-read papers on prompt-based tuning for pre-trained language models.

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

百亿参数的中英文双语基座大模型

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)