3 papers
cs.LG2026
GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
Shangjian Yin, Yu Fu, Yue Dong +1
Post-training has become a crucial step for unlocking the capabilities of large language models, with reinforcement learning (RL) emerging as a critical paradigm. Recent RL-based p…
cs.CL2026
PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch
Shangjian Yin, Shining Liang, Wenbiao Ding +4
High-quality instruction data is critical for LLM alignment, yet existing open-source datasets often lack efficiency, requiring hundreds of thousands of examples to approach propri…
cs.CL2025
Aligning Large Language Models via Fully Self-Synthetic Data
Shangjian Yin, Zhepei Wei, Xinyu Zhu +2
Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Fe…