PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch
Paper • 2510.06670 • Published • 1
SJY8460
SJY23
AI & ML interests
NLP/LLM
Recent Activity
authored a paper 1 day ago
PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from
Scratch authored a paper 1 day ago
Aligning Large Language Models via Fully Self-Synthetic Data authored a paper 1 day ago
GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from ZeroOrganizations
None yet