SJY8460's picture

3 1

SJY8460

SJY23

https://sjy8460.github.io/

AI & ML interests

NLP/LLM

Recent Activity

authored a paper 2 days ago

PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch

authored a paper 2 days ago

Aligning Large Language Models via Fully Self-Synthetic Data

authored a paper 2 days ago

GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero

View all activity

Organizations

None yet

authored 3 papers 2 days ago

PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch

Paper • 2510.06670 • Published Oct 8, 2025 • 1

Aligning Large Language Models via Fully Self-Synthetic Data

Paper • 2510.06652 • Published Oct 8, 2025 • 1

GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero

Paper • 2605.15464 • Published 14 days ago

liked a model about 1 month ago

Qwen/Qwen3.5-4B

Image-Text-to-Text • 5B • Updated Mar 2 • 8.3M • • 565

updated a dataset about 2 months ago

SJY23/PiKa-SFT-30k

Viewer • Updated Apr 9 • 30k • 152 • 2

published a dataset about 2 months ago

SJY23/PiKa-SFT-30k

Viewer • Updated Apr 9 • 30k • 152 • 2

upvoted a paper 3 months ago

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published Mar 6 • 93

upvoted 2 papers 8 months ago

Aligning Large Language Models via Fully Self-Synthetic Data

Paper • 2510.06652 • Published Oct 8, 2025 • 1

PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch

Paper • 2510.06670 • Published Oct 8, 2025 • 1

updated a dataset over 1 year ago

SJY23/SAO-Gemma-9B

Viewer • Updated Oct 28, 2024 • 80k • 26