Yaorui SHI

yrshi

·

syr-cn

AI & ML interests

None yet

Recent Activity

upvoted a paper about 10 hours ago

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

upvoted a paper 7 days ago

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

upvoted a paper 18 days ago

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

View all activity

Organizations

Collections 1

Papers 14

arxiv:2605.06130

arxiv:2603.12631

arxiv:2602.10560

arxiv:2602.07594

spaces 2

AutoRefine

Space of [NeurIPS 2025] paper AutoRefine

ReactXT

models 5

yrshi/ReMemR1-7B

8B • Updated Feb 21 • 73 • 2

yrshi/AutoRefine-Qwen2.5-7B-Instruct

Question Answering • 8B • Updated Jan 21 • 11 • 1

yrshi/AutoRefine-Qwen2.5-7B-Base

Question Answering • 8B • Updated Jan 21 • 13 • 1

yrshi/AutoRefine-Qwen2.5-3B-Base

Question Answering • 3B • Updated Jan 21 • 28 • 2

yrshi/AutoRefine-Qwen2.5-3B-Instruct

3B • Updated May 16, 2025 • 15 • 1

datasets 0

None public yet