Yinghui He

yinghuihe

·

https://ying-hui-he.github.io/

AI & ML interests

Natural Language Processing, Machine Learning Theory

Recent Activity

upvoted a paper 3 days ago

PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

upvoted a paper about 1 month ago

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

submitted a paper about 1 month ago

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

View all activity

Organizations

upvoted a paper 3 days ago

PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

Paper • 2609.40285 • Published 5 days ago • 21

upvoted a paper about 1 month ago

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

Paper • 2608.27455 • Published Aug 27 • 12

upvoted a paper about 2 months ago

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Paper • 2608.05139 • Published Aug 5 • 28

upvoted a paper 6 months ago

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Paper • 2604.12002 • Published Apr 13 • 12

upvoted a paper 12 months ago

Skill-Targeted Adaptive Training

Paper • 2510.10023 • Published Oct 11, 2025 • 10

upvoted 2 papers about 1 year ago

Humanline: Online Alignment as Perceptual Loss

Paper • 2509.24207 • Published Sep 29, 2025 • 12

AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models

Paper • 2505.00147 • Published Apr 30, 2025 • 4