Junjie Yang

Researcher, Xiaohongshu

Joined

September 2019

Names

Junjie Yang (Preferred)

Emails

****@mail.ustc.edu.cn (Confirmed)

****@buckeyemail.osu.edu (Confirmed)

****@gmail.com (Confirmed)

****@xiaohongshu.com (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Researcher

Xiaohongshu (xiaohongshu.com)

2024 – Present

PhD student

Ohio State University (osu.edu)

2019 – 2024

Undergrad student

University of Science and Technology of China (ustc.edu.cn)

2015 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Yingbin Liang

Present

Expertise

LLM

Present

Publications

Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity
Jinze Zhao, Peihao Wang, Junjie Yang, Ruisi Cai, Gaowen Liu, Jayanth Srinivasa, Ramana Rao Kompella, Yingbin Liang, Zhangyang Wang
- CPAL 2026 (Proceedings Track) Oral
- Readers: Everyone
Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
Xueru Wen, Jie Lou, Xinyu Lu, Junjie Yang, yanjiang liu, Yaojie Lu, Debing Zhang, XingYu
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Think When You Need: Self-Adaptive Chain-of-Thought Learning
Junjie Yang, Ke Lin, XingYu
- Submitted to ICLR 2026
- Readers: Everyone
Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
Xueru Wen, Jie Lou, Xinyu Lu, Junjie Yang, Yanjiang Liu, Yaojie Lu, Debing Zhang, XingYu
- CoRR 2025
- Readers: Everyone
Meta ControlNet: Enhancing Task Adaptation via Meta Learning
Junjie Yang, Jinze Zhao, Peihao Wang, Zhangyang Wang, Yingbin Liang
- CPAL 2025 (Proceedings Track) Poster
- Readers: Everyone
Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study
Cheng Chen, Junjie Yang, Yi Zhou
- Accepted by 2020 IEEE International Conference on Big Data
- Readers: Everyone
Meta ControlNet: Enhancing Task Adaptation via Meta Learning
Junjie Yang, Jinze Zhao, Peihao Wang, Yingbin Liang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Enhancing Generalization in Sparse Mixture of Experts Models: The Case for Increased Expert Activation in Compositional Tasks
Jinze Zhao, Junjie Yang, Peihao Wang, Yingbin Liang, Zhangyang Wang
- NeurIPS'24 Compositional Learning Workshop Poster
- Readers: Everyone
Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization
Xuxi Chen, Zhendong Wang, Daouda Sow, Junjie Yang, Tianlong Chen, Yingbin Liang, Mingyuan Zhou, Zhangyang Wang
- CoRR 2024
- Readers: Everyone
Rethinking PGD Attack: Is Sign Function Necessary?
Junjie Yang, Tianlong Chen, Xuxi Chen, Zhangyang Wang, Yingbin Liang
- CoRR 2023
- Readers: Everyone

View all 23 publications

Co-Authors

View all 28 co-authors