Zhanhui Kang

Researcher, tencent, Tencent

Joined

February 2020

Names

Zhanhui Kang (Preferred)

Emails

****@tencent.com (Confirmed)

Personal Links

Career & Education History

Researcher

tencent, Tencent (tencent.com)

2006 – 2026

Undergrad student

computer science, Hefei University of Technology (hfut.edu)

2002 – 2006

Advisors, Relations & Conflicts

Coauthor

Ruobing Xie

2022 – 2026

Coauthor

shumingshi

2019 – 2026

Expertise

deep learning

foundation model

2011 – 2023

Publications

Low-hallucination Synthetic Captions Via Visual CheckList Based Reinforcement Learning for Vision-Language Model Pre-training
Xinsong Zhang, Yarong Zeng, Xinting Huang, Hu Hu, Runquan Xie, Han Hu, Zhanhui Kang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
More Expressive Attention with Negative Weights
Ang Lv, Ruobing Xie, Shuaipeng Li, Jiayi Liao, Xingwu Sun, Zhanhui Kang, Di Wang, Rui Yan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
The Climb Carves Wisdom Deeper Than the Summit: On the Importance of Reasoning Patterns
Ang Lv, Ruobing Xie, Xingwu Sun, Zhanhui Kang, Rui Yan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Autonomy-of-Experts Models
Ang Lv, Ruobing Xie, Yining Qian, Songhao Wu, Xingwu Sun, Zhanhui Kang, Di Wang, Rui Yan
- ICML 2025 poster
- Readers: Everyone
Scaling Laws for Floating–Point Quantization Training
Xingwu Sun, Shuaipeng Li, Ruobing Xie, Weidong Han, Kan Wu, Zhen Yang, Yixing Li, An Wang, SHUAI LI, Jinbao Xue, Yu Cheng, Yangyu Tao, Zhanhui Kang, Cheng-zhong Xu, Di Wang, Jie Jiang
- ICML 2025 poster
- Readers: Everyone
Frequency-Augmented Mixture-of-Heterogeneous-Experts Framework for Sequential Recommendation
Junjie Zhang, Ruobing Xie, Hongyu Lu, Wenqi Sun, Xin Zhao, yu chen, Zhanhui Kang
- WWW 2025 Poster
- Readers: Everyone
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Hanlin Tang, Yifu Sun, Decheng Wu, Kai Liu, Jianchen Zhu, Zhanhui Kang
- EMNLP 2023 Main
- Readers: Everyone

Co-Authors

View all 36 co-authors

Zhanhui Kang

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Low-hallucination Synthetic Captions Via Visual CheckList Based Reinforcement Learning for Vision-Language Model Pre-training

More Expressive Attention with Negative Weights

The Climb Carves Wisdom Deeper Than the Summit: On the Importance of Reasoning Patterns

Autonomy-of-Experts Models

Scaling Laws for Floating–Point Quantization Training

Frequency-Augmented Mixture-of-Heterogeneous-Experts Framework for Sequential Recommendation

EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs

Co-Authors