Yizhen Zhang

I am a second-year master student at IIGroup in Tsinghua University, supervised by Prof. Yujiu Yang. I received my Bachelor's degree at Computer Science and Technology, Harbin Institute of Technology, Shenzhen.

Previously, I was honoured to work with Prof. Wenjie Pei in HITsz. I am currently working closely with Ruilin Luo, Shuoshuo Zhang and Yang Ding at THU.

Email  /  WeChat  /  Github  /  Google Scholar

profile photo
Education
THU logo Tsinghua University
M.Eng. in Artificial Intelligence (2024 - Now)
Advisor: Prof. Yujiu Yang
XDU logo Harbin Institute of Technology, Shenzhen
B.Eng. in Computer Science and Technology (2020 - 2024)
Advisor: Prof. Wenjie Pei
News
  • [Apr. 2026] 🔥 Hy3-preview is open-sourced! Honored to contribute to the RL post-training. Welcome to try and follow our work at Tencent Hy Research.
Research

My current research focuses on Multimodal Large Language Models (MLLMs), specifically revolutionizing reinforcement learning for the alignment of Vision-Language Models and continuously pushing the boundaries of their reasoning ability to unlock full potential in complex scenarios.

Publications (* denotes equal contribution)

profile photo See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning
Shuoshuo Zhang*, Yizhen Zhang*, Jingjing Fu, Lei Song, Jiang Bian, Yujiu Yang, Rui Wang
CVPR 2026
Preprint / Code


profile photo OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
Xinchen Zhang, Bowei Liu, Jiale Liu, Chufan Shi, Yizhen Zhang, Junhong Liu, Youliang Zhang, Zhiheng Li, Yujiu Yang, Ling Yang
ICML 2026
Preprint


profile photo From Narrow to Panoramic Vision: Attention-Guided Cold Start Reshapes Multimodal Reasoning
Ruilin Luo*, Chufan Shi*, Yizhen Zhang*, Cheng Yang, Songtao Jiang, Tongkun Guan, Ruizhe Chen, Ruihang Chu, Peng Wang, Mingkun Yang, Yujiu Yang, Junyang Lin, Zhibo Yang
ICLR 2026
Preprint / Code


profile photo VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
Yang Ding*, Yizhen Zhang*, Xin Lai, Ruihang Chu, Yujiu Yang
ICLR 2026
Preprint / Code


profile photo PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images
Shuoshuo Zhang*, Zijian Li*, Yizhen Zhang, Jingjing Fu, Lei Song, Jiang Bian, Jun Zhang, Yujiu Yang, Rui Wang
ICLR 2026
Preprint / Code


profile photo PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning
Yizhen Zhang*, Yang Ding*, Shuoshuo Zhang*, Xinchen Zhang, Haoling Li, Zhong-zhi Li, Peijie Wang, Jie Wu, Lei Ji, Yelong Shen, Yujiu Yang, Yeyun Gong
NeurIPS 2025
Preprint / Code


profile photo Teaching Your Models to Understand Code via Focal Preference Alignment
Jie Wu*, Haoling Li*, Xin Zhang*, Xiao Liu, Yangyu Huang, Jianwen Luo, Yizhen Zhang, Zuchao Li, Ruihang Chu, Yujiu Yang, Scarlett Li
EMNLP main 2025
Preprint / Code


profile photo Efficiently Building Large Language Models through Merging
Yizhen Zhang*, Yang Ding*, Jie Wu*, Yujiu Yang
NeurIPS 2024 LMC Oral
Preprint

Experience
rednote logo Tencent, Large Language Model Post-training Team
Research Intern 2026 - Project Up (青云计划)
Topic: Post-training & RL
bytedance logo Microsoft, NLC Group
Research Intern 2025 - Star of Tomorrow (明日之星)
Topic: Multimodal Large Language Models Reasoning
Mentor: Lei Ji, Yeyun Gong, Yelong Shen
rednote logo Rednote, Communities Feed Team
Research Intern 2024
Topic: Recommendation System & Computational Advertising
Honors & Awards
  • Neurips 2024 Large Language Model Merging Challenge (LMC)[link] Rank:1/150, 2024
  • CVPR 2023 workshop Image Matching Challenge [link] Silver medal, 2023