Weiyang Jin

PhD student, University of Hong Kong

Joined

March 2023

Names

Weiyang Jin (Preferred)

Emails

****@bjtu.edu.cn (Confirmed)

****@gmail.com (Confirmed)

****@connect.hku.hk (Confirmed)

Personal Links

DBLP

ORCID

Career & Education History

PhD student

University of Hong Kong (hku.hk)

2025 – 2029

Intern

New York University (nyu.edu)

2023 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Xihui Liu

2025 – Present

Expertise

Deep Learning

2022 – Present

Computer Vision

2021 – Present

Publications

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Spatially Guided Training for Vision-Language-Action Model
Jinhui Ye, Fangjing Wang, Ning Gao, Junqiu Yu, Zhu Yangkun, Bin Wang, Jinyu Zhang, Weiyang Jin, Yanwei Fu, Feng Zheng, Yilun Chen, Jiangmiao Pang
- ICLR 2026 Poster
- Readers: Everyone
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Siyuan Li, Zedong Wang, Zicheng Liu, Juanxi Tian, Di Wu, Cheng Tan, Weiyang Jin, Stan Z. Li
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
GTR: Semi-supervised Learning with Grouping and Transporting for Robust Thresholding
Weiyang Jin, Siyuan Li, Zicheng Liu, Zedong Wang, Juanxi Tian, Di Wu, Cheng Tan, Chang Yu, Stan Z. Li
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Siyuan Li, Juanxi Tian, Zicheng Liu, Ge Wang, Zedong Wang, Weiyang Jin, Di Wu, Tao Lin, Cheng Tan, Yang Liu, Baigui Sun, Stan Z. Li
- Submitted to ICLR 2025
- Readers: Everyone
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Siyuan Li, Juanxi Tian, Zedong Wang, Luyuan Zhang, Zicheng Liu, Weiyang Jin, Yang Liu, Baigui Sun, Stan Z. Li
- Submitted to ICLR 2025
- Readers: Everyone
SPA: Enhancing 3D Multimodal LLMs with Mask-based Streamlining Preference Alignment
Weiyang Jin, Baihan Yang, Huan-ang Gao, Jingwei Zhao, Kangliang Chen, Hao Zhao
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Siyuan Li, Zedong Wang, Zicheng Liu, Di Wu, Cheng Tan, Weiyang Jin, Stan Z. Li
- Submitted to NeurIPS 2024 Track Datasets and Benchmarks
- Readers: Everyone
SemiReward: A General Reward Model for Semi-supervised Learning
Siyuan Li, Weiyang Jin, Zedong Wang, Fang Wu, Zicheng Liu, Cheng Tan, Stan Z. Li
- ICLR 2024 poster
- Readers: Everyone
OpenMixup: A Comprehensive Mixup Benchmark for Visual Classification
Siyuan Li, Zedong Wang, Zicheng Liu, Di Wu, Cheng Tan, Weiyang Jin, Stan Z. Li
- Submitted to ICLR 2024
- Readers: Everyone

View all 11 publications

Co-Authors

View all 36 co-authors