WEIYANG JIN

Biography

I am a Ph.D. student at MMLab, University of Hong Kong, starting from November 2025, supervised by Prof. Xihui Liu. I am also fortunate to be collaborating with Prof. Saining Xie. My research interests lie in machine learning, with a particular focus on how to build visual intelligence via representation and self-evolution.

News

• 2026/07 SRUM accepted to ECCV 2026.
• 2026/02 UniVerse accepted to CVPR 2026.
• 2026/01 WISE accepted to ICML 2026.
• 2025/11 Joined Echo Team @ Joy Future Academy as a research intern.
• 2025/10 Will join HKU-MMLab and start my PhD career.

Selected Projects

(*: Equal Contribution, †: Project Leader)

World Model 2

Echo-Memory: A Controlled Study of Memory in Action World Models

Wayne King†, Zeyue Xue, Yuxuan Bian, Jie Huang, Haoran Li, Yaowei Li, Yaofeng Su, Yuming Li, Haoyu Wang, Shiyi Zhang, Songchun Zhang, Yuwei Niu, Sihan Xu, Junhao Zhuang, Haoyang Huang, Nan Duan†

The University of Hong Kong Under Review

Paper Project Code 233

Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation

Yuxuan Bian, Zeyue Xue, Songchun Zhang, Shiyi Zhang, Weiyang Jin, Yaowei Li, Junhao Zhuang, Haoran Li, Jie Huang, Haoyang Huang, Nan Duan†, Qiang Xu†

The Chinese University of Hong Kong Under Review

Paper Project Code 106

Generative Models 4

UniVerse: Empower Unified Generation with Reasoning and Knowledge

Kaiyue Sun*, Weiyang Jin*, Chengqi Duan, Rongyao Fang, Xian Liu, Yuwei Niu, Chunwei Wang, Aoxue Li, Xihui Liu

The University of Hong Kong CVPR 2026

Paper Code 4

WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation

Yuwei Niu*, Munan Ning*, Mengren Zheng, Weiyang Jin†, Bin Lin, Peng Jin, Jiaqi Liao, Chaoran Feng, Kunpeng Ning, Bin Zhu, Li Yuan

Peking University / Chongqing University ICML 2026

Paper Code 212

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

Weiyang Jin*, Yuwei Niu*, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu

HKU MMLab / The University of Hong Kong ECCV 2026

Paper Code 93

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

Yuwei Niu*, Weiyang Jin*, Jiaqi Liao, Chaoran Feng, Peng Jin, Bin Lin, Zongjian Li, Bin Zhu, Weihao Yu, Li Yuan

Peking University / Chongqing University Under Review

Paper Code 60

Foundation Models 1

Next-Embedding Predictive Architectures Are Strong Vision Learners

Sihan Xu, Ziqiao Ma, Wenhao Chai, Xuweiyi Chen, Weiyang Jin, Joyce Chai, Saining Xie, Stella X. Yu

University of Michigan Under Review

Paper Code 338

Technical Reports 4

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

Intern Robotics Team Tech Report

Paper Code 418

RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies

AI MMLab Club Tech Report

Paper Project Code 295

JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

Echo Team Tech Report

Paper Code 1,828

JoyAI-Image: Awakening Spatial Intelligence in Unified Multimodal Understanding and Generation

JD Future Team Tech Report

Paper Code 2,239

Experience

• Echo Team @ Joy Future Academy Research Intern with Dr. Haoyang Huang
  Nov 2025 - Present
• Shanghai Artificial Intelligence Laboratory, Intern Robotics Research Intern with Dr. Yilun Chen
  May 2025 - Aug 2025
• New York University, Vision-X Lab Research Intern with Prof. Saining Xie
  Feb 2024 - May 2025
• Westlake University, CAIRI Lab Research Intern with Prof. Stan Z. Li, IEEE Fellow
  Apr 2023 - Feb 2024
• Tsinghua University, AIR Research Intern with Prof. Hao Zhao
  May 2022 - Apr 2023

Community Contribution

• SOTA-Seminar, Founder An academic exchange community driven by interest, dedicated to communication in different fields and holding academic seminars regularly.
• Lumina, Core-Member The largest embodied intelligence open-source community in China, dedicated to a more open and comprehensive embodied intelligence culture.