Zhao Yang

Zhao Yang

About Me

Hi, I’m Zhao Yang, a third-year PhD student at Renmin University of China, supervised by Prof. Bing Su. I received my Bachelor’s degree from Sichuan University. My research interests focus on Language Models and Deep Generative Models, with a particular emphasis on their applications in AI for Biology (AI4Bio) and sequence-based scientific data.

Recent Research Interests:

  • Developing sequence-based scientific foundation models to advance biological and scientific understanding.
  • Integrating foundation models with biological data and prior knowledge to solve critical community-focused tasks, such as variant effect prediction (VEP).

Projects

* indicates equal contribution

Regulatory DNA Sequence Design with Reinforcement Learning

Zhao Yang, Bing Su, Chuan Cao, Ji-Rong Wen. ICLR 2025.
📄 Paper
💻 Code
TL;DR: We propose a reinforcement learning framework for designing regulatory DNA sequences using transcription factor binding site rewards.

SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model

Jiwei Zhu* , Zhao Yang*, Bing Su. ICLR 2025 AI4NA Workshop & MLGenX Workshop.
TL;DR: We leverage MoE to better model cross-species and cross-genomic profile information in genomic data.

Interpretable Enzyme Function Prediction via Residue-Level Detection

Zhao Yang, Bing Su, Jiahao Chen, Ji-Rong Wen. Preprint, ICLR 2025 LMRL Workshop.
📄 Paper
💻 Code
TL;DR: We propose ProtDETR, a novel framework that reframes enzyme function prediction as an object detection problem by identifying active sites as “objects” to interpret enzyme functionality.

Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling

Zhao Yang, Bing Su, Ji-Rong Wen. ACM MM 2023.
📄 Paper
💻 Code
TL;DR: We propose a text-driven diffusion-based framework for synthesizing long-term human motions, achieving coherent and realistic sequences with novel sampling strategies.

A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language

Bing Su, Dazhao Du, Zhao Yang, Yujie Zhou, Jiangmeng Li, Anyi Rao, Hao Sun, Zhiwu Lu, Ji-Rong Wen. Preprint.
📄 Paper
💻 Code
TL;DR: We propose MoMu, a foundation model associating molecular graphs with natural language, enabling multimodal understanding and applications in molecular science.

Experience

  • Research Intern, Microsoft Research AI4Science China
    Nov 2023 – Nov 2024
    Mentor: Dr. Chuan Cao

Service

  • Reviewer: CVPR 2024, NeurIPS 2024, AISTATS 2025, ICLR 2025, ICML 2025, NeurIPS 2025