CV

Download PDF

Education

• B.Sc. in Artificial Intelligence, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi — Aug 2025 – present. GPA 3.94 / 4.0.
  • Dean’s List (<10%); Sheikh Tahnoon bin Zayed Scholarship in AI Excellence; Pioneer Scholarship.
  • Selected coursework: Applied Machine Learning (M.S. course), Physics & Life Science, Advanced Mathematics.
• High School, Beijing National Day School (BNDS), Beijing — Sep 2019 – Jul 2025.
  • Advanced Placement program jointly with Wasatch Academy (USA).
  • Coursework beyond AP: Calculus III, Differential Equations, Probability Theory, Linear Algebra, Sociology, Marine Biology.
  • SAT 1550 (Math 800 / EBRW 750); TOEFL 111; CEFR C1; seven AP exams scored 5.

Research interests

• Generative models — score-based / diffusion models, discrete diffusion, surrogates for optimization
• Agentic AI — memory, retrieval, and evaluation of autonomous LLM agents
• AI for science — AI-driven drug discovery, biomedical ML agents, protein & genetic-circuit modeling
• Scientific machine learning — physics-informed neural networks and mathematical modeling

Research experience

• Diffusion Surrogates for Offline Optimization (SPADE) — co-first author, Mila – Quebec AI Institute. Oct 2025 – Jan 2026. Conditional diffusion surrogates for offline black-box optimization. Accepted to ICML 2026 and the ICLR 2026 DeLTa workshop. Advisors: Ye Yuan & Prof. Xue (Steve) Liu.
• Surrogate-Guided Memory Retrieval for Agents — co-first author, Mila. Apr 2026 – present. Offline, surrogate-guided training of memory retrieval for autonomous agents.
• BioXArena — key contributions to paper formulation, GenBio AI (Prof. Le Song). Oct 2025 – May 2026. Benchmark of 76 end-to-end biomedical ML coding tasks across 9 domains (arXiv:2605.15766).
• Herculean — ran several key experiments. Mar – May 2026. Agentic benchmark for financial intelligence; under review at NeurIPS 2026 (arXiv:2605.14355).
• QUACK — contributing author, Mila. 2026. Auditing whether multimodal social-deduction agents’ claims are grounded in what they observed (arXiv:2605.27068).
• Semi-Supervised High-Order Relation Learning — contributing author, Harvard Medical School (Prof. Jun Wen). Mar – May 2026. Prediction over a drug–combination–disease relationship dataset.
• A Survey on Discrete Diffusion Models — contributing author. Mar 2026 – present.

Publications

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

Ye Yuan, Rui Song, Weien Li, et al. (including Yonghan Yang), and Xue Liu. (2026). "QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents." arXiv:2605.27068.

Herculean: An Agentic Benchmark for Financial Intelligence

Xueqing Peng, Zhuohan Xie, Yupeng Cao, et al. (including Yonghan Yang). (2026). "Herculean: An Agentic Benchmark for Financial Intelligence." arXiv:2605.14355. Under review at NeurIPS 2026.

BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks

Loka Li, Duzhen Zhang, Xingbo Du, et al. (including Yonghan Yang), Bin Zhang, and Le Song. (2026). "BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks." arXiv:2605.15766.

Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization

Yonghan Yang*, Ye Yuan*, Zipeng Sun, Linfeng Du, Bowei He, Haolun Wu, Can Chen, and Xue Liu. (2026). "Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization." Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), PMLR 306, Seoul, South Korea. (* equal contribution)

Surrogate-Guided Memory Retrieval for Autonomous Agents

Yonghan Yang*, Ye Yuan*, et al. Surrogate-Guided Memory Retrieval for Autonomous Agents. Manuscript in preparation, 2026. (* equal contribution)

A Survey on Discrete Diffusion Models

Yonghan Yang, et al. A Survey on Discrete Diffusion Models. Manuscript in preparation, 2026.

Semi-Supervised High-Order Relation Learning for Drug–Combination–Disease Prediction

Yonghan Yang, et al. Semi-Supervised High-Order Relation Learning for Drug–Combination–Disease Prediction. Manuscript in preparation, 2026.

Honors & awards

• Sheikh Tahnoon bin Zayed Scholarship in AI Excellence & Dean’s List — MBZUAI (2025–26)
• iGEM — Gold medal & top-10 high-school team, two consecutive years (2024, 2025)
• 2025 IMMC — Outstanding (top <1%, Greater China) & Meritorious (top <10%, International)
• 2024 John Locke Institute Global Essay Prize — Finalist & Merit (Economics)
• 2024 ARML — National Silver · 2024 Purple Comet! Math Meet — China 2nd place · 2024 JHMT — Team Silver
• 2023 British Biology Olympiad — Global Gold · 2022 UKBC Intermediate Biology Olympiad — Bronze
• 2022 Junior Canadian Chemistry Olympiad — China Gold, Global Bronze
• 2023 HiMCM — Honorable Mention · 2024 GOI Peace Foundation Essay Contest — Finalist (top 100 / 10,233)
• AP Scholar with Distinction (2024) · 2022 China Thinks Big — research paper accepted to Digital Library

Service & leadership

• Reviewer, ICLR 2026 Workshop on Foundation Models for Science (FM4Science) — 2026
• President & instructor, BNDS synthetic-biology club & iGEM team — 2022–2025
• Team leader, IMMC / MCM mathematical modeling — 2025–2026
• Participant, Rhino-Bird Science Talent Advancement Program (BNRist · Tsinghua · Tencent) — 2024
• Community volunteering with IUCN and HCI; tea-ceremony and environmental-protection service in Beijing

Skills

• Programming: Python, Rust, TypeScript
• Scientific writing & typesetting: Markdown, Typst, LaTeX
• Computational biology: SnapGene, Benchling, AutoDock Vina, AlphaFold, PyMOL
• Visualization & design: Manim, PowerPoint, Photoshop
• Languages: Mandarin (native), English (fluent), French & Japanese (learning)