About

My name is Yu-Hao Huang. I am a fifth-year Ph.D. candidate at School of Computer Science, Nanjing University, advised by Prof. Wu-Jun Li since 2021. I obtained my Bachelor’s degree in FinTech class, Nanjing University on June 2021.

My research interests include generative time series modeling (diffusion models, time series foundation models, cross-modal generation) and reinforcement learning (for decision-making or LLM post-training). I am also interested in applying cutting-edge machine learning techniques (i.e. Transformers, reinforcement learning, diffusion models, LLMs) on quantitative finance problems (i.e. portfolio management, market simulation).

Experience

• Research Intern, Machine Learning Group, Microsoft Research Asia.
  • Mentor: Dr. Lei Song
  • 04/2025 - Now
• Research Intern, Machine Learning Group, Microsoft Research Asia.
  • Mentor: Dr. Chang Xu
  • 02/2023 - 08/2024
  • Core contributor of open-source project TimeCraft.
• Quantitative Investment Lab Intern, Institute for Interdisciplinary Information Core Technology(Xi’an)/Turning AI Research Institute(Nanjing).
  • 11/2019 - 10/2020

Selected Publications

• Controllable Financial Market Generation with Diffusion Guided Meta Agent
  Yu-Hao Huang, Chang Xu, Yang Liu, Weiqing Liu, Wu-Jun Li, Jiang Bian
  • AAAI 2026 (Oral).
  • This work is also presented in GenAI in Finance Workshop, NeurIPS 2025 / AI4TS Workshop (Oral), WWW 2025.
• In-Context Compositional Q-Learning for Offline Reinforcement Learning
  Qiushui Xu, Yuhao Huang, Yushu Jiang, Lei Song, Jinyu Wang, Wenliang Zheng, Jiang Bian
  • ICLR 2026.
• MIRA: Medical Time Series Foundation Model for Real-World Health Data
  Hao Li, Bowen Deng, Chang Xu, Zhiyuan Feng, Viktor Schlegel, Yu-Hao Huang, Yizheng Sun, Jingyuan Sun, Kailai Yang, Yiyao Yu, Jiang Bian
  • NeurIPS 2025.
• Bridge: Bootstrapping text to control time-series generation via multi-agent iterative optimization and diffusion modelling
  Hao Li*, Yuhao Huang*, Chang Xu, Viktor Schlegel, Renhe Jiang, Riza Batista-Navarro, Goran Nenadic, Jiang Bian
  • ICML 2025
• TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts
  Yu-Hao Huang, Chang Xu, Yueying Wu, Wu-Jun Li, Jiang Bian
  • AAAI 2025.
• InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models
  Min Hou, Yueying Wu, Chang Xu, Yu-Hao Huang, Chenxi Bai, Le Wu, Jiang Bian
  • KDD 2025.
• TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation
  Bowen Deng, Chang Xu, Hao Li, Yuhao Huang, Min Hou, Jiang Bian
  • KDD 2025.
• NumLLM: Numeric-Sensitive Large Language Model for Chinese Finances
  Huan-Yi Su, Ke Wu, Yu-Hao Huang, Wu-Jun Li
  • Arxiv preprint, 2024.
• MG-TSD: Multi-granularity time series diffusion models with guided learning process
  Xinyao Fan, Yueying Wu, Chang Xu, Yuhao Huang, Weiqing Liu, Jiang Bian
  • ICLR 2024.

(* indicates equal contribution.)

Service

• Reviewer: ICML 2026; AAAI 2026; NeurIPS 2025; ICLR 2025/2026; ACL ARR since June 2024
• Top reviewer: NeurIPS 2025
• Conference volunteer: ICML 2025; AAAI 2026

Teaching

• Introduction to Big Data and Python Implementation
  • Teaching Assistant, Nanjing University, 2022 Fall
• Data Structure
  • Teaching Assistant, Nanjing University, 2024 Fall