I am a researcher and builder focused on turning AI into real-world impact. I value curiosity, clarity, and disciplined execution. I believe landing the value of AI requires both scientific depth and hands-on craftsmanship. I enjoy open dialogue, sharing what I’ve learned, and learning from others along the way.

I currently serve as the Head of Enterprise AI at Scale AI. Previously I worked at Google Cloud AI and Google Brain as a senior manager, engineering leader and senior staff SWE. Earlier in my career, I was a tenured Computer Science professor at Vanderbilt University. My work and interests focus on

• LLM domain customization (fine-tuning tuning, distillation)
• Reliable and trustworthy evaluation of LLM and Agent
• Reinforcement learning for LLM and Agent
• LLM reasoning and planning
• Stochastic optimization for planning and decision-making under uncertainty

Recent Publications

• Judging with Confidence: Calibrating Autoraters to Preference Distributions
  Zhuohang Li, Xiaowei Li, Chengyu Huang, Guowang Li, Katayoon Goshvadi, Bo Dai, Dale Schuurmans, Paul Zhou, Hamid Palangi, Yiwen Song, Palash Goyal, Murat Kantarcioglu, Bradley A. Malin, Yuan Xue
  [Under submission 2025]

• Deep Researcher with Test-Time Diffusion
  Rujun Han, Yanfei Chen, Zoey CuiZhu, Lesly Miculicich, Guan Sun, Yuanjun Bi, Weiming Wen, Hui Wan, Chunfeng Wen, Solène Maître, George Lee, Vishy Tirumalashetty, Emily Xue, Zizhao Zhang, Salem Haykal, Burak Gokturk, Tomas Pfister, Chen-Yu Lee
  [Under submission 2025]

• Large Language Models can Learn Rules
  Zhaocheng Zhu, Yuan Xue, Xinyun Chen, Denny Zhou, Jian Tang, Dale Schuurmans, Hanjun Dai
  [2024]

• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
  Listed as Emily Xue, one of the 3,410 authors
  [2025]

• Gemini 1.5: Unlocking Multimodal Understanding Across Millions of Tokens of Context
  Listed as Emily Xue, one of the 1,037 authors
  [2024]

• Gemini: A Family of Highly Capable Multimodal Models
  Listed as Emily Xue, one of the 1250 authors
  [2023]

• [Stochastic Gradient Discrete Langevin Dynamics]
  Haoran Sun, Bethany Yixin Wang, Katayoon Goshvadi, Yuan Xue, Dale Schuurmans, Hanjun Dai
  [2023]

• Learning to Optimize with Stochastic Dominance Constraints
  Hanjun Dai, Yuan Xue, Niao He, Bethany Wang, Na Li, Dale Schuurmans, Bo Dai
  [AISTATS 2023]

• Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization
  Hanjun Dai, Mengjiao Yang, Yuan Xue, Dale Schuurmans, Bo Dai
  [ICML 2022]

• Neural Stochastic Dual Dynamic Programming
  Hanjun Dai*, Yuan Xue*, Zia Syed, Dale Schuurmans, Bo Dai
  [ICLR 2022] (* equal contribution)

• Learning to Select the Best Forecasting Tasks for Clinical Outcome Prediction
  Yuan Xue*, Nan Du*, Anne Mottram, Martin Seneviratne, Andrew M. Dai
  [NeurIPS 2020] (* equal contribution)

• Deep State-Space Generative Model For Correlated Time-to-Event Predictions
  Yuan Xue, Denny Zhou, Nan Du, Andrew M. Dai, Zhen Xu, Kun Zhang, Claire Cui
  [KDD 2020]

• Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer
  Edward Choi, Zhen Xu, Yujia Li, Michael W. Dusenberry, Gerardo Flores, Yuan (Emily) Xue, Andrew M. Dai
  [AAAI 2020]

• Multitask prediction of organ dysfunction in the intensive care unit using sequential subnetwork routing
  Diana Mincu, Subhrajit Roy, Eric Loreaux, Natalie Harris, Yuan Xue, Jessica Schrouff, Martin Seneviratne, Nenad Tomasev
  [J Am Med Inform Assoc 2021]

• Predicting inpatient medication orders from electronic health record data
  Kathryn Rough, Andrew M. Dai, Kun Zhang, Emily Xue, Laura M. Vardoulakis, Atul J. Butte, Claire Cui, Michael D. Howell, Alvin Rajkomar
  [Clinical Pharmacology and Therapeutics (2020)]

• BEDS-Bench: Behavior of EHR-models under Distributional Shift–A Benchmark
  Anand Avati, Martin Seneviratne, Emily Xue, Zhen Xu, Balaji Lakshminarayanan, Andrew M. Dai
  [2021]

• Thoracic Disease Identification and Localization with Limited Supervision
  Zhe Li, Chong Wang, Mei Han, Emily Xue, Wei Wei, Jia Li, Fei-Fei Li
  [CVPR 2018]

Google Scholar Page for publications at Vanderbilt

Talks

• Evaluating Large Language Models - Principles, Approaches, and Applications
  Bo Li, Irina Sigler, Yuan Xue
  [NeurIPS Tutorial 2024]

(last updated: Dec 2025)