About me

I’m a Research Scientist at Snowflake AI Research, where I train reasoning models and LLM agents, especially for structured data. Before that, I was a Research Scientist on ByteDance’s Seed-Foundation-Code team.

I earned my Ph.D. from the University of Illinois at Urbana-Champaign under Prof. Ruoyu Sun, with co-advising from Prof. Naira Hovakimyan. In my first year I collaborated with Prof. Justin Sirignano on deep-learning for computational fluid dynamics (CFD), and during my master’s studies I worked with Prof. Kyle Smith on numerical simulation for energy storage systems.

Research interests: Reasoning Models; Agent; Efficient Deep Learning; Natural Language Processing; Computer Vision; Numerical Methods.

Hiring: Snowflake AI Research is seeking research scientist interns for remote, long-term positions (3-6 months, part-time) starting August 2025. Projects include:

  • Post-training tool-augmented LLMs
  • Development of personalized Text-to-SQL models
  • Deep Research on structured data
  • Developing and training of data-science agents

If you are interested, don’t hesitate to send your resume to yite.wang@snowflake.com.

News

[Feb. 2026] Our paper DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science is accepted to ICLR 2026. [arXiv] [code]

[Feb. 2026] We released Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning on arXiv. [arXiv]

[Apr. 2025] I joined Snowflake AI Research, working on reasoning models and LLM agents.

[May. 2024] I joined ByteDance Seed-Foundation-Code as a Research Scientist working on LLM for code.

[Mar. 2024] I successfully defended my Ph.D. thesis.

[Jan. 2024] Our paper on model expansion was accepted to ICLR 2024.

[Oct. 2023] I received the NeurIPS 2023 Scholar Award.

[Sep. 2023] Our paper about dynamic sparse training for GANs was accepted to NeurIPS 2023.

[Jan. 2023] Our paper about foresight pruning was accepted to ICLR 2023.

[Mar. 2022] Our paper about neural architecture search for meta learning was accepted to CVPR 2022.

Publications

See the full publication list on the Publications page.