Yufeng Wang

Reinforcement LearningLLM Post-trainingWorld ModelsAI Agents

Academia

  1. 2023 — 2026

    Ph.D. All but dissertation, Computer Science

    Stony Brook University

    Advised by Prof. Haibin Ling

  2. 2022 — 2023

    Research Assistant

    Stanford University

    AI in Medicine & Imaging

  3. 2019 — 2023

    B.S., Physics

    University of Science and Technology of China

    Quantum Computing

Industry

  1. 2026 May. — 2026 Aug.

    AI Engineer Intern

    Rivian and Volkswagen Group Technologies

    Language Model · Agentic AI

  2. 2025 Aug. — 2026 Mar.

    Research Intern

    Sony AI

    Agentic AI · ML Infra · Edge inference

Research

  1. Terminal-Bench-Science · 2026 · Contributor

    EXAFS Shell Recovery in Fe–N–C Catalysts

    A materials-science task for AI agents: calibrate, select and fit coordination shells from X-ray absorption spectra, with uncertainties. The verifier is calibrated against 83 solution strategies.

  2. Nature Medicine · 2024

    Screening and Diagnosis of Cardiovascular Disease Using AI-Enabled Cardiac Magnetic Resonance Imaging

    Two-stage, video-based deep learning that screens for and diagnoses 11 types of cardiovascular disease from cardiac MRI in 9,719 patients, reaching AUCs near 0.99 and outperforming cardiologists on pulmonary arterial hypertension.

  3. Physical Review B · 2025

    Variational Transformer Density Operator Ansatz for Steady States of Dissipative Quantum Systems

    A transformer density-operator ansatz for the steady states of dissipative quantum many-body systems, accurately predicting the mixed steady states of dissipative Ising and Heisenberg spin chains.

  4. NeurIPS · 2026

    BuresTomFlow: Bures-Geometric Flow Matching for Posterior Quantum Tomography

    Flow matching on the Bures geometry of density matrices, giving fast, amortized posterior samples for Bayesian quantum state tomography.

  5. TMLR · 2026

    Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG

    A training-free gate that decides when to retrieve from the uncertainty of a short draft answer, matching or beating always-on RAG on five QA benchmarks while retrieving 70–90% less.

  6. TMLR · 2026

    Sample-Based Constrained Inference for Matrix-Free Quantum Process Tomography

    A matrix-free reconstruction-and-sampling framework for quantum process tomography whose sampled channels are physically valid (CPTP) by construction, without forming the dense Choi design matrix.

  7. Journal of Cheminformatics · 2026

    How Well Can Off-the-Shelf LLMs Elucidate Molecular Structures from Mass Spectra Using Chain-of-Thought Reasoning?

    A zero-shot chain-of-thought benchmark on MassSpecGym, 231K spectra across four frontier LLMs, that turns a negative result into a training agenda.

  8. arXiv · 2025

    Spectra-to-Structure and Structure-to-Spectra Inference Across the Periodic Table

    XAStruct, trained on X-ray absorption spectra from over 70 elements, predicts spectra from crystal structures and infers local structure from spectra, including the first model to predict neighbor atom types.

All publications on Google Scholar

Service & Awards

Awards

  • Gold Reviewer Award ICML
  • Top Reviewer Award NeurIPS

Reviewer

  • ICML
  • NeurIPS
  • ICLR
  • AAAI
  • IEEE
  • ACL-ARR
  • ACM-Health
  • Journal of Real-Time Image Processing