Skip to content
@AI4Science-WestlakeU

AI for Scientific Simulation and Discovery Lab

Our lab's research solves the core and universal problems at the intersection of AI and science
README.md

AI for Scientific Simulation and Discovery Lab

Our research group at Westlake University (西湖大学) carries out long-term work on core and universal problems for AI + Science:

  • Core AI: Develop generative AI methods based on diffusion/flow matching and next-generation generative models; create self-evolving AI architectures. Develop generalist AI scientists and AI engineers.
  • AI for Physical Sciences: Develop novel generative AI approaches for scientific simulation, control, design, and scientific discovery in complex physical systems such as fluids and plasmas.
  • AI for Life Science: Develop AI virtual cells and decode the evolutionary mechanisms and intrinsic logic of living systems.

Group website: ai4s.lab.westlake.edu.cn
Group Leader website: tailin.org

Popular repositories Loading

  1. RealPDEBench RealPDEBench Public

    [🔥ICLR26 Oral] RealPDEBench: A Benchmark for Complex Physical Systems with Paired Real-World and Simulated Data

    Python 129 17

  2. flow_guidance flow_guidance Public

    [ICML 2025] The official implementation of the paper "On the Guidance of Flow Matching"

    Python 109 10

  3. BuildArena BuildArena Public

    [ICML 2026] BuildArena, where LLM agents design, build, and test rockets, cars, and bridges in a physics simulator given a goal-directed sentence.

    Python 107 6

  4. wdno wdno Public

    [ICLR 2025] Wavelet Diffusion Neural Operator (WDNO) uses diffusion models on wavelet space for generative PDE simulation and control.

    Python 67 2

  5. scDFM scDFM Public

    [ICLR 2026] scDFM: Distributional Flow Matching for Robust Single-Cell Perturbation Prediction

    Python 63 8

  6. research_toolbox research_toolbox Public

    A useful toolbox for research.

    55 3

Repositories

Showing 10 of 29 repositories
  • feature-information-dynamics Public

    [NeurIPS 2026] Official PyTorch implementation of Feature Information Dynamics in Diffusion.

    AI4Science-WestlakeU/feature-information-dynamics's past year of commit activity
    Python 2 MIT 0 0 0 Updated Oct 8, 2026
  • BuildArena Public

    [ICML 2026] BuildArena, where LLM agents design, build, and test rockets, cars, and bridges in a physics simulator given a goal-directed sentence.

    AI4Science-WestlakeU/BuildArena's past year of commit activity
    Python 107 6 0 0 Updated Oct 3, 2026
  • .github Public
    AI4Science-WestlakeU/.github's past year of commit activity
    0 0 0 0 Updated Oct 2, 2026
  • beno Public

    [ICLR 2024] A boundary-embedded neural operator that incorporates complex boundary shape and inhomogeneous boundary values

    AI4Science-WestlakeU/beno's past year of commit activity
    Python 34 MIT 2 1 0 Updated Oct 2, 2026
  • GGBall Public

    [ICLR 2026] The first graph generation framework built upon the Poincaré Ball model of hyperbolic space

    AI4Science-WestlakeU/GGBall's past year of commit activity
    Python 9 MIT 6 0 0 Updated Oct 2, 2026
  • VFScale Public

    [ICLR 2026] VFScale: First Verifier-free Test-time Scalable Diffusion Model for Intrinsic Reasoning.

    AI4Science-WestlakeU/VFScale's past year of commit activity
    Python 6 MIT 0 1 0 Updated Oct 2, 2026
  • t_scend Public

    This repo is the code for T-SCEND, a novel framework that significantly improves diffusion model’s reasoning capabilities with better energy-based training and scaling up test-time computation.

    AI4Science-WestlakeU/t_scend's past year of commit activity
    Python 26 MIT 1 0 0 Updated Oct 2, 2026
  • GenCP Public

    [ICLR 2026] GenCP: Towards Generative Modeling Paradigm of Coupled physics

    AI4Science-WestlakeU/GenCP's past year of commit activity
    Python 24 3 0 0 Updated Oct 2, 2026
  • PACE Public

    [NeurIPS 2026] PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference

    AI4Science-WestlakeU/PACE's past year of commit activity
    Python 5 MIT 1 1 0 Updated Sep 29, 2026
  • scDFM Public

    [ICLR 2026] scDFM: Distributional Flow Matching for Robust Single-Cell Perturbation Prediction

    AI4Science-WestlakeU/scDFM's past year of commit activity
    Python 63 MIT 8 6 0 Updated Sep 28, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.