Amortized Probabilistic Conditioning for Optimization, Simulation and Inference (Chang et al., AISTATS 2025)

Research code for the paper "CFMI: Flow Matching for Missing Data Imputation".

Periodic Materials Generation using Text-Guided Joint Diffusion Model (ICLR 2025)

Official code repository of < CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph >

Combination of transformers and diffusion models for flexible all-in-one simulation-based inference

Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

Source code for Equivariant Flow Matching for Molecular Conformer Generation

An open-source toolbox for fast sampling of diffusion models. Official implementations for our [CVPR-2024, ICML-2024] papers

Simulation-based inference toolkit

A Type-1 Diabetes simulator implemented in Python for Reinforcement Learning purpose

⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

[NeurIPS 2023] The implementation for the paper "Crystal Structure Prediction by Joint Equivariant Diffusion"

Official repo for consistency models.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Official code for ICCV 2023 paper: "Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation".

Unofficial minimal implementation of consistency models (CM) proposed by Song et al. 2023 on a 1D toy task in pytorch

Inherently Interpretable Time Series Classification via Multiple Instance Learning (MILLET)

Official code for Accelerating Diffusion Sampling with Optimized Time Steps (CVPR 2024)

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.

Template for EPFL (BSc, MSc, or doctoral) theses and semester projects

Learning Robust Statistics for Simulation-Based Inference Under Model Misspecification (Huang et al., Neurips 2023)

⚡ Building applications with LLMs through composability ⚡