GP-MoLFormer: Molecular Generation via Transformers
A 46.8M parameter transformer for molecular generation trained on 1.1B SMILES, introducing pair-tuning for efficient …
Generative-Models
A Convexity Principle for Interacting Gases
Introduces displacement interpolation to prove ground state uniqueness via optimal transport, establishing foundations …
Building Normalizing Flows with Stochastic Interpolants
A continuous-time normalizing flow using stochastic interpolants and quadratic loss to bypass costly ODE …
Flow Matching for Generative Modeling
A simulation-free framework for training Continuous Normalizing Flows using Conditional Flow Matching and Optimal …
Flow Straight and Fast
A unified ODE-based framework for generative modeling and domain transfer that learns straight paths for fast 1-step …
Score Matching and Denoising Autoencoders
Theoretical paper proving the equivalence between training Denoising Autoencoders and performing Score Matching on a …
Score-Based Generative Modeling with SDEs
Unified SDE framework for score-based generative models, introducing Predictor-Corrector samplers and achieving SOTA on …
DynamicFlow: Integrating Protein Dynamics into Drug Design
Flow matching model that co-generates ligands and flexible protein pockets, addressing rigid-receptor limitations in …
InvMSAFold: Fast & Diverse Inverse Folding
A fast, diverse inverse folding method combining deep learning with Potts models to capture full sequence landscapes.
MOFFlow: Flow Matching for MOF Structure Prediction
A Riemannian flow matching framework for generating Metal-Organic Framework structures by treating building blocks as …
Molecular String Renderer: Robust Visualization Tool
A robust, type-safe Python library for converting chemical strings (SMILES, SELFIES, InChI) into publication-quality …
Auto-Encoding Variational Bayes (VAE Paper Summary)
Summary of Kingma & Welling's foundational VAE paper introducing the reparameterization trick and variational …