Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy
cs.LG, cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/QDKStorm/ProFiT
Terminology
Sources
- Diffusion Autoencoders are Scalable Image Tokenizers
- Adaptive Protein Tokenization
- Learning the Language of Protein Structure
- EigenFold: Generative Protein Structure Prediction with Diffusion Models
- Flow Matching for Generative Modeling
- Pseudo Numerical Methods for Diffusion Models on Manifolds
- Rectified Flow: A Marginal Preserving Approach to Optimal Transport
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- Protein Structure Tokenization: Benchmarking and New Recipe
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks