tbonnair / Why-Diffusion-Models-Don-t-MemorizeLinks
This repository contains code for the paper "Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training" by T. Bonnaire, R. Urfin, G. Biroli and M. Mézard.
☆31Updated 3 weeks ago
Alternatives and similar repositories for Why-Diffusion-Models-Don-t-Memorize
Users that are interested in Why-Diffusion-Models-Don-t-Memorize are comparing it to the libraries listed below
Sorting:
- ☆36Updated 7 months ago
- Official implementation for Diffusion Alignment as Sampling (DAS), ICLR'25, Spotlight☆55Updated 10 months ago
- Official PyTorch implementation for "Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data" (ICLR…☆72Updated 6 months ago
- Code for TFG: Unified Training-Free Guidance for Diffusion Models☆72Updated last month
- [NeurIPS 2025] Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".☆94Updated last month
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆200Updated 5 months ago
- [ICML 2024] Compositional Image Decomposition with Diffusion Models☆51Updated last year
- Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"☆193Updated 6 months ago
- Official implementation of Learning to Discretize Denoising Diffusion ODEs☆31Updated 7 months ago
- Simple Guidance Mechanisms for Discrete Diffusion Models☆64Updated last year
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆57Updated 6 months ago
- Pytorch implementation for MeanFlow☆272Updated 4 months ago
- ☆51Updated last year
- Unofficial implementation of "SODA: Bottleneck Diffusion Models for Representation Learning"☆96Updated last year
- Interpretable Diffusion Via Information Decomposition☆30Updated last year
- The collection of awesome papers on alignment of diffusion models.☆381Updated last month
- Official implement of paper "Revisiting Multimodal Positional Encoding in Vision–Language Models"☆42Updated last week
- [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think☆225Updated 2 months ago
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆127Updated last year
- Official PyTorch implementation for "Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels"☆96Updated last year
- Official Code Repository for the paper "Continuous Diffusion Model for Language Modeling" (NeurIPS 2025).☆52Updated 2 months ago
- The official PyTorch implementation of Manifold Preserving Guided Diffusion (MPGD)☆38Updated last year
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"☆160Updated 10 months ago
- ☆55Updated 6 months ago
- The official implementation of "[MASK] is All You Need"☆125Updated 4 months ago
- (ICCV 2025) "Principal Components" Enable A New Language of Images☆75Updated 4 months ago
- ☆87Updated 4 months ago
- Generative Universal Verifier as Multimodal Meta-Reasoner☆42Updated last month
- [Neurips 2023] Official pytorch implementation of "Addressing Negative Transfer in Diffusion Models"☆23Updated last year
- ☆106Updated last year