Predicting the generation FID of latent diffusion, with a variant of reconstruction FID of Variational Auto-encoder.

[CVPR2026 Highlight] Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens https://arxiv.org/abs/2603.19232

The first multiplayer video world model in Minecraft

Official repo for UAE

CVPR 2026 (Highlight)-Guiding a Diffusion Transformer with the Internal Dynamics of Itself (IG)

Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

A comprehensive JAX/NNX library for diffusion and flow matching generative algorithms, featuring DiT (Diffusion Transformer) and its variants as the primary backbone with support for ImageNet train…

健康学习到150岁 - 人体系统调优不完全指南

Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).

Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning

[CVPR 2026] DDT: Decoupled Diffusion Transformer

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

Karras et al. (2022) diffusion models for PyTorch

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

This is a list of peer-reviewed representative papers on deep learning dynamics (optimization dynamics of neural networks). The success of deep learning attributes to both network architecture and …

Meaningful titles for tabs and PDF downloads! Also supports tab search.

Taming Transformers for High-Resolution Image Synthesis

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

Collection of advice for prospective and current PhD students

An open-source tool-augmented conversational language model from Fudan University

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

Covert ANTLR4 book source code to Python3 version.