ML Group @ RUC ORG

Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"

Official PyTorch implementation for "Large Language Diffusion Models"

Official PyTorch implementation for "FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis".

[NeurIPS 2025] Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".

No description.

No description.

Official implementation for "EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations" (NIPS 2022)

A Collection of Papers on Diffusion Language Models

Official implementation of "MicroDreamer: Zero-shot 3D Generation in ~20 Seconds by Score-based Iterative Reconstruction".

Official PyTorch implementation for ICLR2024 paper "The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing"

Official PyTorch implementation for "Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels"

Official PyTorch implementation for "Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data" (ICLR 2025)

Concat-ID: Towards Universal Identity-Preserving Video Synthesis

[ICLR 2026] Official PyTorch implementation for "ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding"

No description.

Official PyTorch implementation for "Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations"

Official PyTorch implementation for "Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective"

Official PyTorch implementation for "Effective and Efficient Masked Image Generation Models"

[NeurIPS 2023] Official implementation for our paper "Toward Understanding Generative Data Augmentation".

No description.

Official implementation for "Revisiting Discriminative vs. Generative Classifiers: Theory and Implications".

Official implementation for our paper "Spectral Condition for μP under Width–Depth Scaling".

[NeurIPS 2024] Official implementation for our paper "On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability".

A collection of some large model papers.

Official PyTorch implementation for "A Theory for Conditional Generative Modeling on Multiple Data Sources"

No description.

Project page for paper "large language diffusion models"

No description.

The Demo page of LLaDA 1.5.

No description.

No description.

No description.

Reg-ADA - Official PyTorch implementation of DEEP GENERATIVE MODELING ON LIMITED DATA WITH REGULARIZATION BY NONTRANSFERABLE PRE-TRAINED MODELS, ICLR 2023.

Reg-ADA-APA - Official PyTorch implementation