Stars
Implementation of "Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models" [NeurIPS 2025]
Minimalist RL for Diffusion LLMs with SOTA reasoning performance (89.1% GSM8K). Official implementation of "The Flexibility Trap".
dUltra: Ultra-Fast Diffusion Large Language Models via Reinforcement Learning
[ICLR 2026] dParallel: Learnable Parallel Decoding for dLLMs
[ICLR 2026] Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
Unofficial implementation of the toy example in JiT https://arxiv.org/abs/2511.13720
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Pytorch implementation for MeanFlow
Post-training with Tinker
A research project exploring fine-tuning BERT-style models for text generation
[ICLR 2026] Discrete Diffusion Divergence Instruct (DiDi-Instruct)
Offical implementation of our paper "Exploring the Potential of Diffusion Large Language Models in Code Generation".
The official repository for the paper "Optimal Flow Matching: Learning Straight Trajectories in Just One Step" (NeurIPS 2024)
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The official implementation of "Optimal Stochastic Trace Estimation in Generative Modeling (AISTATS 2025)"
Exploring Applications of GRPO
A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.
Open-Sora: Democratizing Efficient Video Production for All
Fully open reproduction of DeepSeek-R1
Official PyTorch implementation for "Large Language Diffusion Models"
Our library for RL environments + evals
Pytorch implementation of Deep Hedging, Utility Maximization and Portfolio Optimization