Open-source alternatives to DDPD

By Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin Chiu, Volodymyr Kuleshov

This repo contains a PyTorch implementation for the paper Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution by Aaron Lou, Chenlin Meng and Stefano Ermon.

Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models

Efficiency: DPad-enhanced dLLMs achieve up to a 61.39× speedup over vanilla dLLM baselines. Accuracy: DPad-enhanced dLLMs achieve up to a +26.46% improvement over vanilla dLLM baselines. (Evaluation conducted on NVIDIA A100-PCIe-80GB GPUs).

This thesis aimstoinvestigate thepotential of discrete diffusion models in the context ofnaturallanguagegeneration.

](https://huggingface.co/Dream-org/DreamOn-v0-7B)

By Dimitri von Rütte, Janis Fluri, Yuhui Ding, Antonio Orvieto, Bernhard Schölkopf, Thomas Hofmann

Constrained Decoding of Diffusion LLMs with Context-Free Grammars

Dream-Coder 7B is a diffusion LLM for code trained exclusively on open-source data across its development stages—adaptation, supervised fine-tuning, and reinforcement learning. It achieves an impressive 21.4% pass@1 on LiveCodeBench (2410-2505), outperforming other open-source diffusion LLMs by…

Official repository for the paper: Accelerating Diffusion LLMs via Adaptive Parallel Decoding

Code accompanying the paper "Layer Collapse in Diffusion Language Models" by Alexander Conzelmann, Albert Catalan-Tatjer, and Shiwei Liu (Tübingen AI Center / MPI for Intelligent Systems / ELLIS Institute Tübingen). Link: https://arxiv.org/abs/2605.06366

This is the official implementation of Pix2Seq in Tensorflow 2 with efficient TPUs/GPUs support. The original Pix2Seq code aims to be a general framework that turns RGB pixels into semantically meaningful sequences. We now extend it to be a generic codebase, with task-centric organization that…

Current Diffusion Language Models (DLMs) have been studied at a smaller scale compared to their autoregressive (AR) counterparts and lack fair comparison on language modeling benchmarks. Additionally, training diffusion models from scratch at scale remains challenging. We propose adapting…

This repository contains code for training and evaluating the models in the paper Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning.

](https://huggingface.co/Dream-org/Dream-v0-Base-7B)

This repository contains the official implementation of paper A Reparameterized Discrete Diffusion Model for Text Generation.

The pipeline of dKV-Cache

Official implementation of DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models.

This repository contains code for training and evaluating the models in the paper Likelihood-Based Diffusion Language Models.

https://github.com/user-attachments/assets/09c67a58-b425-463d-a998-c1a6049bc171

dInfer is an efficient and extensible inference framework for dLLMs. As illustrated in the following architecture, it modularizes inference into four components: model, diffusion iteration manager, decoder and KV-cache manager. It provides well-designed APIs for flexible algorithms combinations…

SparseD is a novel sparse attention method for diffusion language models (DLMs), delivering near lossless acceleration in performance. It uses full attention and computes sparse patterns during early denoising steps, then reuses these patterns in later steps to restrict computation and improve…

This repository serves as a comprehensive research platform and toolkit for advancing machine learning, quantum computing, and large-scale scientific data analysis. It provides foundational frameworks for developing complex algorithmic systems, offering the necessary infrastructure for distributed training, computational graph execution, and high-performance model development. The project distinguishes itself by integrating specialized research domains with robust, privacy-preserving methodologies. It supports diverse scientific discovery through tools for quantum simulation, physics-informed