Open-source alternatives to S Sahoo Duo

Lingbot-world is an interactive world simulator and framework for generating high-fidelity video environments from text and image prompts. It functions as a video generation system designed to create controllable simulations for applications such as robotics learning and gaming. The project includes a video motion controller that directs camera and object movement using transformation matrices and action strings. It utilizes a quantized inference engine to reduce memory usage and accelerate the generation of video sequences. The system covers a range of optimization techniques, including fou

Sana is a framework for high-resolution image and video synthesis based on a linear diffusion transformer. It provides a toolkit for the training, fine-tuning, and execution of text-to-image and text-to-video models, as well as a video generative world model capable of simulating physical environments with precise spatial control. The project is distinguished by its use of linear complexity layers to handle high resolutions and its support for long-form, minute-length video generation in real time. It implements a two-stage inference paradigm that separates structural generation from visual t

DMax is a new dLLM paradigm achieving aggressive parallel decoding while preserving generation quality.

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

Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

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

Constrained Decoding of Diffusion LLMs with Context-Free Grammars

dVoting: Fast Voting for dLLMs

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

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…

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).

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

We introduce SDAR (Synergy of Diffusion and AutoRegression), a large-scale diffusion language model that unites the complementary strengths of autoregressive and discrete diffusion modeling. By merging the training efficiency of autoregressive methods with the highly parallel decoding ability of…

MaskKV: Fine-Grained Cache Eviction for Efficient dLLM Inference

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