[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

《EasyOffer》（<大模型面经合集>）是针对LLM宝宝们量身打造的大模型暑期实习Offer指南，主要记录大模型暑期实习和秋招准备的一些常见大厂手撕代码、大厂面经经验、常见大厂思考题等；小白一个，正在学习ing......有问题各位大佬随时指正，希望大家都能拿到心仪Offer！

Official PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles" (Slow Fast Sampling).

Modern Android music player built with Material 3 and powered by Media3, offering rich features and a smooth listening experience.

Android music player framework, compatible with MediaSession. Support custom music player (MediaPlayer, ExoPlayer), custom Notification, custom audio effect engine, only WiFi network, sound quality…

Material You music player for android

Music search, downloader & player app using Jetpack Compose

From UI Proposal to Code 🎶▶️

Dream 7B, a large diffusion language model

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

The official Meta Llama 3 GitHub site

A framework for few-shot evaluation of language models.

Official PyTorch implementation for "Large Language Diffusion Models"

The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024

An Efficient Text-to-Image Generation Pretrain Pipeline

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Efficient controlnet for DiTs

VideoSys: An easy and efficient system for video generation

《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version in translation

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉

Open-Sora: Democratizing Efficient Video Production for All

This repo contains the code for 1D tokenizer and generator

Magnificent app which corrects your previous console command.

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

CSU - CS期末备考复习资料；中南大学计科&计算机复习; Review material; Central South University