"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

[NeurIPS'21] Projected GANs Converge Faster

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

A bridge to use Langchain output as an OpenAI-compatible API

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Efficient vision foundation models for high-resolution generation and perception.

This repo contains the code for 1D tokenizer and generator

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Official implementation of BLIP3o-Series

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Writing kubernetes controllers can be simple

End-to-end realtime stack for connecting humans and AI

Cutting Edge WebRTC Video Conferencing

[CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation

An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine

Windows inside a Docker container.

Official inference framework for 1-bit LLMs

High performance self-hosted photo and video management solution.

Vim-fork focused on extensibility and usability

Clean, modern, Python 3.6+ code generator & library for Protobuf 3 and async gRPC

Docker files and images to run Ceph in containers

Garnet is a remote cache-store from Microsoft Research that offers strong performance (throughput and latency), scalability, storage, recovery, cluster sharding, key migration, and replication feat…

[ECCV 2024] Official PyTorch implementation code for realizing the technical part of Mixture of All Intelligence (MoAI) to improve performance of numerous zero-shot vision language tasks.

The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.