bytedance

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.

Official Repo For Pixel-LLM Codebase: Sa2VA (Arxiv-25), SAMTok (CVPR-26), VRT, SaSaSa2VA (1-st solution for LSVOS)

SALMONN family: A suite of advanced multi-modal LLMs

KV cache store for distributed LLM inference

Awesome samples for Volcengine AgentKit Platform with VeADK.

Web-Bench is a benchmark designed to evaluate the performance of LLMs in actual Web development.

An acceleration library that supports arbitrary bit-width combinatorial quantization operations

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

Repo2Run is an LLM-based agent that automates environment configuration by generating error-free Dockerfiles for Python repositories.

video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates high-quality audio-visual video captions, which is developed by the Department of Electronic Engineering at Tsinghua University and ByteDance.

PatchEval: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities

Official repository for our paper "FullStack Bench: Evaluating LLMs as Full Stack Coders"

CausalMatch is a Bytedance research project aimed at integrating cutting-edge machine learning and econometrics methods to bring about automation in decision-making process.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra Topics: agent, agent-tars, browser-use, computer-use, cowork, gui-agent, gui-operator, mcp, mcp-server, multimodal, tars, ui-ta

ComfyUI Lumi Batcher is a batch processing extension plugin designed for ComfyUI, aiming to improve workflow debugging efficiency. Traditional debugging methods require adjusting parameters one by one, while this tool si

batchRun is an ansible-similar IT automation system, which is more suitable for IC industry.