Chrome DevTools for coding agents

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Fast and memory-efficient exact attention

[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Official inference framework for 1-bit LLMs

Production-ready platform for agentic workflow development.

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, e…

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Ongoing research training transformer models at scale

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

Post-training with Tinker

A large-scale benchmark for machine learning methods in fluid dynamics

Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

Learn OpenCV : C++ and Python Examples

This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three …

A generative speech model for daily dialogue.

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Official code for TimeCraft: A Time Series Generation Framework for Real-World Applications

TSGBench: Time Series Generation Benchmark (VLDB'24)

A professional list on Large (Language) Models and Foundation Models (LLM, LM, FM) for Time Series, Spatiotemporal, and Event Data.

Large Language & Foundation Models for Time Series.

verl: Volcano Engine Reinforcement Learning for LLMs

Filtered - PCMCI (F-PCMCI) causal discovery algorithm. Extension of the PCMCI causal discovery algorithm augmented with a feature selection method.

Causal Neural Nerwork

[NeurIPS 2024] Codebase for PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs.

The code Implementation of the paper “KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks".