-
Tsinghua University
- No. 30 Shuangqing Road, Haidian District, Beijing 100084, P.R. China.
-
10:40
(UTC +08:00)
Highlights
Stars
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
HunyuanVideo-1.5: A leading lightweight video generation model
SimpleMem: Efficient Lifelong Memory for LLM Agents
Collection of common code that's shared among different research projects in FAIR computer vision team.
Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project
State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.
Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".
An Open-source Toolkit for Deep Learning based Recommendation with Tensorflow.
Skill Compose is an open-source agent builder and runtime platform for skill-powered agents. No workflow graphs. No CLI.
[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
Uni-MoE: Lychee's Large Multimodal Model Family.
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"
Deep Reinforcement Learning with pytorch & visdom
⚡ 需求分析效率提升 200%!全球首个为 AI 编程时代设计的团队协作 MCP 服务器,自动分析需求自动编写前后端代码,下载切图
Dynamic MBTI Personality Simulation for LLM Agents via Carl Jung's Theory. A framework that enables LLM agents' MBTI personalities to naturally evolve and grow through interaction.
7/24 Office — Self-evolving AI Agent system. 26 tools, 3500 lines pure Python, MCP/Skill plugins, three-layer memory, self-repair, 24/7 production.
SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation
This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaof…
[ICCV2025 Highlight] Stereo Any Video: Temporally Consistent Stereo Matching
Agentic Generative Engine Optimizaiton
AI-powered programmatic advertising infrastructure for U.S. SMBs
OmniClaw is the execution layer for AI-native payments. It sits between raw wallet infrastructure and production payment flows so AI agents and AI-powered apps can move money with better safety, tr…
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, bet…
EvoCorps:面向网络舆论去极化的进化式多 Agent 框架,在传播过程中主动介入,协同降温情绪、对抗极端化、推动理性讨论。