🎨 A smart universal color management system for Python visualization.

NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation

🧠 Prometheus: A Knowledge-Graph-Driven 🤖 AI Agent that maps 🗺, understands 🧩, and repairs 🛠 complex codebases — not by guessing, but by reasoning. ⚡

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

[NeurIPS 2025] More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models

[NeurIPS 25 @ ER] Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs

AIPPT Online editor，Base On ChatPPT， supports document editing services throughout the entire process, including import, export, layout beautification, online editing, playback, and presentation an…

An efficient storage and compute engine for both on-prem and cloud-native data analytics.

A golang goroutine pool with high-performance and elegance

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.

Official codebase for "Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens" (NerIPS 2025).

对传统rag的改造，让大模型像专业研究员一样读懂厚重的基础设施公募Reits招募说明书，精准定位证据并复核答案。

INFTY Engine: An Optimization Toolkit to Support Continual AI

JittorGeometric is a Jittor-based graph machine learning library.

Enterprise Security Data Pipeline Platform (SDPP) with Integrated Real-Time Threat Detection Engine

"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

A curated collection of AI+X papers published in Nature / Science / Cell / Lancet / Radiology and their flagship sub-journals

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

A pytorch implementation of the paper "TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree".

Official repo for the paper "Multimodal Phased Transformer for Sentiment Analysis".