GigaBrain-0: A World Model-Powered Vision-Language-Action Model

Personal Website with Obsidian-like knowledge graph

iBKH: The integrative Biomedical Knowledge Hub

TVM Documentation in Chinese Simplified / TVM 中文文档

[NeurIPS2025 spotlight★] Official implementation for "RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation".

GigaModels: A Comprehensive Repository and Platform for Multi-modal, Generative, and Perceptual Models

🌐 WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

🔥minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,矿池抽水,矿池中转,矿场运维专用

HunyuanVideo-1.5: A leading lightweight video generation model

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

Query-aware Token Selector (QTSplus), a lightweight yet powerful visual token selection module that serves as an information gate between the vision encoder and LLMs.

GigaTrain: An Efficient and Scalable Training Framework for AI Models

[PVLDB 2024 Best Paper Nomination] TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods

SAG - SQL驱动的RAG引擎 · 查询时自动构建知识图谱 | SQL-Driven RAG Engine · Automatically Build Knowledge Graph During Querying

The Intelligent GUI Agent for Mobile Phones

PageEyes Agent 是一个轻量级 UI Agent，通过自然语言指令驱动，无需编写脚本既可实现Web、Android平台的UI自动化任务。

INFTY Engine: An Optimization Toolkit to Support Continual AI

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

A blueprint for building production-ready RAG systems that minimize hallucination, featuring switchable 3-step (Speed) and 4-step (Precision) pipelines.

🤖 A comprehensive task management system specifically designed for AI assistants. Supports project management, task tracking, team collaboration, and seamless AI integration through MCP (Model Cont…

Joint Semantic Detection and Dissemination Control of Phishing Attacks on Social Media via LLama- Based Modeling

Enables YOLOv5 object detection through ROS topics

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

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

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

Go bindings for the CUDA Driver and Runtime APIs, cuBLAS, and cuDNN.