A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Official Code for “Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling” ICLR 2026

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

🦞 Production-grade AI Agent design system — 龙虾教练：产品级 AI Agent 设计体系

React component library on Radix Primitives. Install packages on demand; use with theme or headless.

Agent behavior that compiles.

🚀 基于 HIP 的 ONNX 算子异构优化与评估框架，支持自定义 Kernel 注入。内置完整精度验证机制。 | A high-performance HIP-based ONNX operator optimization and benchmarking framework with built-in precision validation. | 我的先导杯国赛onnx题目在此完成

An Optimizing Framework on MLIR for Efficient FPGA-based Accelerator Generation

Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.

[EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking

Fat-Cat: A document-centric context management Agent. Making context as simple as reading chat history.

A self-evolving, bootstrapped bot powered by Codex

Capture what you want with LLM

Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.

Ubuntu environment simulator for Portfolio built with Angular 19

openclaw小龙虾机器人：openclaw中文版！接入国产生态：钉钉、QQ、微信、国产大模型！你专属的个人AI助手。任何操作系统，任何平台。龙虾的方式!

GigaTrain: An Efficient and Scalable Training Framework for AI Models

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…

Translate PDF, Word, PowerPoint, etc. | zotero翻译插件，微信扫码注册，新用户可免费翻译25万汉字或100万个英文字母。超能文献官网:suppr.wilddata.cn；

A cross-platform instant messaging client application built with Tauri and Vue 3, featuring one-to-one chat, group chat, file transfer, audio/video calling, screen recording, screenshot capture, an…

GigaWorld-0: World Models as Data Engine to Empower Embodied AI

HunyuanVideo-1.5: A leading lightweight video generation model

正方教务系统自动抢课脚本：并发抢课、时间/教师筛选、换课、定时执行，内置图形界面。 | Auto course grabber with concurrent enrollment, filtering & scheduling.

iBKH: The integrative Biomedical Knowledge Hub

[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

Official code of Motus: A Unified Latent Action World Model

LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer, ICLR 2026

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

the Propeller calculation and optimization by a Surrogate model