LLM驱动的 A/H/美股智能分析器，多数据源行情 + 实时新闻 + Gemini 决策仪表盘 + 多渠道推送，零成本，纯白嫖，定时运行

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对…

😼 优雅地使用基于 clash/mihomo 的代理环境

[CVPR 2026] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

MTGS: Multi-Traversal Gaussian Splatting

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images

Physically-Plausible Image Signal Processing (PPISP) for Radiance Field Reconstruction

FlashInfer: Kernel Library for LLM Serving

一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂Vibe PPT＂; 支持上传任意模板图片；上传任意素材&智能解析；一句话/大纲/页面描述自动生成PPT；口头修改指定区域、一键导出可编辑ppt - An AI-native PPT generator based on nano banana pro🍌

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Official implementation of "ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation"

Visual Geometry Transformer for Autonomous Driving

[ASPLOS 2026] CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting with CPU Offloading

30天掌握量化交易 (持续更新)

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

Official code for "SRFormer: Permuted Self-Attention for Single Image Super-Resolution" (ICCV 2023) and SRFormerV2

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

ReSim: Reliable World Simulation for Autonomous Driving

CUDA Library Samples

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

Official implementation of 2D Triangle Splatting for Direct Differentiable Mesh Training

CUDA accelerated rasterization of gaussian splatting

An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.

Official implement of VGGT-Long

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold