Highlights
- Pro
Stars
LaTeX class and template for Marie Skłodowska-Curie Actions Postdoctoral Fellow (MSCA-PF) grant applications
😼 优雅地使用基于 clash/mihomo 的代理环境
Cross-Layer Injection (CLI): a dynamic many-to-many bridge between vision encoder layers and LLM decoder layers for deep vision-language fusion. ECCV 2026.
张雪峰.skill — 张雪峰的认知操作系统。高考志愿/考研/职业规划的实战思维框架。由女娲.skill生成。
SGLang is a high-performance serving framework for large language models and multimodal models.
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
[ICCV 2025] Official Implementation of Federated Continual Instruction Tuning
[CVPR 2025] CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
一个基于 Python Telegram Bot 的自动化认证工具，能够自动完成 SheerID 平台的学生/教师身份验证流程。
High-fidelity world models for general embodied intelligence, such as data engines and world simulators.
TPAMI 2026 | This repository collects awesome survey, resource, and paper for lifelong learning LLM agents
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
TaoSync是一个适用于OpenList v3+的自动化同步工具/Sync for OpenList/AList
An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.
An Alpine Linux container for the iCloud Photos Downloader command line utility
ATM-Bench: A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data (images, videos, emails). Features referential queries, evidence-grounded answering, and multi-sourc…
Xbox Download Assistant (Xbox下载助手) — Supports download acceleration for Xbox, Microsoft Store, PlayStation, Nintendo Switch, EA App, Battle.net, Epic Games, Ubisoft Connect, Riot Games, and Rocksta…
Open Images is a dataset of ~9 million images that have been annotated with image-level labels and bounding boxes spanning thousands of classes.
State-of-the-art 2D and 3D Face Analysis Project
[Neurips 2025'] VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping
An arbitrary face-swapping framework on images and videos with one single trained model!
Convert PDF to markdown + JSON quickly with high accuracy
🎥 Python and OpenCV-based scene cut/transition detection program & library.
BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.