Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.
Parse human names into title, given, middle, family, suffix, nickname and maiden name. Typed, zero-dependency, CJK-aware.
- python
- text-processing
- text-parser
- python-module
Inspect, visualize and intervene on any operation in any neural network. Capture every activation and gradient, the full computational graph and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle and tinygrad. Validated on 6400+ models. Built for researchers and their AI agents.
Cross-platform desktop GUI for music source separation
A Lite Bert For Self-Supervised Learning Language Representations
reFrame is an experimental camera with a color ePaper display. Designed to capture and display one photo at a time, making every frame deliberate and memorable.
[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021
- pedestrian-detection
- autonomous-driving
- citypersons
- caltech
A standalone python script which utilizes python's built-in modules to enumerate SUID binaries, separate default binaries from custom binaries, cross-match those with bins in GTFO Bin's repository & auto-exploit those, all with colors! ( ͡~ ͜ʖ ͡°)
- python
- python-3
- gtfo-bin
- auto-exploitation
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.
One-time password library for HMAC-based (HOTP) and time-based (TOTP) passwords
Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle
🚀🚀🚀 YOLO series of PaddlePaddle implementation, PP-YOLOE+, RT-DETR, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv10, YOLO11, YOLOX, YOLOv5u, YOLOv7u, YOLOv6Lite, RTMDet and so on. 🚀🚀🚀
- ppyolo
- ppyoloe
- yolov5
- yolov6
TranslatedLet AI Agents such as Codex and Claude Code become your cross-platform computer repair assistant: 64 on-demand Playbooks covering diagnostics, cleanup, performance, network and security maintenance. You can directly ask about a full C drive, a sluggish computer, rogue software, application migration, and data recovery. It gathers evidence first, then makes a plan, and makes changes only after confirmation.
Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱
refugiOS es un sistema operativo portátil diseñado para situaciones de emergencia, falta de conectividad a Internet o necesidad extrema de privacidad
- digital-resilience
- digital-resistance
- emergency
- emergency-preparedness
Wav2Lip version 288 and pipeline to train
A tool to bypass Minecraft Java Edition model limits by baking vertex data into texture.
Books and other resources
Current development of SSLyze now takes place on a separate repository
A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.
[ECCV 2026] VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
An enhanced Wan2.2 Image-to-Video node specifically designed to fix the slow-motion issue in 4-step LoRAs (like lightx2v).
A Comprehensive Reinforcement Learning Zoo for Simple Usage 🚀
in preparation...