implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
- yolov4
- scaled-yolov4
- yolov4-csp
- darknet
106,102 visible repositories in the index
721–744 of 1,781 · Most stars
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
DarkFly tool V.4.0
Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.
Enable seamless collaboration between Claude Code and Codex, transforming from a single agent to multiple agents for significantly enhanced productivity!
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs
A modern yet simple multi-platform video cutter and joiner.
Community maintained hardware plugin for vLLM on Apple Silicon
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
Nix User Repository: User contributed nix packages [maintainer=@Pandapip1]
A multi-instrument music transcription model developed by Kyutai and Mirelo.
Daijishō is a retro launcher that manages your retro games libraries. This repo is for assets and served as a main page.
Python module for handling audio metadata
[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
ClipCascade is a lightweight utility that automatically syncs the clipboard across devices, no key press required.
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
A Comprehensive Collection of Everything Related to Tradingview Pine Script.
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation (CVPR2026 Highlight)''
适用于AdGuard、Quantumult X、SmartDNS的去广告规则,合并优质上游规则并去重整理排列。
A collection of robotics simulation environments for reinforcement learning