[CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"
- attention
- cvpr2023
- image-classification
- object-detection
140,194 visible repositories in the index
15,889–15,912 of 19,330 · Most stars
[CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"
An MCP Multimodal AI Agent with eyes and ears!
Python interface for the Firmata (http://firmata.org/) protocol. It is compliant with Firmata 2.1. Any help with updating to 2.2 is welcome. The Capability Query is implemented, but the Pin State Query feature not yet.
A Python wrapper around the NLPIR/ICTCLAS Chinese segmentation software.
AI short drama & micro-drama video generator — turns any idea into a complete short-form drama using multi-agent AI pipeline (screenwriter → storyboard → frames → video). Seedance 2 VIP, Kling 3.0 Pro, Veo 3.1, Sora 2.
A regular-expression based python MITM DNS server with support for DNS Rebinding attacks
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step (ACL'24)
This repository implements several swarm optimization algorithms and visualizes them. Implemented algorithms: Particle Swarm Optimization (PSO), Firefly Algorithm (FA), Cuckoo Search (CS), Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), Grey Wolf Optimizer (GWO) and Whale Optimization Algorithm (WOA)
[NeurIPS 2021] LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
[CVPR 2025] Multiple Object Tracking as ID Prediction
Yuan 1.0 Large pretrained LM
Personal-Model First Self Evolving AI Agent 🐘
A graph-based functional API for building complex scikit-learn pipelines.
ESIM for Multi-turn Response Selection Task
Python core of avatar²
Minimal Jupyter C kernel
Access your Taskwarrior tasks from any browser anywhere
Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using Tensorflow)
huggingface mirror download
Official Python toolkit for generic object tracking benchmark GOT-10k and beyond
用PaddlePaddle和Tensorflow实现常用的深度学习算法
The fastest digital human algorithm, now on your desktop.