Popular GitHub Repositories for Rotary Position Encoding

? Scalable embedding, reasoning, ranking for images and sentences with CLIP

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework

Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition

Data augmentation for NLP, presented at EMNLP 2019

MLBox is a powerful Automated Machine Learning python library.

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

Natural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need

Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025)

Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.

A comprehensive code for AI & Robotics.

Cameras as Relative Positional Encoding

FFmate is a modern and powerful automation layer built on top of FFmpeg - designed to make video and audio transcoding simpler, smarter, and easier to integrate

[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

PyTorch implementation of the position-aware attention model for relation extraction

Rust-tokenizer offers high-performance tokenizers for modern language models, including WordPiece, Byte-Pair Encoding (BPE) and Unigram (SentencePiece) models

Unified learning approach for egocentric hand gesture recognition and fingertip detection.

Detect and remove logos from videos, even if they change position several times