Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

This project analyzes Tennis players in a video to measure their speed, ball shot speed and number of shots. This project will detect players and the tennis ball using YOLO and also utilizes CNNs t…

Tennis analysis using deep learning and machine learning

This project goes beyond traditional video analysis. By leveraging state-of-the-art technologies like YOLO, PyTorch, and CNNs, it provides detailed insights into tennis player performance, helping …

This computer vision project analyzes tennis match videos using cutting-edge techniques. It employs YOLOv8 for player detection, finetuned YOLO for ball tracking, and ResNet50 for extracting court …

Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art (WACVW'24)

Open source Twitch for developers

Create standalone Windows programs from Python code

Object detection and tracking in sports videos

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

a small, expressive orm -- supports postgresql, mysql, sqlite and cockroachdb

Suika Stay Home by Billy Rennekamp and Joon Yeon Park

OpenStego is a steganography application that provides two functionalities: a) Data Hiding: It can hide any data within an image file. b) Watermarking: Watermarking image files with an invisible si…

UP-TO-DATE LLM Watermark paper. 🔥🔥🔥

LLM Program Watermarking

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.

AutoML tool for RAG

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.

reverse-engineered client for the LG SmartThinQ API

Instant voice cloning by MIT and MyShell.

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

[CVPR2024, Highlight] Official code for DragDiffusion

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)