AI-powered visual learning platform

Thrifty is proof-of-concept SDR software for TDOA positioning using inexpensive SDR hardware such as the RTL-SDR.

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

Repository of the paper "AnyUp: Universal Feature Upsampling".

Cloud-RF API clients for use with the CloudRF API https://api.cloudrf.com

Take your LLM to the optometrist.

It shows how to use strands agent.

A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms

PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

Dereflection Any Image with Diffusion Priors and Diversified Data

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

LangChain, LangGraph Open Tutorial for everyone!

Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

OpenLayers

It shows advanced RAG and 4 design patterns of agentic workflow based on LangChain and LangGraph using Amazon Nova Pro.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Tesseract Open Source OCR Engine (main repository)

A collective list of free APIs

CoTracker is a model for tracking any point (pixel) on a video.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…