PaperBanana: Automating Academic Illustration For AI Scientists

Python programs, usually short, of considerable difficulty, to perfect particular skills.

Adds [^1] footnote syntax support to VS Code's built-in Markdown preview

A microsite for creating concept dependency graph networks for education.

Dataset for benchmarking Dicom Deidentification.

[DEIMv2] Real Time Object Detection Meets DINOv3

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

A lightweight LMM-based Document Parsing Model

Python tool for converting files and office documents to Markdown.

FrogPilot is a fully open-source, frog-themed, and highly customizable fork of openpilot, built with clean commits and a strong focus on serving the community. Shaped by both user and developer con…

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

Multi-Joint dynamics with Contact. A general purpose physics simulator.

Official inference framework for 1-bit LLMs

Python finite-state machines and statecharts made easy.

Convert PDF to markdown + JSON quickly with high accuracy

aider is AI pair programming in your terminal

📃 A better UX for chat, writing content, and coding with LLMs.

Aruco marker detection with intel realsense camera D435 with less delay on 2DOF pose estimation

OctoTools: An agentic framework with extensible tools for complex reasoning

Darknet/YOLO object detection framework

Igus Rebel controller with ROS2 and MoveIt2: hardware interfaces and commander demos

[RSS 2025] "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

[ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"

[ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

Fully open reproduction of DeepSeek-R1

Openpilot on Jetson Xavier NX

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.