Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capa…

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Multimodal Transformer for Real-time Surgical Activity Recognition and Prediction

Codebase for the paper: "TIM: A Time Interval Machine for Audio-Visual Action Recognition"

Large-scale Self-supervised Pre-training for Endoscopy

K-Scale's library for programmatically interacting with OnShape

🚨 GROW YOUR AUDIENCE WITH HUGOBLOX! 🚀 HugoBlox is an easy, fast no-code website builder for researchers, entrepreneurs, data scientists, and developers. Build stunning sites in minutes. 适合研究人员、企业家、…

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

PyTorch code and models for V-JEPA self-supervised learning from video.

A Blender add-on to import models from google maps

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Dense Optical Tracking: Connecting the Dots

🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.

A beautiful, simple, clean, and responsive Jekyll theme for academics

LLM based autonomous agent that does online comprehensive research on any given topic

Specify what you want it to build, the AI asks for clarification, and then builds it. Completely separate team and codebase from the AI Web App builder https://gptengineer.app

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

Surgical AI and Innovation Lab's public repository

Long Surgical Phase Recognition

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

⏰ AI conference deadline countdowns

A curated list of awesome temporal action segmentation resources.

Code release for "Learning Video Representations from Large Language Models"

Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation

An autoregressive character-level language model for making more things