A collection of libraries and tools that help you build adaptive, accessible, and robust user experiences.

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

Standard Open Arm 100

🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper

OO for LLMs

DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dat…

Purpose-built, Rust-native software engine for robotics

Node-Based Robotics Framework Written in Rust

An exploration of LLM steering

Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23…

A simple unified framework for evaluating LLMs

Mathematical operations for JAX pytrees

This repository contains the code for the paper "Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks" by Abhinav Rao, Sachin Vashishta*, Atharva Naik*, Somak Aditya, a…

Inference code for LLaMA models in JAX

Open-source Next.js template for building apps that are fully generated by AI. By E2B.

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

The nnsight package enables interpreting and manipulating the internals of deep learned models.

This repository is related to 'Intriguing Properties of Hyperbolic Embeddings in Vision-Language Models', published at TMLR (2024), https://openreview.net/pdf?id=P5D2gfi4Gg

JAILBREAK PROMPTS FOR LIBERATING AI MODELS

Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

Improving Alignment and Robustness with Circuit Breakers

Repo is required for the code of our research paper on micro-budget training of large scale diffusion model.

Quickly make and deploy full-stack apps with database, auth, styling, storage etc. figured out for you. Add all primitives you want.

Sparse and discrete interpretability tool for neural networks

Remote Functions. Instead of API.

🔨 Flexible, lean, community-driven, dependable, fast Vite-based frontend framework.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

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