Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"

Witness the aha moment of VLM with less than $3.

PyTorch code and models for VJEPA2 self-supervised learning from video.

Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Representation Learning MSc course Summer Semester 2023

🤗 image matching webui

Code for Scaling Language-Free Visual Representation Learning (WebSSL)

Build your own visual reasoning model

An extension of the PyMARL codebase that includes additional algorithms and environment support

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

A suite of image and video neural tokenizers

A large-scale benchmark and learning environment.

[ICCV 25] Official repository of "Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues"

Pyrallis is a framework for structured configuration parsing from both cmd and files. Simply define your desired configuration structure as a dataclass and let pyrallis do the rest!

Realtime API for Lucky World simulator with ROS-like interface

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

🕳 bore is a simple CLI tool for making tunnels to localhost

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Astro template to help you build an interactive project page for your research paper

LaTeX package and annotated examples for annotating equations using TikZ.

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.