MuJoCo Models for Google's Scanned Objects Dataset

Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot lear…

The Abstraction and Reasoning Corpus

A library for scientific machine learning and physics-informed learning

Official implementation of "RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models" - A theoretical and empirical analysis of Mamba for vision tas…

ViMix-14M is a curated multi-source video-text dataset of ~14 million pairs that provides crawl-free, download-ready access with high-quality, temporally-aligned captions, addressing the data bottl…

[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

Depth Anything 3

[AAAI 2026] Official code for MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation

Unified framework for robot learning built on NVIDIA Isaac Sim

A gym environment for ALOHA

LITEN: Learning from Inference Time Execution for VLAs

Inference Microsoft Florence2 VLM

Experimental codebase for Differential Walk on Spheres.

Official code of RDT 2

Uncertainty quantification for semantic image segmentation models using Monte Carlo dropout method

PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.

PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.

Investigating PINNs

Official code for VisProg (CVPR 2023 Best Paper!)

PINN Course in UofT

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

Code implementation of MimicFunc

Official implementation of "Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy."

VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulation (CoRL 2024)

Reference PyTorch implementation and models for DINOv3

CoRL25-"AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies"