[RSS 2021] An End-to-End Differentiable Framework for Contact-Aware Robot Design

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

A LinearOperator implementation to wrap the numerical nuts and bolts of GPyTorch

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

Efficient Track Anything

Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

[NeurIPS 2024] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set …

Diffusion Classifier leverages pretrained diffusion models to perform zero-shot classification without additional training

Jupyter Notecbook tutorials for the Technion's EE Computer Vision course

Differentiable signal processing on the sphere for PyTorch

A curated set of C++ examples for optimization-based elastodynamic contact simulation using CUDA, emphasizing algorithmic convergence, penetration-free, and inversion-free conditions. Designed for …

Bring portraits to life!

Learning with 3D rotations, a hitchhiker’s guide to SO(3) - ICML 2024

'Random Features for Large-Scale Kernel Machines' by Ali Rahimi and Benjamin Recht. The code within provides a detailed walkthrough of the techniques introduced in the paper, demonstrating how to e…

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

[NeurIPS 2023] AbdomenAtlas 1.0 (5,195 CT volumes + 9 annotated classes)

My own implementation for some sort of loss functions that have been used for segmentation task.

[CVPR 2023] Official Pytorch code for PROB: Probabilistic Objectness for Open World Object Detection

[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

Starter notebook and utilities for the Clevr-4 dataset

Comments on the Nature of Being a Graduate Student

A python library for self-supervised learning on images.

A collection of learning resources for curious software engineers

Material for gpu-mode lectures