[AAAI 2026] Next Generation Active Learning: Mixture of LLMs in the Loop

This repository contains links to machine learning exams, homework assignments, and exercises that can help you test your understanding.

official code for paper "MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles"

CURE-OR: Challenging Unreal and Real Environments for Object Recognition

A collection of useful datasets for robotics and computer vision

Florence-2 is a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks.

A list of papers that studies Novel Class Discovery

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

PyTorch code and models for the DINOv2 self-supervised learning method.

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

[EMNLP 2023] LLM guided text clustering

[ACL 2024 Findings] Generalized Category Discovery with Large Language Models in the Loop

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Code for our ICRA 2025 paper "ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations"

Benchmark Suite for Deep Learning

Code release for the paper "Personalized Robotic Object Rearrangement from Scene Context", accepted at ROMAN 2025

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet…

Mobile manipulation research tools for roboticists

A flexible, high-performance 3D simulator for Embodied AI research.

Repository for the model proposed in Patel et al. "Predicting Routine Object Usage for Proactive Robot Assistance", CoRL 2023

A benchmark environment for fully cooperative human-AI performance.

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning

Speed: Gina Cody School HPC Facility: Scripts, Tools, and Refs

Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation

Unified framework for robot learning built on NVIDIA Isaac Sim