Lightweight coding agent that runs in your terminal

Repository of the paper "AnyUp: Universal Feature Upsampling".

Demystify RAM Usage in Multi-Process Data Loaders

Reference PyTorch implementation and models for DINOv3

[ICCV25] Official Implementation of LeGrad

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

Vision Concept-based Interpretable Networks pytorch implementation

A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization

A final sanity checklist to help your CS paper get accepted, not desk rejected.

A collection of research materials on explainable generative models

The official implementation of our work How to Probe: Simple Yet Effective Techniques for Improved Post-hoc Explanations

Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Segment-Anything + 3D. Let's lift anything to 3D.

Maximally separating features in intermediate feature layers using PCL loss + image transformations with adversarial example transferability.

Human Activity Recognition (HAR) with Vision Transformer (ViT) based on Convolutional Features.

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Generative Models by Stability AI

[ECCV 2024] Official Release of SILC: Improving vision language pretraining with self-distillation

[NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.

Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.

Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

Implementation of adaptive hierarchical certification for segmentation using randomized smoothing.

CLIP-like model evaluation

MLX: An array framework for Apple silicon

Refine high-quality datasets and visual AI models

A personified chatbot responding to a query based on the answering pattern of Dr. APJ Abdul Kalam using Information Retrieval, Natural Language Processing, and Deep Learning techniques.

Deep Generative Diffusion Model for Pokemon Generation based on Denoising Probablistic Model (DDPM).