Official release of 'EgoSound: Benchmarking Sound Understanding in Egocentric Videos'

Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

My favorite emojis to use in a Slack setting, saved here to make sure I can access them in future Slacks

AI agents running research on single-GPU nanochat training automatically

University of Tübingen M.Sc. Machine Learning Projects

Code for the paper "DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models"

This repo contains my solutions to “Introduction to Machine Learning Interviews” by Chip Huyen.

Algorithms for outlier, adversarial and drift detection

Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"

A Repository consisting resources primarily of the Gate DA and AI

computer vision and sports

The official code release for Unsupervised Out-of-distribution Detection with Diffusion Inpainting (ICML 2023)

PyTorch native post-training library

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Probing the representations of Vision Transformers.

Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"

LAVIS - A One-stop Library for Language-Vision Intelligence

medigan - A Python Library of Pretrained Generative Models for Medical Image Synthesis

Official PyTorch implementation of the ICCV'23 paper “Anomaly Detection under Distribution Shift”

List of papers studying machine learning through the lens of category theory

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Text-to-3D Generation within 5 Minutes

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.

CMF library helps to collect and store information associated with ML pipelines. It tracks the lineages for artifacts and executions of distributed AI pipelines. It provides API's to record and que…

A Simple pytorch implementation of GradCAM and GradCAM++