Vision
45 resources · page 1 of 2
AI in the Sciences and Engineering
Creator not supplied; see original source.
ETH CAMLab AI_Science_Engineering GitHub repo: course materials for AI in the Sciences and Engineering.
AirfRANS
Creator not supplied; see original source.
AirfRANS GitHub repo: dataset and scripts for ML surrogates of RANS airfoil flow simulations.
APEBench
Creator not supplied; see original source.
TUM APEBench GitHub repo (NeurIPS 2024): benchmark suite for autoregressive neural PDE emulators.
Introducing: Be My AI (Be My Eyes)
Creator not supplied; see original source.
Be My Eyes announcement of Be My AI, a GPT-4-based visual assistant that describes images for blind and low-vision users.
Convolutional Neural Operator
Creator not supplied; see original source.
ETH CAMLab Convolutional Neural Operator GitHub repo: official implementation for learning PDE solution operators.
DiffEqFlux.jl
Creator not supplied; see original source.
SciML DiffEqFlux.jl GitHub repo: neural differential equation layers in Julia.
facebookresearch/dinov2
Creator not supplied; see original source.
Meta DINOv2 GitHub repo: PyTorch code and models for self-supervised visual features.
Distill (archive)
Creator not supplied; see original source.
Distill: archived journal of interactive, visual machine learning research articles.
ImageNet
Creator not supplied; see original source.
ImageNet site: the large-scale image classification dataset behind the ImageNet challenge, with download access.
InternVL
Creator not supplied; see original source.
OpenGVLab InternVL GitHub repo: open-source multimodal model family with code and weights.
MBZUAI ORYX
Creator not supplied; see original source.
MBZUAI ORYX GitHub organisation: code for vision-language models and multimodal evaluation.
NeuralPDE.jl
Creator not supplied; see original source.
SciML NeuralPDE.jl GitHub repo: physics-informed neural network solvers for PDEs in Julia.
Qwen3-VL
Creator not supplied; see original source.
QwenLM Qwen3-VL GitHub repo: multimodal large language model series with usage code.
SciML Book (MIT 18.337)
Creator not supplied; see original source.
SciML Book: lecture notes from MIT 18.337 on parallel computing and scientific machine learning.
Solver-in-the-Loop
Creator not supplied; see original source.
TUM Solver-in-the-Loop GitHub repo: learning from differentiable physics to correct iterative PDE solvers.
pytorch-image-models (timm)
Creator not supplied; see original source.
Hugging Face timm GitHub repo: PyTorch image models, encoders and training scripts.
Ultralytics YOLO
Creator not supplied; see original source.
Ultralytics GitHub repo: YOLO models for object detection, segmentation and pose estimation.
VinAI
Creator not supplied; see original source.
VinAI site: Vietnamese company doing AI research and building applied AI products.
WGA: AI provisions of the 2023 MBA
Creator not supplied; see original source.
WGA page on artificial intelligence provisions in the 2023 Minimum Basic Agreement.
ImageNet Classification with Deep Convolutional Neural Networks (NeurIPS Proceedings)
Creator not supplied; see original source.
AlexNet paper (NIPS 2012) by Krizhevsky, Sutskever and Hinton: deep convolutional network for ImageNet classification.
NYU Deep Learning (LeCun/Canziani)
Creator not supplied; see original source.
NYU Deep Learning course (Spring 2021) by Yann LeCun and Alfredo Canziani, with lectures, labs and notebooks.
PDE-Transformer
Creator not supplied; see original source.
PDE-Transformer project page: transformer architecture for learning partial differential equations from data.
Physics-based Deep Learning (TUM)
Creator not supplied; see original source.
Physics-based Deep Learning book from TUM: hands-on guide to combining physical simulation with deep learning.
PointNet
Creator not supplied; see original source.
PointNet project page: deep network architecture that consumes raw point clouds for 3D classification and segmentation.
Roboflow documentation
Creator not supplied; see original source.
Roboflow documentation for building computer-vision datasets, training models and deploying them.
UvA Deep Learning tutorials
Creator not supplied; see original source.
University of Amsterdam deep learning tutorial notebooks in PyTorch and JAX/Flax, covering core architectures.
ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)
Creator not supplied; see original source.
NeurIPS paper (PDF, 2012) AlexNet: ImageNet classification with deep convolutional neural networks.
Chronos: Learning the Language of Time Series
Creator not supplied; see original source.
arXiv paper (2024) introducing Chronos, pretrained time-series forecasting models using language-model tokenization.
CLIP
Creator not supplied; see original source.
arXiv paper (2021) introducing CLIP, contrastive language-image pretraining for transferable visual models.
DenseNet
Creator not supplied; see original source.
arXiv paper (2016) "Densely Connected Convolutional Networks", introducing DenseNet, where each layer receives feature maps from all earlier layers.
DETR
Creator not supplied; see original source.
arXiv HTML version of the DETR paper (2020) on end-to-end object detection with transformers.
DINOv2: Learning Robust Visual Features without Supervision
Creator not supplied; see original source.
arXiv HTML version of the DINOv2 paper (2023) on self-supervised visual features.