--- id: "/non-llm-neural-networks-ml-foundations/vision/" title: "vision: 44 curated resources" url: "https://skillissue.dev/non-llm-neural-networks-ml-foundations/vision/" --- # vision: 44 curated resources vision [Beginner](/non-llm-neural-networks-ml-foundations/beginner/index.md) [Intermediate](/non-llm-neural-networks-ml-foundations/intermediate/index.md) [Advanced](/non-llm-neural-networks-ml-foundations/advanced/index.md) [Expert](/non-llm-neural-networks-ml-foundations/expert/index.md) 44 resources · page 1 of 2 - ### [AI in the Sciences and Engineering](/foundations/llm-fundamentals/ai-in-the-sciences-and-engineering/index.md) by [Computational and Applied Mathematics Laboratory @ ETH Zurich](https://camlab.ethz.ch) ETH CAMLab AI_Science_Engineering GitHub repo: course materials for AI in the Sciences and Engineering. entity repo Switzerland — ETH Zurich CAMLa en - ### [AirfRANS](/foundations/llm-fundamentals/airfrans/index.md) by [SimAI](https://www.ansys.com/ai/) AirfRANS GitHub repo: dataset and scripts for ML surrogates of RANS airfoil flow simulations. entity repo France — Extrality/Sorbonne/CN en - ### [APEBench](/foundations/llm-fundamentals/apebench/index.md) by [TUM Physics-based Simulation](https://ge.in.tum.de) TUM APEBench GitHub repo (NeurIPS 2024): benchmark suite for autoregressive neural PDE emulators. entity repo EU-DE en - ### [Introducing: Be My AI (Be My Eyes)](/foundations/llm-fundamentals/be-my-ai-be-my-eyes/index.md) by [Be My Eyes](https://bemyeyes.com/) Be My Eyes announcement of Be My AI, a GPT-4-based visual assistant that describes images for blind and low-vision users. entity company Denmark en - ### [Convolutional Neural Operator](/foundations/llm-fundamentals/convolutional-neural-operator/index.md) by [Computational and Applied Mathematics Laboratory @ ETH Zurich](https://camlab.ethz.ch) ETH CAMLab Convolutional Neural Operator GitHub repo: official implementation for learning PDE solution operators. entity repo Switzerland — ETH Zurich CAMLa en - ### [DiffEqFlux.jl](/foundations/llm-fundamentals/diffeqflux-jl/index.md) by [SciML Open Source Scientific Machine Learning](https://sciml.ai) SciML DiffEqFlux.jl GitHub repo: neural differential equation layers in Julia. entity repo Global — SciML en - ### [facebookresearch/dinov2](/foundations/llm-fundamentals/dinov2/index.md) by [Meta Research](https://opensource.fb.com) Meta DINOv2 GitHub repo: PyTorch code and models for self-supervised visual features. entity repo West en - ### [Distill (archive)](/foundations/llm-fundamentals/distill-archive/index.md) by [Distill](https://distill.pub/) Distill: archived journal of interactive, visual machine learning research articles. entity org West en - ### [InternVL](/foundations/llm-fundamentals/internvl-technical-repository/index.md) by [OpenGVLab](https://github.com/OpenGVLab) OpenGVLab InternVL GitHub repo: open-source multimodal model family with code and weights. entity repo China zh - ### [MBZUAI ORYX](/foundations/llm-fundamentals/mbzuai-oryx/index.md) by [ORYX](https://www.ival-mbzuai.net/) MBZUAI ORYX GitHub organisation: code for vision-language models and multimodal evaluation. entity org United Arab Emirates en - ### [NeuralPDE.jl](/foundations/llm-fundamentals/neuralpde-jl/index.md) by [SciML Open Source Scientific Machine Learning](https://sciml.ai) SciML NeuralPDE.jl GitHub repo: physics-informed neural network solvers for PDEs in Julia. entity repo Global — SciML en - ### [Qwen3-VL](/foundations/llm-fundamentals/qwen3-vl-technical-repository/index.md) by [Qwen](https://qwen.ai/) QwenLM Qwen3-VL GitHub repo: multimodal large language model series with usage code. entity repo China zh - ### [SciML Book (MIT 18.337)](/foundations/llm-fundamentals/sciml-book-mit-18-337/index.md) by [Chris Rackauckas (MIT 18.337)](https://book.sciml.ai/) SciML Book: lecture notes from MIT 18.337 on parallel computing and scientific machine learning. entity org West en - ### [Solver-in-the-Loop](/foundations/llm-fundamentals/solver-in-the-loop/index.md) by [TUM Physics-based Simulation](https://ge.in.tum.de) TUM Solver-in-the-Loop GitHub repo: learning from differentiable physics to correct iterative PDE solvers. entity repo EU-DE en - ### [pytorch-image-models (timm)](/foundations/llm-fundamentals/timm/index.md) by [Hugging Face](https://huggingface.co/) Hugging Face timm GitHub repo: PyTorch image models, encoders and training scripts. entity repo West en - ### [Ultralytics YOLO](/foundations/llm-fundamentals/ultralytics-yolo/index.md) by [Ultralytics](https://ultralytics.com) Ultralytics GitHub repo: YOLO models for object detection, segmentation and pose estimation. entity repo West en - ### [VinAI](/foundations/llm-fundamentals/vinai/index.md) by [VinAI](https://vinai.io/) VinAI site: Vietnamese company doing AI research and building applied AI products. entity org Vietnam en - ### [WGA: AI provisions of the 2023 MBA](/foundations/llm-fundamentals/wga-ai-provisions-of-the-2023-mba/index.md) by [Writers Guild of America West](https://wga.org/) WGA page on artificial intelligence provisions in the 2023 Minimum Basic Agreement. entity standard-policy US en - ### [ImageNet Classification with Deep Convolutional Neural Networks (NeurIPS Proceedings)](/foundations/llm-fundamentals/alexnet/index.md) by [Alex Krizhevsky, Ilya Sutskever and Geoffrey E. Hinton (University of Toronto)](https://www.utoronto.ca/) AlexNet paper (NIPS 2012) by Krizhevsky, Sutskever and Hinton: deep convolutional network for ImageNet classification. Intermediate learning_resource guide West en - ### [NYU Deep Learning (LeCun/Canziani)](/foundations/llm-fundamentals/nyu-deep-learning-lecun-canziani/index.md) by [Alfredo Canziani](https://atcold.github.io/) NYU Deep Learning course (Spring 2021) by Yann LeCun and Alfredo Canziani, with lectures, labs and notebooks. Intermediate learning_resource guide West en - ### [PDE-Transformer](/foundations/llm-fundamentals/pde-transformer/index.md) by [TUM Physics-based Simulation](https://ge.in.tum.de) PDE-Transformer project page: transformer architecture for learning partial differential equations from data. Intermediate learning_resource guide EU-DE en - ### [Physics-based Deep Learning (TUM)](/foundations/llm-fundamentals/physics-based-deep-learning-tum/index.md) by [Nils Thuerey et al. (TU Munich)](https://physicsbaseddeeplearning.org/) Physics-based Deep Learning book from TUM: hands-on guide to combining physical simulation with deep learning. Intermediate learning_resource guide West en - ### [PointNet](/foundations/llm-fundamentals/pointnet/index.md) by [Charles R. Qi et al. (Stanford University)](https://www.stanford.edu/) PointNet project page: deep network architecture that consumes raw point clouds for 3D classification and segmentation. Intermediate learning_resource guide US en - ### [Roboflow documentation](/foundations/llm-fundamentals/roboflow-documentation/index.md) by [Roboflow](https://roboflow.com/) Roboflow documentation for building computer-vision datasets, training models and deploying them. Intermediate learning_resource docs US en - ### [UvA Deep Learning tutorials](/foundations/llm-fundamentals/uva-deep-learning-tutorials/index.md) by [Phillip Lippe (University of Amsterdam)](https://uvadlc.github.io/) University of Amsterdam deep learning tutorial notebooks in PyTorch and JAX/Flax, covering core architectures. Intermediate learning_resource guide West en - ### [ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)](/foundations/llm-fundamentals/alexnet-2/index.md) by [Alex Krizhevsky, Ilya Sutskever and Geoffrey E. Hinton (University of Toronto)](https://www.utoronto.ca/) NeurIPS paper (PDF, 2012) AlexNet: ImageNet classification with deep convolutional neural networks. Advanced–Expert learning_resource paper North America — Canada - ### [Chronos: Learning the Language of Time Series](/foundations/llm-fundamentals/chronos-2/index.md) by [Abdul Fatir Ansari et al. (Amazon)](https://www.amazon.science/) arXiv paper (2024) introducing Chronos, pretrained time-series forecasting models using language-model tokenization. Advanced–Expert learning_resource paper Global (Amazon/AWS; US/German en - ### [CLIP](/foundations/llm-fundamentals/clip/index.md) by [Alec Radford et al. (OpenAI)](https://openai.com/) arXiv paper (2021) introducing CLIP, contrastive language-image pretraining for transferable visual models. Advanced learning_resource paper West en - ### [DenseNet](/foundations/llm-fundamentals/densenet/index.md) by [Gao Huang et al. (Cornell University)](https://www.cornell.edu) arXiv paper (2016) "Densely Connected Convolutional Networks", introducing DenseNet, where each layer receives feature maps from all earlier layers. Advanced–Expert learning_resource paper CN en - ### [DETR](/foundations/llm-fundamentals/detr/index.md) by [Nicolas Carion et al. (Meta)](https://ai.meta.com/) arXiv HTML version of the DETR paper (2020) on end-to-end object detection with transformers. Advanced–Expert learning_resource paper US en - ### [DINOv2: Learning Robust Visual Features without Supervision](/foundations/llm-fundamentals/dinov2-2/index.md) by [Maxime Oquab et al. (Meta AI)](https://ai.meta.com/) arXiv HTML version of the DINOv2 paper (2023) on self-supervised visual features. Advanced–Expert learning_resource paper Global — Meta AI and Inria (Eu en - ### [EfficientNet](/foundations/llm-fundamentals/efficientnet/index.md) by [Mingxing Tan and Quoc V. Le (Google Brain)](https://research.google/) ICML 2019 paper (PDF) EfficientNet: scaling convolutional networks by depth, width and resolution. Advanced–Expert learning_resource paper US [Next page](/non-llm-neural-networks-ml-foundations/vision/page/2/index.md) [Plain-text Markdown copy](/non-llm-neural-networks-ml-foundations/vision/index.md)