✨ New Feature: Dataset Loaders! ✨ Easily find code to load datasets in your preferred framework! Supporting: Hugging Face datasets, TensorFlow datasets, OpenMMLab, AllenNLP, and many more libraries! Example: paperswithcode.com/dataset/sst

🌊 MLPs are back with a vengeance: is this the next wave after Transformers? In this week's newsletter we cover top trending papers for May (lots of MLPs!), a DALL-E like method for text-to-image generation, and much more! paperswithcode.com/newsletter/10/

🎉 We've just crossed 4000 Datasets! 🎉 A huge thanks to the community for their ongoing contributions. Since launch: 🆕 1000+ new datasets added 🔗 Dataset links now show on arXiv 👩‍💻 Dataset loaders Browse full catalogue here: paperswithcode.com/datasets

🎉 New - Leaderboard Filters! 🎉 You can: 🤖 Filter by architecture, e.g. transformers on imagenet 📈 Plot 2D charts: e.g. accuracy vs params 🔧 Filter by method, e.g. turn off multiscale on coco Many comparisons are now possible beyond SoTA! Example: paperswithcode.com/sota/image-cla…

🔥 Papers with Code Newsletter #11 🔥 We cover: • better understanding of scaling properties in Vision Transformers • a method to cast the RL problem as conditional sequence modeling • techniques for SoTA out-of-distribution detection •… and more paperswithcode.com/newsletter/11

🚗 ONCE: A dataset of 1 million LiDAR scenes and 7 million corresponding camera images for 3D object detection in the autonomous driving scenario. The data is selected from 144 driving hours, which is 20x longer than other 3D autonomous driving datasets. paperswithcode.com/dataset/once

"Cognitive Computational Neuroscience" in the eyes of VQGAN and CLIP. Quite accurate if you ask me.

🎉 We’ve just crossed 5000 ML Benchmarks! 🎉 A huge thanks to the community for their ongoing contributions. Benchmarks help you keep track of the latest progress in ML across a wide range of tasks. Browse all benchmarks here: paperswithcode.com/sota

The Open Graph Benchmark (OGB) is a great example that good benchmarks and datasets drive progress in ML research, it's great to have its leaderboards at Papers with Code

👩‍💻 Machine Learning Meets Code! In this week’s newsletter, we summarize the latest advances in ML for code - including Codex (powering GitHub Copilot). Other highlights: 🧬 AlphaFold code released! 🤖 Transformers for RL 🎑 CLIP for VQA Read on below: paperswithcode.com/newsletter/13/

Hot Research 🔥 on Papers with Code! A new way to keep track of trending papers discussed by the community. Check it out: paperswithcode.com/top-social

Thanks again for all the love, arXiv community. Cheers to the next 30 years! #arXiv30

New code example on keras.io: a message-passing neural network for predicting properties of molecules given their graph. keras.io/examples/graph…

Video! Artificial Intelligence: Challenges and Opportunities for arXiv, with Nika Haghtalab Robert Stojnic youtu.be/oMt0GRaQ4po #arXiv30 Papers with Code

In a new paper from Ross Wightman et al. a traditional ResNet-50 is re-trained using a modern training protocol. It achieves a very competitive 80.4% top-1 accuracy on ImageNet without using extra data or distillation. [mini-thread] paperswithcode.com/paper/resnet-s…

StyleGAN3 is out and results are 🤯! It proposes architectural changes that suppress aliasing and forces the model to implement more natural hierarchical refinement which improves its ability to generate video and animation. paperswithcode.com/paper/alias-fr… 1/8

Graph neural networks are driving lots of progress in machine learning by extending deep learning approaches to complex graph data and applications. Let’s take a look at a few methods ↓

🪐 Introducing Galactica. A large language model for science. Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more. Explore and get weights: galactica.org

🎉New Paper🎉 Nougat - Neural Optical Understanding for Academic Documents 📄💻 It can extract text, equations and tables from academic PDFs with high precision. See examples here: facebookresearch.github.io/nougat/ Paper: arxiv.org/abs/2308.13418/ Code and models: github.com/facebookresear…

Amazing work by my colleague Lukas Blecher! We present Nougat, a model to process scientific papers in PDF to extract text and latex equations with high precision.