XOutlier
Download .zipAdd to Chrome

Papers with Code

@paperswithcode113k followers

Our mission is to organize science by converting information into useful knowledge.

Open on X
Top outlier
57.1ร—
Best organic post
Peak views
0
Single post
Bookmarks
11k
Across 95 organic posts
Last scan
Oct 17
Community cache
Posts 95 posts
#DatePostโ†“ OutlierViewsLikesRepostsBookmarks
1Nov 15, '22๐Ÿช Introducing Galactica. A large language model for science. Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecu57.1ร—07.3k2k2.7k
2Oct 8, '20๐ŸŽ‰ Papers with Code partners with arXiv! Code links are now shown on arXiv articles, and authors can submit code through arXiv. Read more:32.5ร—06.1k1.7k201
3Feb 2, '21๐ŸŽ‰ Introducing... Datasets! We are now indexing 3000+ research datasets from machine learning. Find datasets by task and modality, compare usage over time, browse benchmarks, and m15.9ร—02.6k735435
4Nov 1, '21๐ŸŽ‰ We've just crossed 5000 Datasets! ๐ŸŽ‰ We now index and organize more than 5000 research datasets for machine learning. A huge thanks to the research community for their ongoing c11.7ร—01.9k451444
5Feb 1, '19Weโ€™ve just released the new Papers With Code! Site now has over 950+ ML tasks, 500+ evaluation tables (including state of the art results) and 8500+ papers with code. Explore the r11.3ร—01.5k748164
6Jul 8, '20๐ŸŽ‰ Introducing... Methods! We are now tracking 730+ building blocks of machine learning: optimizers, activations, attention layers, convolutions and much more! Compare usage over t11.2ร—01.8k547316
7May 13, '21๐ŸŽ‰ Introducing Datasets on arXiv! ๐ŸŽ‰ The new "Code & Data" tab shows datasets used and introduced in the paper! Read more:10.2ร—02k442120
8Dec 10, '20๐ŸŽ‰ Papers with Code is expanding to more sciences! Today we launch new sites for physics, maths, CS, statistics and astronomy. You can use these sites to sync your code to show on 10.0ร—01.9k369195
9Oct 27, '21Graph neural networks are driving lots of progress in machine learning by extending deep learning approaches to complex graph data and applications. Letโ€™s take a look at a few meth8.9ร—01.3k287478
10May 7, '20๐ŸŽ‰ A huge update to Papers with Code: now with 2500+ leaderboards and 20,000+ results. Plus, results now link directly to tables in arXiv! Read more in our blog post below and feel7.3ร—01.3k323163
11Dec 30, '20โช Papers with Code: Year in Review. Weโ€™re ending the year by taking a look back at the top trending papers, libraries and benchmarks for 2020. Read on below!6.0ร—0906263238
12Dec 30, '21โช Papers with Code: Year in Review Weโ€™re ending the year by taking a look back at the top trending machine learning papers, libraries and new datasets for 2021. Read on below!5.2ร—0795201237
13Feb 16, '21๐ŸŽ‰ Introducing...Papers with Libraries! We are now indexing ML libraries from the community. We start with the amazing TIMM by @wightmanr. Explore 330+ models, visualize architectu5.1ร—0901246102
14Nov 10, '21Deep learning models for tabular data continue to improve. What are the latest methods and recent progress? Letโ€™s have a look โ†“4.8ร—0665133296
15Apr 13, '21๐ŸŽ‰ Introducing @paperswithdata ๐ŸŽ‰ A curated, daily feed of newly published datasets in machine learning. Follow to stay updated with new datasets!4.6ร—081425270
16Dec 13, '19Weโ€™re excited to announce weโ€™re joining Facebook AI! Read more about it here: @facebookai4.4ร—090216153
17Nov 3, '21Graph neural networks are rapidly advancing progress in ML for complex graph data applications. In this weekโ€™s newsletter, we show you recent uses of GNNs ranging from protein inte4.3ร—0703149180
18Sep 4, '20๐Ÿ”ฅ Introducing... the ML Reproducibility Challenge 2020! The 4th annual edition now expands to cover papers from 7 major ML conferences: NeurIPS, EMNLP, ACL, ICML, ICLR, CVPR and E4.0ร—068421082
19Apr 25, '2210 Recent Trends in Language Models In this thread, we summarize ten recent trends and insights in language models. โ†“3.7ร—0477124220
20Oct 10, '19๐ŸŽ‰ Introducing sotabench : a new service with the mission of benchmarking every open source ML model. We run GitHub repos on free GPU servers to capture their results: compare to p3.7ร—062820744
21Mar 17, '21๐Ÿ’ซ There has been an explosion of interest in self-supervised learning (SSL) for vision and NLP. In this week's newsletter, we show you recent uses of SSL across various ML tasks f3.6ร—0584156132
22Nov 18, '21๐Ÿงฌ Machine learning is having a big impact on scientific discovery In this week's newsletter we show recent papers where ML is accelerating scientific discovery, from protein struc3.3ร—0526114144
23Jul 1, '21๐Ÿ’ฅ Deep learning makes strides on tabular data! In this weekโ€™s newsletter, we summarize recent developments and papers using deep learning models for tabular data... and much more.3.2ร—0519126134
24Jun 8, '21๐ŸŽ‰ We've just crossed 4000 Datasets! ๐ŸŽ‰ A huge thanks to the community for their ongoing contributions. Since launch: ๐Ÿ†• 1000+ new datasets added ๐Ÿ”— Dataset links now show on arXiv3.2ร—057712987
25Feb 16, '22Vision Transformers aim to bring the strengths of transformers into the world of computer vision. It's early days but progress has been happening in areas such as as image recognit3.1ร—050796152
26Feb 10, '22๐ŸŽ‰ Papers with Code partners with OpenReview ๐ŸŽ‰ Find code and datasets directly from @openreviewnet papers!3.0ร—06449654
27Dec 18, '20๐ŸŽ‰ Introducing the new Papers with Code newsletter! Our newsletter helps you manage the firehose of new ML papers by highlighting trending papers, new state-of-the-art results, and2.9ร—056212448
28Feb 12, '21๐ŸŽ‰ We've just crossed 1000 ML Methods! ๐ŸŽ‰ A huge thanks to the community for their ongoing contributions. Methods help to discover the latest building blocks of machine learning (e2.8ร—05368391
29Jun 25, '20Awesome tool by @EladRichardson. Chrome Extension that connects Google Scholar with code implementations from Papers With Code! ๐Ÿ”ฅ2.8ร—045812870
30Nov 17, '22Thank you everyone for trying the Galactica model demo. We appreciate the feedback we have received so far from the community, and have paused the demo for now. Our models are avai2.6ร—05034474
31Aug 31, '22๐Ÿ”ฅTop Trending ML Papers of the Month Here is a thread to catchup on the top 10 trending papers of August on @paperswithcode.2.6ร—038081140
32Sep 8, '20๐Ÿค Code Snippets! Methods now come with links to example implementations, so you can see how to implement hundreds of methods in various frameworks. Example:2.4ร—044610650
34Feb 25, '21โšก๏ธ Efficient Vision Models are Trending! โšก๏ธ This weekโ€™s newsletter highlights progress in building efficient vision models, adopting Transformers to challenging domains like GANs, 2.2ร—03779475
35Feb 15, '20๐Ÿ“ˆ Self-supervised learning is a popular research trend, with lots of progress in the past year. Check out this task page with paper collections, resources and a new self-supervise2.2ร—03739370
36May 10, '22๐ŸŽ‰ We've now crossed 6000 Datasets! ๐ŸŽ‰ Some dataset stats: - 1.8K for image tasks - 1.6K for text tasks - 286 for question answering - 7.4K ML benchmarks in total Thanks for all th2.2ร—03597685
37Mar 10, '22๐ŸŽ‰ We've crossed 6000 Benchmarks! ๐ŸŽ‰ We now maintain more than 6.4K benchmarks for machine learning. A huge thanks to the research community for ongoing contributions. Browse all b2.0ร—03946857
38Sep 1, '21๐Ÿ”ฅThe ML Reproducibility Challenge is back! The 5th annual edition now expands to cover papers from 9 major ML conferences: NeurIPS, ICML, ICLR, ACL-IJCNLP, EMNLP, CVPR, ICCV, AAAI2.0ร—03279850
39May 31, '22๐Ÿ”ฅTop Trending ML Papers of the Month Here is a thread to catchup on the top 10 trending papers of May on @paperswithcode. 1/112.0ร—03227392
40Oct 12, '21StyleGAN3 is out and results are ๐Ÿคฏ! It proposes architectural changes that suppress aliasing and forces the model to implement more natural hierarchical refinement which improves 2.0ร—03898441
41Apr 26, '20ICLR is starting! See all ICLR-2020 papers with official code sorted by number of GitHub stars here:2.0ร—034710441
42Jan 18, '22๐Ÿ”ฅ The debate between ConvNets and Transformers intensifies! In this week's newsletter: the latest improvements on ConvNets, neural networks for mathematical reasoning, and a close2.0ร—03398071
43Feb 17, '22๐Ÿ’ซ New research explains how vision transformers work! In this week's newsletter: summary of how and why vision transformers work, improving OOD detection, a unified multimodal pre2.0ร—03277184
44Feb 9, '21There's been a rapid adoption of self-attention models for visual recognition. This weeks' newsletter highlights a taxonomy of self-attention models for vision, recent papers, and 2.0ร—03158177
45Apr 8, '20What do popular research repositories have in common? We aim to capture this with the ML Code Completeness Checklist - now part of the NeurIPS 2020 submission process. Read more he1.9ร—03148756
46Jun 20, '19XLNet outperforms BERT on 20 tasks, often by a large margin, and achieves state-of-the-art results on 18 tasks including question answering, natural language inference, sentiment a1.9ร—033810326
47May 27, '21โœจ New Feature: Dataset Loaders! โœจ Easily find code to load datasets in your preferred framework! Supporting: @huggingface datasets, TensorFlow datasets, OpenMMLab, AllenNLP, and ma1.8ร—03257354
48Jul 10, '20๐Ÿ”ฅ Our new autocomplete gives you ๐™›๐™–๐™จ๐™ฉ access to 25k papers with code, 2.8k leaderboards, 1.6k tasks, 760 methods. Researchers can add results & methods for papers to enhan1.8ร—03637533
49Jul 19, '22Keeping up with Language Models Check out these trending papers to catchup on the latest developments in language models. โ†“1.8ร—027941106
50Mar 8, '21Labels? Where we're going, we don't need...labels. ๐Ÿ’ฅ VISSL is a new library for self-supervised learning by @priy2201 et al. You can browse and compare different self-supervised l1.8ร—02926968
51Jun 4, '21๐ŸŒŠ 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 fo1.7ร—02786867
52Jun 10, '19๐ŸŽ‰ New feature: PyTorch Hub and Google Colab integration! Now you can go straight from a paper to a Colab notebook, and obtain pre-trained models from PyTorch Hub (look out for mor1.7ร—031010217
53Apr 5, '19๐ŸŽ‰ New feature: State-of-the-art GitHub badges. Submit evaluation results from your paper to obtain a badge for the official GitHub repository. A new way to highlight your paper's 1.7ร—03238216
54Sep 22, '20๐Ÿš€ The ML Reproducibility Challenge is an amazing opportunity for students to learn about cutting edge ML research. @JesseDodge explains how you can incorporate it in your course t1.6ร—02586762
55Jul 10, '19Now over 1,000 tables tracking the state-of-the-art in ML! Thanks to the amazing community for making this possible by submitting results from papers.1.6ร—02758431
56Feb 17, '21๐Ÿ”ฅ Torchvision on Papers with Code! ๐Ÿ”ฅ ๐Ÿ”Ž Discover and compare 60+ pre-trained models ๐Ÿ”ฎ Tasks: image/video classification, segmentation, object detection ๐Ÿ‹๏ธ Training recipes for 1.6ร—02976246
57Aug 22, '22๐Ÿ”ฅThe ML Reproducibility Challenge is back! The 6th edition now expands to papers from 11 ML conferences: NeurIPS, ICML, ICLR, ACL, EMNLP, CVPR, ECCV, AAAI, IJCAI-ECAI, ACM FAccT &1.6ร—02426963
58Mar 24, '22Vision-language pre-trained models are driving lots of progress on machine learning tasks that require vision & language modalities. Letโ€™s take a look at some recent models โ†“1.6ร—02545472
59Nov 23, '21๐Ÿค Papers with Code is now helping to maintain . AI Conference Deadlines makes it easy to find and follow conference deadlines in areas such as machine learning and NLP. Thanks to 1.6ร—02736650
60Jul 5, '22๐Ÿ”ฅTop Trending ML Papers of the Month Here is a thread to catchup on the top 10 trending papers of June on @paperswithcode. โ†“1.6ร—02314587
61Mar 31, '21๐Ÿ“ˆ Vision Transformers are trending in the community! In this weekโ€™s newsletter, we summarize recent research in vision transformers, real-time rendering of NeRFs, advancing GPT-st1.6ร—02667250
62May 4, '21โœจ A single MSc course produced 9 papers! โœจ Learn about their story and how the Reproducibility Challenge can boost your course in a post by @__alucic:1.6ร—02715553
63May 18, '21๐Ÿ”ฅ Papers with Code Newsletter #9 ๐Ÿ”ฅ We cover: โ€ข MLP-style models with competitive results on image classification! โ€ข dataset links on arXiv articles, โ€ข diffusion models beat GANs 1.5ร—02886039
64Jul 16, '21๐Ÿ‘ฉโ€๐Ÿ’ป Machine Learning Meets Code! In this weekโ€™s newsletter, we summarize the latest advances in ML for code - including Codex (powering GitHub Copilot). Other highlights: ๐Ÿงฌ Alph1.5ร—02556050
65Feb 22, '21Detectron2 on Papers with Code! ๐Ÿš€ ๐Ÿ‘๏ธ Discover 80+ models for object detection and segmentation. โš–๏ธ Visualize performance vs speed tradeoffs. ๐Ÿ”ฎ Perform advanced tasks like panopt1.5ร—02586050
66Oct 5, '20๐Ÿ’กThe Vision Transformer has been getting some...attention. Results, code, methods and more have been indexed here: . A good starting point for anyone who wants to dig deeper.1.5ร—02816330
67Jun 25, '19CVPR 2019 Implementations: get all the papers with code in one place here:1.4ร—02399018
68Jul 26, '21Hot Research ๐Ÿ”ฅ on Papers with Code! A new way to keep track of trending papers discussed by the community. Check it out:1.4ร—02635639
69Feb 2, '22๐Ÿ› ๏ธ Hybrid models for vision and NLP are on the rise! In this week's newsletter: the latest hybrid architectures for vision and language, language models in embodied agents, top 101.4ร—02564949
70Apr 8, '21We're hiring passionate engineers looking to make ML research more reproducible, discoverable and extensible. Apply here to work with us on this mission:1.4ร—02735930
71Dec 24, '20DeiT is a new Vision Transformer which trains on ImageNet alone, with a new teacher-student training strategy specific to transformers. Paper, code, results, methods and more have 1.4ร—02634346
73Nov 12, '21๐ŸŽ‰ Papers with Code partners with ACL! Access code and datasets directly from ACL papers. Huge thanks to @mjpost and @mmbollmann for the collaboration.1.4ร—02815617
74Jun 3, '21๐ŸŽ‰ Reproducibility Reports are LIVE! Papers now link to reproducibility reports. Alongside code, this is a new signal for how reproducible a paper's findings are. Thanks to RC2020 1.4ร—02735913
75Aug 5, '19An Animated History of ImageNet : from AlexNet to FixResNeXt-101. See the full table and add more results here:1.3ร—02427714
76Jul 28, '22๐Ÿ”ฅTop Trending ML Papers of the Month Here is a thread to catchup on the top 10 trending papers of July on @paperswithcode.1.3ร—02093365
77Oct 4, '21In a new paper from @wightmanr 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 withou1.3ร—02354833
79Dec 7, '21Text-Driven Neural Stylization for 3D Meshes This new paper proposes a text-driven, neural network based approach (Text2Mesh) for stylizing 3D meshes. Paper & Code: (A short th1.3ร—02343741
80Apr 16, '21๐Ÿ“ˆ Top trending ML papers of March 2021 In this week's newsletter: top trending papers, state-of-the-art speech recognition, revisiting neural probabilistic language models, progre1.2ร—02194542
81Sep 10, '21๐Ÿ’ฅ Exciting progress in language modeling for long sequences! In this week's newsletter, read about new methods for long sequences (Fastformer, โˆž-former, ALiBi), T5 on code, zero-s1.2ร—02024443
82Mar 31, '19New state-of-the-art for several semantic segmentation benchmarks. FastFCN by Wu et al replaces dilated convolutions with a Joint Pyramid Upsampling (JPU) module to reduce computat1.1ร—02076117
83Dec 6, '19NeurIPS 2019 Implementations - get all the papers with code in one place here:1.1ร—01767319
84Sep 28, '22Language models are getting more capable! How are researchers measuring progress and probing language models? Letโ€™s take a look in this thread. 1/61.1ร—01752765
85Sep 16, '19New state-of-the-art for object detection on COCO. Liu et al introduce a composite backbone architecture that extracts more representational basic features than the original backbo1.1ร—01855824
86Jan 13, '21๐Ÿ” Check out this link if you want to quickly browse the ICLR 2021 list of accepted papers containing code. You can filter papers by task, author, keyword, etc.1.1ร—02015126
87Mar 3, '22๐Ÿ“ˆ Trending Papers with Code ICYMI, here is a roundup of the top 10 trending machine learning papers on Papers with Code for February 2022.1.1ร—01853942
88Dec 2, '21๐Ÿš€ Vision models are getting bigger and more effective! In this week's newsletter: a summary of the latest in visual synthesis, new techniques for scaling up vision models, and muc1.1ร—02003335
89Jun 21, '22โšก๏ธMultimodal research is rapidly advancing! In this week's newsletter: we summarize progress in general-purpose ML (Unified-IO, MetaLM, LIFT) and more. Read on here:1.0ร—01674635
90Oct 1, '20๐Ÿ” Many of the @paperswithcode methods now appear as featured snippets on @Google! If you are an author, you can add your methods to the resource (with descriptions, images) to enh1.0ร—02194016
91Mar 30, '22๐Ÿ’ซ Vision-and-Language models are trending! In this weekโ€™s newsletter: we highlight progress in vision-and-language pretrained models, new ML papers & results, and more. Read o1.0ร—01863338
92Jun 22, '19Want a quick way to find the state of the art on a machine learning task? Type in โ€œstate of the art [task]โ€ on @Google. Voila. ๐Ÿ”ฅ1.0ร—0187597
93Aug 12, '21๐Ÿ’ก Can we build NNs to process any modality? In this week's newsletter, we summarize architectures for handling diverse modalities and output tasks... and much more! Read on below:1.0ร—01713840
94Jul 13, '21๐ŸŽ‰ Weโ€™ve just crossed 5000 ML Benchmarks! ๐ŸŽ‰ A huge thanks to the community for their ongoing contributions. Benchmarks help you keep track of the latest progress in ML across a wi1.0ร—01963427
95Mar 1, '21๐Ÿ’ฅMMDetection comes to Paper with Code! Explore 370 object detection & instance segmentation models by @OpenMMLab: โš–๏ธ Compare speed vs performance. ๐Ÿ“„ Linked papers and methods1.0ร—01874817
96Apr 16, '19Interesting new paper for image classification that introduces a new type of convolution (OctaveConv): achieves higher accuracy with fewer FLOPs on ImageNet. But no public code yet1.0ร—01755312
98Dec 21, '20๐Ÿ“ˆ Papers with Code now integrates with ongoing competitions! Our first partner is @Eval_AI - huge thanks to @rishabhjain2018! Learn more about how to integrate your competitions h1.0ร—01803518
99Mar 16, '21๐ŸŽ‰ Introducing AllenNLP on Papers with Code Libraries We are excited to welcome @ai2_allennlp to our library catalogue. ๐Ÿ•ต๏ธโ€โ™€๏ธ Explore state-of-the-art NLP models ๐ŸŽฏ Find training 0.9ร—01693321

Scan another creator

@
@karpathy@levelsio@paulg@naval@marclou@illyism

Run this on any account.

XOutlier builds this table for every public profile you open on x.com, with live data and every post, not just the top 50.

Add to Chrome Download .zip