Hacker Papers

1. 676
   

   Deep Learning is Robust to Massive Label Noise

   David Rolnick et al. · 2017

   Hacker News threads

   • Mar 2022Deep learning on electronic medical records is doomed to fail
   • Oct 2022Why we chose not to release Stable Diffusion 1.5 as quickly
   • Jul 2024A multimodal dataset with one trillion tokens

   arXiv ↗
2. 677
   

   Recurrent Relational Networks

   Rasmus Berg Palm et al. · 2017

   Hacker News threads

   • Dec 2018The Machine Learning Race Is Really a Data Race
   • Feb 2019Neural Networks Are Essentially Polynomial Regression (2018)
   • Jul 2023Code Interpreter will be available to all ChatGPT Plus users over the next week

   arXiv ↗
3. 678
   

   Deep Image Prior

   Dmitry Ulyanov et al. · 2017

   Hacker News threads

   • Aug 2018This AI is bad at drawing but will try anyways
   • Feb 2021Adversarial.io – Fighting mass image recognition
   • Dec 2021HyperNeRF

   arXiv ↗
4. 679
   

   A Multi-Horizon Quantile Recurrent Forecaster

   Ruofeng Wen et al. · 2017

   Hacker News threads

   • Nov 2019Ask HN: Why do so many startups claim machine learning is their long game?
   • Jul 2021Is Facebook's “Prophet” the time-series Messiah or just a naughty boy?
   • Dec 2022Statistical vs. Deep Learning forecasting methods

   arXiv ↗
5. 680
   

   Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

   Timur Garipov et al. · 2018

   Hacker News threads

   • Feb 2023Knowledge Is a Region in Weight Space for Fine-Tuned Language Models
   • Jun 2024Grokfast: Accelerated Grokking by Amplifying Slow Gradients
   • Jun 2026Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model

   arXiv ↗
6. 681
   

   Investigating Human Priors for Playing Video Games

   Rachit Dubey et al. · 2018

   Hacker News threads

   • Oct 2019Machines Beat Humans on a Reading Test
   • May 2020Pac-Man recreated with a GAN trained on 50k game episodes
   • Oct 2021Megatron-Turing NLG 530B, the World’s Largest Generative Language Model

   arXiv ↗
7. 682
   

   Delayed Impact of Fair Machine Learning

   Lydia T. Liu et al. · 2018

   Hacker News threads

   • Jan 2019Alexandria Ocasio-Cortez Is Absolutely Right About Racist Algorithms
   • Sep 2020Algorithm Helps New York Decide Who Goes Free Before Trial
   • Dec 2020AI researcher Timnit Gebru resigns from Google

   arXiv ↗
8. 683
   

   Averaging Weights Leads to Wider Optima and Better Generalization

   Pavel Izmailov et al. · 2018

   Hacker News threads

   • Jan 2020An idea from physics helps AI see in higher dimensions
   • Jul 2020The Overfitted Brain: Dreams evolved to assist generalization
   • Apr 2024Schedule-Free Learning – A New Way to Train

   arXiv ↗
9. 684
   

   AutoAugment: Learning Augmentation Policies from Data

   Ekin D. Cubuk et al. · 2018

   Hacker News threads

   • Jun 2018Improving Deep Learning Performance with AutoAugment
   • Aug 2018Current state of the art in objects classification
   • May 2019Show HN: DeepSwarm – Optimising CNNs Using Swarm Intelligence

   arXiv ↗
10. 685
    

    Neural Guided Constraint Logic Programming for Program Synthesis

    Lisa Zhang et al. · 2018

    Hacker News threads

    • Jun 2023Compilers for the Future
    • Aug 2023Show HN: LLMs can generate valid JSON 100% of the time
    • Jan 2025What Is miniKanren?

    arXiv ↗
11. 686
    

    ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

    Robert Geirhos et al. · 2018

    Hacker News threads

    • Sep 2019People Recognize Objects by Visualizing Their “Skeletons”
    • Feb 2021What Inception Net Doesn't See
    • May 2024AI vs. a giraffe with no spots (2023)

    arXiv ↗
12. 687
    

    Lessons from Building Acoustic Models with a Million Hours of Speech

    Sree Hari Krishnan Parthasarathi, Nikko Strom · 2019

    Hacker News threads

    • Apr 2019Alexa researchers train speech recognizer on 1M hours of unlabeled speech
    • Dec 2019Common Voice: A Massively-Multilingual Speech Corpus
    • Apr 2020Building an end-to-end Speech Recognition model in PyTorch

    arXiv ↗
13. 688
    

    BERT Rediscovers the Classical NLP Pipeline

    Ian Tenney et al. · 2019

    Hacker News threads

    • Mar 2021Self-supervised learning: The dark matter of intelligence
    • Feb 2023We Found an Neuron in GPT-2
    • May 2023Show HN: Visual intuitive explanations of LLM concepts (LLM University)

    arXiv ↗
14. 689
    

    Deep Learning Recommendation Model for Personalization and Recommendation Systems

    Maxim Naumov et al. · 2019

    Hacker News threads

    • Mar 2020Smart Algorithms beat Hardware Acceleration for Large-Scale Deep Learning
    • Mar 2024Building Meta's GenAI infrastructure
    • Mar 2025Strobelight: A profiling service built on open source technology

    arXiv ↗
15. 690
    

    Hamiltonian Neural Networks

    Sam Greydanus et al. · 2019

    Hacker News threads

    • Feb 2020Sometimes, requiring explanability is counterproductive
    • Jun 2020Teaching physics to neural networks removes 'chaos blindness'
    • Jul 2020AI in physics: are we facing a scientific revolution?

    arXiv ↗
16. 691
    

    Attention is not not Explanation

    Sarah Wiegreffe, Yuval Pinter · 2019

    Hacker News threads

    • Sep 2019Attention Mechanism in Deep Learning
    • Dec 2020Ask HN: What's the best paper you've read in 2020?
    • Jan 2026The Q, K, V Matrices

    arXiv ↗
17. 692
    

    KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning

    Tarin Clanuwat et al. · 2019

    Hacker News threads

    • Nov 2019Machine Learning Can Help Unlock the World of Ancient Japan
    • Dec 2025The writing is on the wall for handwriting recognition
    • Apr 2026Hokusai and Tesselations

    arXiv ↗
18. 693
    

    Array Languages Make Neural Networks Fast

    Artjoms Šinkarovs et al. · 2019

    Hacker News threads

    • Apr 2021CPU-based algorithm trains deep neural nets up to 15 times faster than top GPU
    • Mar 2023HN thread 34978026
    • Jun 2024Arthur Whitney releases an open-source subset of K with MIT license

    arXiv ↗
19. 694
    

    OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network

    Xavier Marjou · 2019

    Hacker News threads

    • Nov 2020What language do people speak in the Balkans, anyway? (2019)
    • May 2023Deseret Alphabet
    • Jul 2025Why English doesn't use accents
    • Jul 2025Why English doesn't use accents

    arXiv ↗
20. 695
    

    ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

    Omar Khattab, Matei Zaharia · 2020

    Hacker News threads

    • May 2024Vector indexing all of Wikipedia on a laptop
    • Sep 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
    • Jan 2025Supercharge vector search with ColBERT rerank in PostgreSQL

    arXiv ↗
21. 696
    

    LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

    Valeriia Cherepanova et al. · 2021

    Hacker News threads

    • Jan 2021LowKey web app tweaks images to thwart facial recognition systems
    • Feb 2021Adversarial.io – Fighting mass image recognition
    • Apr 2021Ask HN: Amyone successfully verify fawkes claims of protection against AI?

    arXiv ↗
22. 697
    

    CvT: Introducing Convolutions to Vision Transformers

    Haiping Wu et al. · 2021

    Hacker News threads

    • Mar 2022Transformers, originally designed to handle language, are taking on vision
    • Jul 2022
    • Dec 2025The Illustrated Transformer

    arXiv ↗
23. 698
    

    Escaping the Big Data Paradigm with Compact Transformers

    Ali Hassani et al. · 2021

    Hacker News threads

    • Mar 2022Transformers, originally designed to handle language, are taking on vision
    • Dec 2023Deep Dive into the Vision Transformers Paper (ViT)
    • Jul 2025FastVLM: Efficient Vision Encoding for Vision Language Models

    arXiv ↗
24. 699
    

    Addressing "Documentation Debt" in Machine Learning Research: A Retrospective Datasheet for BookCorpus

    Jack Bandy, Nicholas Vincent · 2021

    Hacker News threads

    • Feb 2023Ask HN: Does Google use the text inside gdocs and Gmail for training AI models?
    • Jul 2023The Pile: a dataset for language modeling [pdf]
    • Sep 2023

    arXiv ↗
25. 700
    

    TruthfulQA: Measuring How Models Mimic Human Falsehoods

    Stephanie Lin et al. · 2021

    Hacker News threads

    • Oct 2021Dublin Core's dirty little secret (2010)
    • Feb 2023ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT
    • Aug 2026If this is true, the hyperscalers are toast

    arXiv ↗

Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.