Hacker Papers

1. 626
   

   Learning to Transduce with Unbounded Memory

   Edward Grefenstette et al. · 2015

   Hacker News threads

   • Jun 2015Learning to Transduce with Unbounded Memory
   • Jun 2015Learning to Transduce with Unbounded Memory (Google DeepMind) [pdf]
   • Dec 2015Teaching Machines to Read and Comprehend [pdf]
   • Jan 2016Differentiable Programming
   • Aug 2018Markov Chains Explained Visually (2014)

   arXiv ↗
2. 627
   

   Progressive Growing of GANs for Improved Quality, Stability, and Variation

   Tero Karras et al. · 2017

   Hacker News threads

   • Nov 2018Progressive Growing of GANs for Improved Quality, Stability, and Variation
   • Apr 2018A.I. Researchers Are Making More Than $1M, Even at a Nonprofit
   • Oct 2018Christie’s sells its first AI portrait for $432k
   • Nov 2023SDXL Turbo: A Real-Time Text-to-Image Generation Model

   arXiv ↗
3. 628
   

   REALM: Retrieval-Augmented Language Model Pre-Training

   Kelvin Guu et al. · 2020

   Hacker News threads

   • Feb 2020Realm: Retrieval-Augmented Language Model Pre-Training
   • Aug 2020Recent Advances in Natural Language Processing
   • Dec 2022How Does GPT Obtain Its Ability? Tracing Emergent Abilities of Language Models
   • Feb 2023Sundar Pichai: An important next step on our AI journey

   arXiv ↗
4. 629
   

   A Metric Learning Reality Check

   Kevin Musgrave et al. · 2020

   Hacker News threads

   • May 2020A Metric Learning Reality Check
   • May 2020A Deep Metric Learning Reality Check
   • May 2020A Metric Learning Reality Check
   • May 2020A complete 4-year course plan for an AI undergraduate degree
   • Jun 2020Stanford Class on Deep Multi-Task and Meta-Learning
   • Dec 2022Statistical vs. Deep Learning forecasting methods

   arXiv ↗
5. 630
   

   Measuring Mathematical Problem Solving With the MATH Dataset

   Dan Hendrycks et al. · 2021

   Hacker News threads

   • Nov 2021Measuring mathematical problem solving with the MATH dataset
   • Mar 2023Cerebras-GPT vs. LLaMA AI Model Performance Comparison
   • Oct 2023An AI Which Imitates Humans Can Beat Humans
   • Jan 2025Mistral Small 3

   arXiv ↗
6. 631
   

   Carbon Emissions and Large Neural Network Training

   David Patterson et al. · 2021

   Hacker News threads

   • May 2021Carbon Emissions and Large Neural Network Training
   • Jan 2022Carbon Emissions and Large Neural Network Training
   • Apr 2021Carbon Emissions and Large Neural Network Training
   • Apr 2021Google-led paper pushes back against claims of AI inefficiency
   • Oct 2021Small Language Models Are Also Few-Shot Learners
   • Jan 2022Deep physical neural networks trained with backpropagation

   arXiv ↗
7. 632
   

   Perceiver IO: A General Architecture for Structured Inputs & Outputs

   Andrew Jaegle et al. · 2021

   Hacker News threads

   • Aug 2021Perceiver IO: A General Architecture for Structured Inputs and Outputs
   • Apr 2025Perceiver IO: A General Architecture for Structured Inputs and Outputs (2021)
   • Sep 2021Has AI found a new foundation?
   • Nov 2021Permutation-Invariant Neural Networks for Reinforcement Learning
   • Jun 2023Bytes Are All You Need: Transformers Operating Directly on File Bytes

   arXiv ↗
8. 633
   

   Beyond neural scaling laws: beating power law scaling via data pruning

   Ben Sorscher et al. · 2022

   Hacker News threads

   • Aug 2022Beyond neural scaling laws: beating power law scaling via data pruning
   • Jul 2022Beyond neural scaling laws: beating power law scaling via data pruning
   • Jul 2022Google fires engineer who called its AI sentient
   • Dec 2022Copilot Internals
   • Mar 2026Microgpt

   arXiv ↗
9. 634
   

   TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

   Noah Hollmann et al. · 2022

   Hacker News threads

   • Oct 2022A Transformer That Solves Small Tabular Classification Problems in a Second
   • Aug 2022Why do tree-based models still outperform deep learning on tabular data?
   • Aug 2023Interpretable Graph Neural Networks for Tabular Data
   • Jan 2025Show HN: TabPFN v2 – A SOTA foundation model for small tabular data

   arXiv ↗
10. 635
    

    Hungry Hungry Hippos: Towards Language Modeling with State Space Models

    Daniel Y. Fu et al. · 2022

    Hacker News threads

    • Jan 2023Hungry Hungry Hippos: Towards Language Modeling with State Space Models
    • Jan 2023Towards Language Modeling With State Space Models
    • Feb 2023GraphGPT: Extrapolating knowledge graphs from unstructured text
    • Mar 2023We're never getting rid of ChatGPT
    • Apr 2025Bamba: An open-source LLM that crosses a transformer with an SSM

    arXiv ↗
11. 636
    

    The Poison of Alignment

    Aibek Bekbayev et al. · 2023

    Hacker News threads

    • Aug 2023The Poison of (LLMs) Alignment
    • Aug 2023The Poison of Alignment
    • Aug 2023The Poison of Alignment
    • Sep 2023Study shows over time, ChatGPT lost accuracy
    • Jun 2024Cost of self hosting Llama-3 8B-Instruct
    • Jan 2025DeepSeek's Hidden Bias: How We Cut It by 76% Without Performance Loss

    arXiv ↗
12. 637
    

    What Algorithms can Transformers Learn? A Study in Length Generalization

    Hattie Zhou et al. · 2023

    Hacker News threads

    • Feb 2024What Algorithms Can Transformers Learn? A Study in Length Generalization
    • Feb 2024Every model learned by gradient descent is approximately a kernel machine (2020)
    • Apr 2024What can LLMs never do?
    • Dec 2024Byte Latent Transformer: Patches Scale Better Than Tokens

    arXiv ↗
13. 638
    

    Power Hungry Processing: Watts Driving the Cost of AI Deployment?

    Alexandra Sasha Luccioni et al. · 2023

    Hacker News threads

    • Apr 2024Power Hungry Processing: Watts Driving the Cost of AI Deployment?
    • Dec 2023Making an image with generative AI uses as much energy as charging your phone
    • Feb 2024Paragraph Pollution: AI is (probably) greener than you typing on a laptop
    • Apr 2024When Will the GenAI Bubble Burst?

    arXiv ↗
14. 639
    

    LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench

    Karthik Valmeekam et al. · 2024

    Hacker News threads

    • Sep 2024LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of O1 on PlanBench
    • Sep 2024Apple No Longer in Talks to Join OpenAI Investment Round
    • Oct 2024Were RNNs all we needed?
    • Jan 2025Coconut by Meta AI – Better LLM Reasoning with Chain of Continuous Thought?

    arXiv ↗
15. 640
    

    Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

    Yang Yue et al. · 2025

    Hacker News threads

    • Apr 2025Does RL Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
    • Jun 2025Does Reinforcement Learning Incentivize Reasoning Capacity in LLMs?
    • May 2025GRPO experiment - I trained a Language Model to schedule events
    • Mar 2026Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem
    • Jul 2026Some thoughts about Anthropic's new cryptanalysis results

    arXiv ↗
16. 641
    

    A Taxonomy of Omnicidal Futures Involving Artificial Intelligence

    Andrew Critch, Jacob Tsimerman · 2025

    Hacker News threads

    • Jul 2026A Taxonomy of Omnicidal Futures Involving Artificial Intelligence
    • Jul 2026A Taxonomy of Omnicidal Futures Involving Artificial Intelligence (2025)
    • Jul 2026Fields Medals 2026
    • Sep 2026The Last 24 Hours Are the Opening Scene in a Horror Movie
    • Oct 2026LeCun has "zero concerns" about AI wiping out humanity, recent "rogue" incidents

    arXiv ↗
17. 642
    

    Bad Universal Priors and Notions of Optimality

    Jan Leike, Marcus Hutter · 2015

    Hacker News threads

    • Jun 2021Bad Universal Priors and Notions of Optimality (2015)
    • Aug 2021Fooling Neural Networks [pdf]
    • May 2024Ilya Sutskever to leave OpenAI
    • Nov 2024The $5000 Compression Challenge (2001)

    arXiv ↗
18. 643
    

    SSD: Single Shot MultiBox Detector

    Wei Liu et al. · 2015

    Hacker News threads

    • Nov 2016State of the Art Dnn. Single Shot MultiBox Detector
    • Nov 2017Using CNNs for Handbag Brand and Color Detection
    • Oct 2019Video Architecture Search
    • Feb 2020Creator of YOLO and SSD algorithm stopped CV research due to ethical concerns

    arXiv ↗
19. 644
    

    Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

    Anh Nguyen et al. · 2016

    Hacker News threads

    • Jun 2016Impressive synthesized images in new paper
    • Jun 2016Generative Models
    • Aug 2016Text to Image Synthesis Using Thought Vectors
    • May 2017Deep Learning’s Impact on Image Processing, Mathematics, and Humanity

    arXiv ↗
20. 645
    

    Understanding Black-box Predictions via Influence Functions

    Pang Wei Koh, Percy Liang · 2017

    Hacker News threads

    • Mar 2017Understanding Black-Box Machine Learning Predictions via Influence Functions
    • Jul 2021The Computer Scientist Training AI to Think with Analogies
    • Feb 2023Stable Attribution
    • Mar 2023Adobe Firefly: AI Art Generator

    arXiv ↗
21. 646
    

    Reformer: The Efficient Transformer

    Nikita Kitaev et al. · 2020

    Hacker News threads

    • Jan 2020Reformer: The Efficient Transformer
    • Jan 2020Standardizing OpenAI’s deep learning framework on PyTorch
    • Oct 2020Nilang.jl – A Reversible Julia DSL
    • May 2026SubQ: a sub-quadratic LLM with 12M-token context

    arXiv ↗
22. 647
    

    Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

    Yuntao Bai et al. · 2022

    Hacker News threads

    • Aug 2023Training a Helpful and Harmless Assistant with Reinforcement Learning from Human
    • Mar 2023Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA
    • Aug 2023The Poison of (LLMs) Alignment
    • Sep 2023Meta wants its open source AI model to be as capable as OpenAI’s best model

    arXiv ↗
23. 648
    

    Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding

    Zijiao Chen et al. · 2022

    Hacker News threads

    • Nov 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modelin
    • Nov 2022Reconstructing images a person sees via non-invasive brain scans
    • Feb 2023Real-Time Brain-to-Image Reconstructions
    • May 2023Brain Activity Decoder Can Reveal Stories in People’s Minds

    arXiv ↗
24. 649
    

    PAL: Program-aided Language Models

    Luyu Gao et al. · 2022

    Hacker News threads

    • Jan 2023Program Aided Language Models
    • Jan 2023GPT-3: Techniques to improve reliability
    • Mar 2023Oceania Always at War with Eastasia: Generative AI and Knowledge Pollution
    • Nov 2025Program-of-Thought Prompting Outperforms Chain-of-Thought by 15% (2022)

    arXiv ↗
25. 650
    

    Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

    Chengyi Wang et al. · 2023

    Hacker News threads

    • Jan 2023Neural Codec Language Models Are Zero-Shot Text to Speech Synthesizers
    • Jan 2023Will TTS and STT benefit from the AI boom?
    • Feb 2023I had ChatGPT write a Decemberists song
    • Sep 2024Amazon's Secret Weapon in Chip Design Is Amazon

    arXiv ↗

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