Hacker Papers

1. 951
   

   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 ↗
2. 952
   

   Conflict-free Replicated Data Types (CRDTs)

   Nuno Preguiça et al. · 2018

   Hacker News threads

   • Jul 2021Faster CRDTs: An Adventure in Optimization
   • Mar 2022Making CRDTs Byzantine Fault Tolerant [pdf]
   • Dec 2022Ask HN: What are best patterns for events in distributed transactions?

   arXiv ↗
3. 953
   

   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 ↗
4. 954
   

   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 ↗
5. 955
   

   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 ↗
6. 956
   

   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 ↗
7. 957
   

   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 ↗
8. 958
   

   ZX-calculus for the working quantum computer scientist

   John van de Wetering · 2020

   Hacker News threads

   • Jun 2023Introduction to the ZX-Calculus
   • Jun 2024Category theory using string diagrams (2014)
   • Dec 2024A particle physics course for high-school students

   arXiv ↗
9. 959
   

   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 ↗
10. 960
    

    Pattern-defeating Quicksort

    Orson R. L. Peters · 2021

    Hacker News threads

    • Jul 2021Do Low-Level Optimizations Matter? (2020)
    • May 2023Ask HN: What is new in Algorithms / Data Structures these days?
    • Jun 202310~17x faster than what? A performance analysis of Intel x86-SIMD-sort (AVX-512)

    arXiv ↗
11. 961
    

    Memory-assisted prompt editing to improve GPT-3 after deployment

    Aman Madaan et al. · 2022

    Hacker News threads

    • Mar 2022GPT-3 can run code
    • Dec 2022Building a Virtual Machine Inside ChatGPT
    • Jan 2023What Is AGI-Hard

    arXiv ↗
12. 962
    

    Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

    Mitchell Wortsman et al. · 2022

    Hacker News threads

    • Dec 2024Beyond Gradient Averaging in Parallel Optimization
    • Mar 2026NanoGPT Slowrun: Language Modeling with Limited Data, Infinite Compute
    • Jun 2026Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model
    • Jun 2026Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model

    arXiv ↗
13. 963
    

    Flow Matching for Generative Modeling

    Yaron Lipman et al. · 2022

    Hacker News threads

    • May 2025Veo 3 and Imagen 4, and a new tool for filmmaking called Flow
    • Jun 2025Normalizing Flows Are Capable Generative Models
    • Jul 2026Show HN: Flow Matching model inference in C

    arXiv ↗
14. 964
    

    Efficiently Scaling Transformer Inference

    Reiner Pope et al. · 2022

    Hacker News threads

    • Jun 2023AudioPaLM: A Large Language Model That Can Speak and Listen
    • Jul 2023Chiplet ASIC supercomputers for LLMs like GPT-4
    • Feb 2024Groq runs Mixtral 8x7B-32k with 500 T/s

    arXiv ↗
15. 965
    

    Scaling Laws for Generative Mixed-Modal Language Models

    Armen Aghajanyan et al. · 2023

    Hacker News threads

    • Feb 2023Planning for AGI and Beyond
    • Mar 2023Google Releases Paper on Embodied LLM (562b parameters)
    • Apr 2025Liquid: Language models are scalable and unified multi-modal generators

    arXiv ↗
16. 966
    

    Visual Instruction Tuning

    Haotian Liu et al. · 2023

    Hacker News threads

    • Dec 2023Vowels and Diphthongs in Sperm Whales
    • Apr 2024Suggest HN: Rabbit r1 AI device for blind or visually impaired people?
    • May 2024PaliGemma: Open-Source Multimodal Model by Google

    arXiv ↗
17. 967
    

    Simple and Controllable Music Generation

    Jade Copet et al. · 2023

    Hacker News threads

    • Jun 2023MusicGen-Looper: Generate fixed-bpm loops from text prompts
    • Mar 2025Show HN: Sonauto API – Generative music for developers
    • Oct 2025Should LLMs just treat text content as an image?

    arXiv ↗
18. 968
    

    The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models

    Matthew Renze, Erhan Guven · 2024

    Hacker News threads

    • Mar 2025Sketch-of-Thought: Efficient LLM Reasoning
    • Apr 2026Talk like caveman
    • Jul 2026Autistic Caveman: Why use many token when correct token do trick

    arXiv ↗
19. 969
    

    LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks

    Subbarao Kambhampati et al. · 2024

    Hacker News threads

    • Oct 2024Use Prolog to improve LLM's reasoning
    • Apr 2025Chain of Recursive Thoughts: Make AI think harder by making it argue with itself
    • Dec 2025If you're going to vibe code, why not do it in C?

    arXiv ↗
20. 970
    

    OpenVLA: An Open-Source Vision-Language-Action Model

    Moo Jin Kim et al. · 2024

    Hacker News threads

    • Aug 2024OpenVLA: An Open-Source Vision-Language-Action Model
    • Nov 2024A Revolution in How Robots Learn
    • Jan 2025Nvidia bets on robotics to drive future growth

    arXiv ↗
21. 971
    

    Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

    Shengbang Tong et al. · 2024

    Hacker News threads

    • Jun 2024Cambrian-1 an Open, Vision-Centric Exploration of Multimodal LLMs
    • Jan 2025DeepSeek releases Janus Pro, a text-to-image generator [pdf]
    • Feb 2025Why LLMs still have problems with OCR

    arXiv ↗
22. 972
    

    LiCoEval: Evaluating LLMs on License Compliance in Code Generation

    Weiwei Xu et al. · 2024

    Hacker News threads

    • Apr 2025Cursor IDE support hallucinates lockout policy, causes user cancellations
    • Dec 2025Codex, Opus, Gemini try to build Counter Strike
    • Sep 2026Microsoft exec called AI scraping 'the largest theft of labor in human history'

    arXiv ↗
23. 973
    

    Deliberative Alignment: Reasoning Enables Safer Language Models

    Melody Y. Guan et al. · 2024

    Hacker News threads

    • May 2025Beyond Semantics: Unreasonable Effectiveness of Reasonless Intermediate Tokens
    • May 2026The Gay Jailbreak Technique
    • Jun 2026The US lifts its block on Mythos 5

    arXiv ↗
24. 974
    

    OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

    Jiacheng Liu et al. · 2025

    Hacker News threads

    • Apr 2025OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
    • May 2025Judge said Meta illegally used books to build its AI
    • Sep 2026On the Navier–Stokes Millennium Prize Problem

    arXiv ↗
25. 975
    

    ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems

    Francois Chollet et al. · 2025

    Hacker News threads

    • Jun 2025OpenAI o3-pro
    • Jul 2025New AI architecture delivers 100x faster reasoning with just 1,000 examples
    • Jul 2026Separating signal from noise in coding evaluations

    arXiv ↗

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