Hacker Papers
- 726
Scalable Diffusion Models with Transformers
Hacker News threads
- Aug 2023Diffusion Transformer
- Feb 2024Sora: Creating video from text
- Feb 2024Stable Diffusion 3
- May 2025Gemini Diffusion
- Jun 2025Normalizing Flows Are Capable Generative Models
- 727
Persistent Pre-Training Poisoning of LLMs
Hacker News threads
- 728
Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
Hacker News threads
- 729
How Community Feedback Shapes User Behavior
Hacker News threads
- 730
Show and Tell: A Neural Image Caption Generator
Hacker News threads
- 731
Deep Learning and the Information Bottleneck Principle
Hacker News threads
- Nov 2016Ask HN: What projects are you currently working on?
- Nov 2016Exact mapping between Variational Renormalization Group and Deep Learning (2014)
- Nov 2016Exact mapping between Variational Renormalization Group and Deep Learning (2014)
- May 2018Why does deep and cheap learning work so well?
- Aug 2023Do Machine Learning Models Memorize or Generalize?
- 732
A Tour of Reinforcement Learning: The View from Continuous Control
Hacker News threads
- 733
Semantic Image Synthesis with Spatially-Adaptive Normalization
Hacker News threads
- 734
Mission Apollo: Landing Optical Circuit Switching at Datacenter Scale
Hacker News threads
- 735
A Length-Extrapolatable Transformer
Hacker News threads
- 736
Large Language Model Guided Tree-of-Thought
Hacker News threads
- 737
ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
Hacker News threads
- 738
Multiplying Matrices Without Multiplying
Hacker News threads
- Sep 2021Multiplying Matrices Without Multiplying
- Jun 2021Multiplying Matrices Without Multiplying
- Jun 2022Bolt: Faster matrix and vector operations that run on compressed data
- Jun 2022Bolt: Faster matrix and vector operations that run on compressed data
- Nov 2023Show HN: Stella Nera – Maddness Hardware Accelerator
- May 2024Reproducing GPT-2 in llm.c
- 739
Demystifying Differentiable Programming: Shift/Reset the Penultimate Backpropagator
Hacker News threads
- Feb 2020Demystifying Differentiable Programming (2018)
- May 2018Demystifying Differentiable Programming (2018)
- Aug 2019Demystifying Differentiable Programming: Shift/Reset, Penultimate Backpropagator
- Nov 2018Automatic Differentiation in Machine Learning: A Survey [pdf]
- Feb 2019What Is Differentiable Programming?
- Feb 2019What Is Differentiable Programming?
- Feb 2021Swift for TensorFlow Shuts Down
- 740
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
Hacker News threads
- Apr 2024Sophia: Scalable Stochastic 2nd-Order Optimizer for Language Model Pre-Training
- May 2023Sophia: A Scalable Stochastic Second-Order Optimizer
- Jul 2023Sophia: A Scalable Stochastic Optimizer for Language Model Pre-Training
- May 2023MITx Differential Equations starts May 31
- Jun 2023Notes on training BERT from scratch on an 8GB consumer GPU
- Jun 2023Notes on training BERT from scratch on an 8GB consumer GPU
- Aug 2023Risky Giant Steps Can Solve Optimization Problems Faster
- 741
A Comprehensive Survey on Graph Neural Networks
Hacker News threads
- Jan 2019A Comprehensive Survey on Graph Neural Networks (2019)
- Jan 2019Graph Neural Networks: A Review of Methods and Applications
- Feb 2020Graph Neural Networks – An Overview
- Feb 2020Graph Neural Networks – An Overview
- May 2022Beyond message passing: A physics-inspired paradigm for graph neural networks
- 742
That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design
Hacker News threads
- Nov 2024That Chip Has Sailed: Critique of Unfounded Skepticism Around AI for Chip Design
- Nov 2024A Critique of Unfounded Skepticism Around AI for Chip Design
- Nov 2024AI Alone Isn't Ready for Chip Design
- Nov 2024AI Alone Isn't Ready for Chip Design
- Dec 2024Jeff Dean responds to EDA industry about AlphaChip
- Dec 2024Jeff Dean responds to EDA industry about AlphaChip
- Feb 2025Accelerating scientific breakthroughs with an AI co-scientist
- 743
Constructor Theory of Information
Hacker News threads
- May 2014Constructor Theory of Information
- Nov 2014Constructor Theory of Information
- Mar 2019Constructor Theory of Information
- May 2014A New “Theory of Everything”: Reality Emerges from Cosmic Copyright Law
- May 2014A New “Theory of Everything”: Reality Emerges from Cosmic Copyright Law
- Dec 2014Wave-particle duality is the uncertainty principle in disguise
- Apr 2021How to Rewrite the Laws of Physics in the Language of Impossibility
- 744
egg: Fast and Extensible Equality Saturation
Hacker News threads
- Oct 2020egg: Fast and Extensible E-graphs
- Mar 2021Reflections on IDEA vs VS Code
- Jul 2022Ask HN: What are some cool but obscure data structures you know about?
- Jul 2022Ask HN: What are some cool but obscure data structures you know about?
- Dec 2023Atree: A simple and efficient pointer-free tree implementation
- 745
Are Delayed Issues Harder to Resolve? Revisiting Cost-to-Fix of Defects throughout the Lifecycle
Hacker News threads
- Sep 2017Revisiting Cost-To-Fix of Defects Throughout the Lifecycle
- Apr 2019Are Delayed Issues Harder to Resolve? [pdf]
- Sep 2017The Cost of Skipping TDD and Code Reviews (2016)
- Sep 2017The Cost of Skipping TDD and Code Reviews (2016)
- Jul 2021The “bugs are 100x more expensive to fix in production” study might not exist
- Feb 2025Clean Code vs. A Philosophy Of Software Design
- 746
Constant Velocity Physical Warp Drive Solution
Hacker News threads
- May 2024Constant Velocity Physical Warp Drive Solution
- May 2024Constant Velocity Physical Warp Drive Solution
- May 2024Constant Velocity Physical Warp Drive Solution
- May 2024
- Jul 2024New study simulates gravitational waves from failing warp drive
- Jul 2024New study simulates gravitational waves from failing warp drive
- Nov 2024Congress hears testimony on aliens
- 747
Communication-Efficient Learning of Deep Networks from Decentralized Data
Hacker News threads
- May 2017Communication-Efficient Learning of Deep Networks from Decentralized Data
- Apr 2017Machine learning without centralized training data
- Apr 2017Machine learning without centralized training data
- Dec 2020Does GPT-2 Know Your Phone Number?
- Apr 2023Thumb-Key: a privacy-conscious smart keyboard, made specifically for your thumbs
- 748
Achieving Human Parity in Conversational Speech Recognition
Hacker News threads
- Oct 2016Achieving Human Parity in Conversational Speech Recognition
- Oct 2016Researchers reach human parity in conversational speech recognition
- Oct 2016Researchers reach human parity in conversational speech recognition
- Aug 2017Conversational Speech Recognition System [pdf]
- Oct 2020AI outperforms humans in speech recognition
- 749
Lower Bounds for Multiplication via Network Coding
Hacker News threads
- Mar 2019Lower bounds for the cost of multiplication via network coding
- Mar 2019Integer multiplication in time O(n log n) [pdf]
- Apr 2019Mathematicians Discover the Perfect Way to Multiply
- Jul 2020Mathematicians discover a perfect way to multiply (2019)
- Jul 2020Mathematicians discover a perfect way to multiply (2019)
- 750
ZeRO-Offload: Democratizing Billion-Scale Model Training
Hacker News threads
- Feb 2021Zero-Offload: Democratizing Billion-Scale Model Training
- Mar 2021Zero-3 Offload: Scale DL models to trillion parameters without code changes
- Mar 2021Zero-3 Offload: Scale DL models to trillion parameters without code changes
- May 2023Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
- Oct 2023Why async gradient update doesn't get popular in LLM community?
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.