Hacker News with Generative AI: Machine Learning

Simons Foundation Launches Collaboration on Ecological Neuroscience (simonsfoundation.org)
The newly launched Simons Collaboration on Ecological Neuroscience (SCENE) will unite leading scientists across neuroscience and machine learning to discover how the brain represents ‘sensorimotor’ (that is, sensory and motor) interactions.
Neuroscience, Machine Learning, Collaboration, Science
16 points by domofutu 6 hours ago | 1 comments
Lossless LLM compression for efficient GPU inference via dynamic-length float (arxiv.org)
Large Language Models (LLMs) have grown rapidly in size, creating significant challenges for efficient deployment on resource-constrained hardware.
Artificial Intelligence, Computer Science, Machine Learning, Compression
294 points by CharlesW 10 hours ago | 99 comments
Paper2Code: Automating Code Generation from Scientific Papers (arxiv.org)
Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce results and build upon prior work.
Machine Learning, Scientific Research, Code Generation, Reproducibility
91 points by Jerry2 11 hours ago | 11 comments
The Urgency of Interpretability (darioamodei.com)
In the decade that I have been working on AI, I’ve watched it grow from a tiny academic field to arguably the most important economic and geopolitical issue in the world.
Artificial Intelligence, Machine Learning, Ethics
14 points by jdkee 1 day ago | 1 comments
Docker Model Runner Brings Local LLMs to Your Desktop (thenewstack.io)
Docker, Generative AI, Machine Learning, Software
5 points by CrankyBear 1 day ago | 0 comments
Show HN: Lemon Slice Live – Have a video call with a transformer model (ycombinator.com)
Hey HN, this is Lina, Andrew, and Sidney from Lemon Slice. We’ve trained a custom diffusion transformer (DiT) model that achieves video streaming at 25fps and wrapped it into a demo that allows anyone to turn a photo into a real-time, talking avatar.
Generative AI, Machine Learning, Video, Artificial Intelligence, Demo
188 points by lcolucci 1 day ago | 80 comments
Show HN: High-performance GenAI engine now open source (github.com/arthur-ai)
Make AI work for Everyone - Monitoring and governing for your AI/ML
Generative AI, Open Source, Artificial Intelligence, Machine Learning
20 points by fryz 2 days ago | 12 comments
Double Descent Demystified: size of smallest non-zero singular value of X (arxiv.org)
Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever larger into the highly overparameterized (data undersampled) regime.
Machine Learning, Deep Learning, Mathematical Concepts
8 points by highfrequency 2 days ago | 1 comments
FontDiffuser: Text to Font (yeungchenwa.github.io)
Automatic font generation is an imitation task, which aims to create a font library that mimics the style of reference images while preserving the content from source images.
Font Generation, Artificial Intelligence, Machine Learning
26 points by SubiculumCode 2 days ago | 5 comments
Improving Deep Learning with a Little Help from Physics (quantamagazine.org)
Rose Yu has a plan for how to make AI better, faster and smarter — and it’s already yielding results.
Deep Learning, Artificial Intelligence, Physics, Machine Learning
10 points by marsh_mellow 2 days ago | 0 comments
"Periodic table of machine learning" could fuel AI discovery (news.mit.edu)
MIT researchers have created a periodic table that shows how more than 20 classical machine-learning algorithms are connected.
Machine Learning, Artificial Intelligence, Research, Algorithms, Science
17 points by mikhael 3 days ago | 4 comments
Yann LeCun "Mathematical Obstacles on the Way to Human-Level AI" (youtube.com)
Artificial Intelligence, Machine Learning, Computer Science, Yann LeCun
11 points by rramadass 3 days ago | 0 comments
Product Quantization: Compressing high-dimensional vectors by 97% (pinecone.io)
Machine Learning, Data Compression, Vector Databases
10 points by jxmorris12 3 days ago | 0 comments
π0.5: A VLA with open-world generalization (pi.website)
Robots have come a long way over the past few years—they can perform impressive acrobatic feats, dance on stage, follow language commands and, in some of our own results, perform complex tasks like folding laundry or cleaning off a table. But the biggest challenge in robotics is not in performing feats of agility or dexterity, but generalization: the ability to figure out how to correctly perform even a simple task in a new setting or with new objects.
Robotics, Artificial Intelligence, Machine Learning, Computer Vision
175 points by lachyg 3 days ago | 44 comments
Are polynomial features the root of all evil? (2024) (alexshtf.github.io)
It turns out that it’s just a MYTH. There’s nothing inherently wrong with high degree polynomials, and in contrast to what is typically taught, high degree polynomials are easily controlled using standard ML tools, like regularization. The source of the myth stems mainly from two misconceptions about polynomials that we will explore here. In fact, not only they are great non-linear features, certain representations also provide us with powerful control over the shape of the function we wish to learn.
Machine Learning, Data Science, Myths, Mathematics, Polynomial Regression
185 points by Areibman 3 days ago | 75 comments
Show HN: Morphik – Open-source RAG that understands PDF images, runs locally (github.com/morphik-org)
Morphik is an alternative to traditional RAG for highly technical and visual documents.
Open Source, RAG, PDF, Machine Learning, Software
193 points by Adityav369 4 days ago | 43 comments
Algebraic Semantics for Machine Knitting (uwplse.org)
As programming languages researchers, we’re entitled to a certain level of mathematical rigor behind the languages we write and analyze.
Computer Science, Programming Languages, Formal Methods, Machine Learning
243 points by PaulHoule 4 days ago | 19 comments
Introduction to Graph Transformers (kumo.ai)
Graphs are everywhere. From modeling molecular interactions and social networks to detecting financial fraud, learning from graph data is powerful—but inherently challenging.
Machine Learning, Data Science
43 points by gk1 4 days ago | 0 comments
Fox Succeeds in Scrapping Machine Learning Claims at CAFC Under 101 (ipwatchdog.com)
The U.S. Court of Appeals for the Federal Circuit (CAFC) on Friday addressed an issue of first impression in the patent eligibility context, holding that “claims that do no more than apply established methods of machine learning to a new data environment” are not patent eligible.
Law, Patents, Artificial Intelligence, Machine Learning
3 points by zoobab 4 days ago | 1 comments
Show HN: I'm 15 and built a neural network from scratch in C++,just math (github.com/muchlakshay)
A C++ implementation of a Multilayer Perceptron (MLP) neural network using Eigen, supporting multiple activation and loss functions, mini-batch gradient descent, and backpropagation for training.
Machine Learning, C++, Neural Networks
8 points by muchlakshay 4 days ago | 2 comments
Forecaster reacts: METR's bombshell paper about AI acceleration (peterwildeford.substack.com)
About a month ago, METR, an AI evaluations organization, published a bombshell graph and paper that says that AI is accelerating quickly. With OpenAI’s recent launch of o3 and o4-mini, we can see if these predictions hold up.
Artificial Intelligence, Machine Learning, Research, Predictions, OpenAI
49 points by nopinsight 4 days ago | 74 comments
Show HN: Keep your PyTorch model in VRAM by hot swapping code (github.com/valine)
This is an example of how to hotswap PyTorch training code without unloading your model weights from VRAM.
Machine Learning, PyTorch, Deep Learning, Software, Programming
77 points by valine 5 days ago | 7 comments
Pushing the Limits of LLM Quantization via the Linearity Theorem (arxiv.org)
Quantizing large language models has become a standard way to reduce their memory and computational costs.
Machine Learning, Artificial Intelligence, Optimization, Quantization
95 points by felineflock 6 days ago | 2 comments
Gemma 3 QAT Models: Bringing AI to Consumer GPUs (googleblog.com)
Last month, we launched Gemma 3, our latest generation of open models. Delivering state-of-the-art performance, Gemma 3 quickly established itself as a leading model capable of running on a single high-end GPU like the NVIDIA H100 using its native BFloat16 (BF16) precision.
Artificial Intelligence, Machine Learning, Hardware, Computer Vision, Open Source
597 points by emrah 6 days ago | 272 comments
Sparsely-Gated Mixture of Experts (MoE) (thegreenplace.net)
In transformer models, the attention block is typically followed by a feed forward layer (FF), which is a simple fully-connected NN with a hidden layer and nonlinearity.
Transformers, Deep Learning, Machine Learning, Computer Science
15 points by mfrw 6 days ago | 0 comments
Welcome to the Era of Experience [pdf] (googleapis.com)
Artificial Intelligence, Reinforcement Learning, Machine Learning
114 points by Siah 6 days ago | 52 comments
A curated blog for learning LLM internals: tokenize, attention, PE, and more (ycombinator.com)
I've been diving deep into the internals of Large Language Models (LLMs) and started documenting my findings.
Machine Learning, Deep Learning, Computer Science
6 points by zljdanceholic 6 days ago | 1 comments
Microsoft's "1‑bit" AI model runs on a CPU only, while matching larger systems (arstechnica.com)
Future AI might not need supercomputers thanks to models like BitNet b1.58 2B4T.
Artificial Intelligence, Computer Hardware, Machine Learning
8 points by moh_maya 6 days ago | 0 comments
Ask HN: What are the hottest areas of *non*-LLM AI work currently? (ycombinator.com)
10+ years ago, "AI" would likely refer to work in RL, evolutionary/genetic algorithms, etc.
Artificial Intelligence, Machine Learning, Research, Trends, Employment
15 points by dira3 7 days ago | 5 comments
Inferring the Phylogeny of Large Language Models (arxiv.org)
This paper introduces PhyloLM, a method adapting phylogenetic algorithms to Large Language Models (LLMs) to explore whether and how they relate to each other and to predict their performance characteristics.
Machine Learning, Generative AI, AI Research
68 points by weinzierl 7 days ago | 6 comments