🌊 Diffusion models - matan · Scour

NOEM: efficient and scalable finite element method enabled by reusable neural operators 🤖AI

·2d·Hacker News

Show HN: WaveletLM – wavelet-based, attention-free model with O(n log n) scaling 🔄Transformers

github.com·4d·Hacker News

Why Model Collapse in LLMs is Inevitable With Self-Learning 🎲Bayesian Cognition

hackaday.com·20h·Hacker News

Meta-Harness: End-to-End Optimization of Model Harnesses 🔄Transformers

Show HN: "Be horse." – a diffusion language model on an M2 Air 🔄Transformers

boesch.dev·1d·Hacker News

The Data Layer Tax for Robot Learning 🔄Transformers

rerun.io·9h·Hacker News

The Metropolis-Hastings algorithm 🎲Bayesian Cognition

blog.djnavarro.net·5d

Paper page - Large Language Models Explore by Latent Distilling 🔄Transformers

huggingface.co·7h

ODEs for attracting manifolds 🤖AI

kosti.bearblog.dev·2d

Getpal - extract a color palette from an image 🔤Font Rendering

bit-101.com·22h

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning 🔄Transformers

machinelearning.apple.com·1d·Hacker News

Which one is more important: more parameters or more computation? (2021) 🔄Transformers

parl.ai·6d·Hacker News

Distilling a Tiny Model for Fast Interpretability 🔄Transformers

ethanfast.substack.com·2d·Substack

What are embeddings? 🎨Computational Creativity

vickiboykis.com·4d

Show HN: I Built a Guide to the Manifold Shift in Mechanistic Interpretability 🎲Bayesian Cognition

aithoughtsarenotalwaysstraightlines.vercel.app·1d·Hacker News

Temporal Language Models 🔄Transformers

calcifercomputing.com·2d·Hacker News

There Will Be a Scientific Theory of Deep Learning 🔬AI Research

news.ycombinator.com·5d·Hacker News

A Post-Regression World 🎲Bayesian Cognition

signalintent.net·2d·Hacker News

The Policy Picks the Policy 🎲Bayesian Cognition

noise2signal.bearblog.dev·2d

Softmax, can you derive the Jacobian? And should you care? 🤖AI

idlemachines.co.uk·3d·Hacker News

Log in to enable infinite scrolling