🤖 Transformers - buckman · Scour

Transformers in NLP: How Self-Attention Replaced Recurrence and Changed Everything 🔄Transformer Models

Google Nested Learning Explained: Hope Architecture, Continual Learning, and the End of Frozen LLMs 🧠LLM Reasoning

aipapersacademy.com·7h

Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models 🤖Large Language Models

biorxiv.org·2d

Zero-Cost Transparent Semiotic Awareness for Frozen Language Models SRT-Adapter 🧠LLM Training

sublius.substack.com·8h·Substack

Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis 🔄Transformer Models

proceedings.neurips.cc·2d

Transformers 🤖Transformer Architecture

chizkidd.github.io·4d·Hacker News

What is an LLM? A Guide on Large Language Models and How They Work 🧠LLM

datacamp.com·4d

The Sequence Knowledge #846: Beyond Transformer: A New Series 🤖Transformer Architecture

substackcdn.com·5d·Substack

Explore LLM word representations using similarity analysis (part 1) 🧠LLM

thepalindrome.org·4d

How AI Is Evolving: From Large Language Models to Agentic Intelligence 🤖GenAI

en.tempo.co·5d

ml-intern ⚙️ML Infrastructure

producthunt.com·5d

Watch language models think. ✍️Prompt Engineering

openinterp.org·3d·Hacker News

What makes gpt-image-2 so good? Is the architecture of the training sets? 🧠Deep Learning

news.ycombinator.com·4d·Hacker News

Parallel Token Prediction for Language Models ⚡Inference

justuswill.com·4d·Hacker News

Language Modeling Without Neural Networks 🤖Large Language Models

nathan.rs·6d·Hacker News

Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution 🏛Sovereign AI Infrastructure

media.licdn.com·6d

LibratioAI/sessa: Official PyTorch implementation of Sessa: Selective State Space Attention for long-context sequence modeling. 🔥PyTorch

github.com·3d·Hacker News

Can Large Language Models Understand Context? 🤖Large Language Models

machinelearning.apple.com·6d

My 12-Week Plan to Actually Understand AI ✍️Prompt Engineering

shobhitshri.substack.com·6d·Substack

Constituent-constrained word prediction during language comprehension 🧠LLM Training

·5d

Log in to enable infinite scrolling