🧮 Algebraic Archives - matmat · Scour

There's a new $1 million prize to understand what happens inside LLMs: "Using AI models today is like alchemy: we can do seemingly magical things, but don't und...

withmartian.com·2d

✨Effect Handlers

Dynamic Boolean Synthesis with Zero-suppressed Decision Diagrams

arxiv.org·1d

⚙️Logic Synthesis

LLMs Are Lexical Thijarians

vinayprabhu.substack.com·3d·

Discuss: Substack

🌀Brotli Dictionary

Recent miscellany: 1D glider, flags, stripes, and telephony

quuxplusone.github.io·3d

🔲Cellular Automata

Choosing the Right RAG: Comparing the Most Common Retrieval-Augmented Generation Frameworks

dev.to·2d·

Discuss: DEV

📊Multi-vector RAG

Parameter-Efficient Fine-Tuning with Differential Privacy for Robust Instruction Adaptation in Large Language Models

arxiv.org·1d

How to Build an LLM-Powered Database Query Bot for Your Web App in 1 Day

semicolonandsons.com·3d·

Discuss: Hacker News

🗄️Database Internals

Small-Gain Nash: Certified Contraction to Nash Equilibria in Differentiable Games

arxiv.org·1d

🎯Performance Proofs

AI Application in Anti-Money Laundering for Sustainable and Transparent Financial Systems

arxiv.org·1d

🔍Vector Forensics

RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translation

arxiv.org·1d

Non-Intrusive Data-Free Parametric Reduced Order Model for Geometrically Nonlinear Structures

arxiv.org·1d

📐Linear Algebra

Mitigating the Antigenic Data Bottleneck: Semi-supervised Learning with Protein Language Models for Influenza A Surveillance

arxiv.org·2d

🧠Machine Learning

DAE-HardNet: A Physics Constrained Neural Network Enforcing Differential-Algebraic Hard Constraints

arxiv.org·2d

🌀Differential Geometry

DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems

arxiv.org·1d

Toward Reliable Machine Unlearning: Theory, Algorithms, and Evaluation

arxiv.org·1d

🧠Machine Learning

Show HN: Memory System for Claude Code and Other CLIs

github.com·5d·

Discuss: Hacker News

🌳Incremental Parsing

RAM Jam - why flocking together doesn’t mean you have to follow the herd.

dpconline.org·5d

🔄Archival Workflows

PlantBiMoE: A Bidirectional Foundation Model with SparseMoE for Plant Genomes

arxiv.org·1d

🔗Monadic Parsing

Mary, the Cheeseburger-Eating Vegetarian: Do LLMs Recognize Incoherence in Narratives?

arxiv.org·1d

💻Programming languages

Google outlines MIRAS and Titans, a possible path toward continuously learning AI

the-decoder.com·5d

🌀Brotli Internals

Loading more...