🧮 SMT Solvers

Z3, Constraint Satisfaction, Boolean Satisfiability, Theorem Proving, Mathematical Optimization

Java is a "Tower of Babel" language.
guidewiredevelopment.wordpress.com·1d·
Discuss: Substack
🔗Concatenative Programming
Incremental query updating in adhesive categories
topos.institute·4d
🔗Combinatory Logic
Why ML Needs a New Programming Language with Chris Lattner
signals-threads.simplecast.com·18h
🎵Audio ML
Every Implementable Algorithm Is Extensionally a Lookup Table
table.dk.workers.dev·3d·
Discuss: Hacker News
🔍Type Inference
Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts
bilawal.net·2d·
Discuss: Hacker News
💻Local LLMs
Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models
arxiv.org·11h
✨Effect Handlers
Do LLM Modules Generalize? A Study on Motion Generation for Autonomous Driving
arxiv.org·11h
🎙️Whisper
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
arxiv.org·11h
⚙️Compression Benchmarking
Show HN: CompareGPT – Making LLMs More Trustworthy by Reducing Hallucinations
news.ycombinator.com·1d·
Discuss: Hacker News
⚡Proof Automation
Generalized Golub-Kahan bidiagonalization for generalized saddle point systems
arxiv.org·11h
📐Linear Algebra
FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization
arxiv.org·11h
💻Local LLMs
Portable Targeted Sampling Framework Using LLVM
arxiv.org·11h
🎯Emulation Accuracy
DiVerify: Hardening Identity-Based Software Signing with Programmable Diverse-Context Scopes
arxiv.org·11h
🔐PKI Archaeology
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
arxiv.org·11h
💨Cache Analysis
NeurStore: Efficient In-database Deep Learning Model Management System
arxiv.org·11h
🗂️Vector Databases
PromptOp – Your AI Lab in One Platform
dev.to·1d·
Discuss: DEV
🔍Concolic Testing
Code Wars - 6kyu 'Split Strings' solution in Python
dev.to·17h·
Discuss: DEV
🧪Binary Fuzzing
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
arxiv.org·11h
🏛Digital humanities
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
arxiv.org·3d
🤖Grammar Induction
Hidden Convexity in Active Learning: A Convexified Online Input Design for ARX Systems
arxiv.org·11h
🧠Machine Learning