🔨 Compilers - matmat · Scour

Learning Reasoning World Models for Parallel Code ⚡Z3 Optimization

Less Is More: Measuring How LLM Involvement affects Chatbot Accuracy in Static Analysis ✅Formal Methods

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving ⚡Z3 Optimization

HARBOR: Automated Harness Optimization 🔗Topological Sorting

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training 📊Quantization

arxiv.org·2d·Hacker News

Pass i/m/s flags as parameters to Regex nodes ✅Format Verification

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding 🧠Neural Codecs

Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems 🧮Kolmogorov Complexity

Fable 5, F# compiler released 🦀Rust Macros

github.com·3d·Hacker News

tuures/LiteMarkup: Tiny Markdown-like parser with a typed, AST-first TypeScript API. Under 3 KB gzipped, zero dependencies. 📝Concrete Syntax

github.com·6d·Hacker News

Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs 🎯Performance Proofs

Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy 📼Cassette Combinators

LLM4C2Rust: Large Language Models for Automated Memory-Safe Code Transpilation 🏗️Compiler Archaeology

SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution 🦀Rust Macros

LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL 📐Binary Grammars

VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation ⚡Circuit Verification

RECURSUM: Automated Code Generation for Recurrence Relations Exceeds Expert Optimization via LayeredCodegen 🎯Performance Proofs

Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL 🔗Concatenative Programming

HELIX: Verified compilation of cyber-physical control systems to LLVM IR ⚖️RISC-V Formal

ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization 💻Local LLMs

Sign up or log in to see more results

Log in to enable infinite scrolling