This paper evaluates the performance of large language models on popular benchmarks and finds that only a small percentage of the performant implementations are significantly faster than canonical sol…

The paper introduces CodeGolf Bench, a novel multi-language benchmark using code golf to measure LLMs' ability to generate highly concise and efficient code, showing that reasoning models significantl…

The paper introduces Grid Programs, a novel, Turing-complete model of computation where programs are two-dimensional arrangements of instructions, fundamentally departing from linear code structures.

The paper proposes Fuzzy-Function Programming and introduces Program-as-Weights (PAW), a compact, locally-executable neural artifact for everyday programming tasks.

This paper proposes a portable inlining-prediction framework for lightweight systems, using production compiler diagnostics, an extractor, and a trained predictor.

This paper presents a method for compressing matrices using a RePair straight-line program (SLP), allowing matrix-vector products with time and space proportional to the compressed size, and demonstra…

The paper proposes a generic memory framework for advanced static program analysis, supporting various memory behaviors from different programming languages using Abstract Interpretation theory.

The paper proposes the Communicating Finite Automata (CFA) abstraction and a framework for component program refactoring in large language model inference services, achieving significant speedup and r…

This paper tests the assumption of how NVIDIA GPUs handle warp divergence and finds that the cost remains stable and predictable despite architectural changes.

The paper introduces Spaghetti Architect, a tool that generates controlled code datasets for machine learning models by deliberately adding redundancy, messiness, and difficulty.

This paper presents Calf, a dependent type theory for cost verification, which synthesizes the physicist's and banker's views on amortized analysis using potential functions and credit annotations.

FPMoE introduces a sparse Mixture-of-Experts (MoE) architecture to improve functional code generation across multiple functional programming languages, achieving state-of-the-art performance with fewe…

This paper introduces Generalized Constraint Projection (GCP), a zero-annotation inference framework for dynamically typed languages, which separates sources of evidence for function parameters and pr…

The paper introduces REBench, a comprehensive, standardized benchmark dataset designed to enable fair and rigorous evaluation of Large Language Models (LLMs) on complex binary reverse engineering task…

The largest reported verification campaign for the Rust standard library is presented, integrating complementary tools and analyzing effectiveness.