Related papers: Kernel Contracts: A Specification Language for ML …
Kernels are powerful and versatile tools in machine learning and statistics. Although the notion of universal kernels and characteristic kernels has been studied, kernel selection still greatly influences the empirical performance. While…
Large Language Models are essential coding assistants, yet their training is predominantly English-centric. In this study, we evaluate the performance of code language models in non-English contexts, identifying challenges in their adoption…
Language models that can learn a task at inference time, called in-context learning (ICL), show increasing promise in natural language inference tasks. In ICL, a model user constructs a prompt to describe a task with a natural language…
Reusable software components need expressive specifications. This paper outlines a rigorous foundation to model-based contracts, a method to equip classes with strong contracts that support accurate design, implementation, and formal…
Kernel functions are vital ingredients of several machine learning algorithms, but often incur significant memory and computational costs. We introduce an approach to kernel approximation in machine learning algorithms suitable for…
Public development processes are a key characteristic of open source projects. However, fixes for vulnerabilities are usually discussed privately among a small group of trusted maintainers, and integrated without prior public involvement.…
As modern machine learning models continue to advance the computational frontier, it has become increasingly important to develop precise estimates for expected performance improvements under different model and data scaling regimes.…
The problem of error correction in both coherent and noncoherent network coding is considered under an adversarial model. For coherent network coding, where knowledge of the network topology and network code is assumed at the source and…
Large Language Models (LLMs) have achieved state-of-the-art performance across software engineering tasks, from code generation to translation. However, we identify and systematically evaluate a critical failure mode: Programming Language…
We propose a new family of specification tests called kernel conditional moment (KCM) tests. Our tests are built on a novel representation of conditional moment restrictions in a reproducing kernel Hilbert space (RKHS) called conditional…
LLM-based agents for GPU kernel generation are advancing rapidly, yet their progress is fundamentally constrained by the benchmarks they optimize against. Existing benchmarks are poorly aligned with production inference frameworks: they…
Smart contracts on a blockchain behave precisely as specified by their code. A vulnerability in this code can lead to unexpected behaviour, which is hard to fix because a blockchain does not allow to change smart contract code after its…
The use of kernels for nonlinear prediction is widespread in machine learning. They have been popularized in support vector machines and used in kernel ridge regression, amongst others. Kernel methods share three aspects. First, instead of…
In this paper we present a framework to analyze conflicts of contracts written in structured English. A contract that has manually been rewritten in a structured English is automatically translated into a formal language using the…
Agentic security systems increasingly combine LLM planners with tools that can discover, validate, and report vulnerabilities. This creates an asymmetric control problem: the system should retain strong offensive capability inside an…
Large Language Models (LLM) are increasingly used for software development, yet existing benchmarks for LLM-based coding assistance do not reflect the constraints of High Energy Physics (HEP) and High Performance Computing (HPC) software.…
This paper studies the statistical complexity of kernel hyperparameter tuning in the setting of active regression under adversarial noise. We consider the problem of finding the best interpolant from a class of kernels with unknown…
Large Language Models (LLMs) have demonstrated remarkable capabilities in code understanding and generation. However, their effectiveness on non-code Software Engineering (SE) tasks remains underexplored. We present 'Software Engineering…
We are interested in mesh-free formulas based on the Monte-Carlo methodology for the approximation of multi-dimensional integrals, and we investigate their accuracy when the functions belong to a reproducing-kernel space. A kernel typically…
Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world applications often demand stricter adherence to detailed…