Related papers: Modernizing SMT-Based Type Error Localization

Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and one-stage end-to-end architectures, suffer from different…

Large Language Models (LLMs) excel at problem solving by generating chain of thoughts in natural language, but such verbal thinking is computationally costly and prone to overthinking. A recent work instead proposes a latent thinking…

Large language models (LLMs) are increasingly being applied to black-box optimization tasks, from program synthesis to molecule design. Prior work typically leverages in-context learning to iteratively guide the model towards better…

We present a prescriptive type system with parametric polymorphism and subtyping for constraint logic programs. The aim of this type system is to detect programming errors statically. It introduces a type discipline for constraint logic…

Issue localization, the process of identifying code locations that need modification to resolve software issues, is a critical yet challenging task in software development. The semantic gap between natural language issue descriptions and…

Modern stochastic optimization pipelines increasingly rely on learned generative models to represent uncertainty, while downstream decisions are evaluated almost entirely through Monte Carlo scenarios. This shifts the operational object of…

In this paper, we consider a fundamental problem in modern digital communications known as multi-input multi-output (MIMO) detection, which can be formulated as a complex quadratic programming problem subject to unit-modulus and discrete…

Macro embedding is a popular approach to defining extensible shallow embeddings of object languages in Scheme like host languages. While macro embedding has even been shown to enable implementing extensible typed languages in systems like…

Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs still contain multiple errors. Importantly, feeding back such…

In this paper we present a new Turbo analog error correcting coding scheme for real valued signals that are corrupted by impulsive noise. This Turbo code improves Donoho's deterministic construction by using a probabilistic approach. More…

Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consistency sampling, these advances often focus on final correctness…

LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is hindered by…

Text Style Transfer (TST) is performable through approaches such as latent space disentanglement, cycle-consistency losses, prototype editing etc. The prototype editing approach, which is known to be quite successful in TST, involves two…

Benefits of static type systems are well-known: they offer guarantees that no type error will occur during runtime and, inherently, inferred types serve as documentation on how functions are called. On the other hand, many type systems have…

Large language models (LLMs) exhibit remarkable capabilities in handling natural language tasks; however, they may struggle to consistently follow complex instructions including those involve multiple constraints. Post-training LLMs using…

Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples from the target domain. In this work, we tackle the fully…

We propose a novel methodology (namely, MuLER) that transforms any reference-based evaluation metric for text generation, such as machine translation (MT) into a fine-grained analysis tool. Given a system and a metric, MuLER quantifies how…

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Large language models often suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages. This critically degrades the user experience, especially in low-resource settings. We…

We present mstlo (mistletoe), a Rust library for high-performance online monitoring of signal temporal logic (STL), with Python bindings. The library provides: (i) a unified interface for multiple STL semantics, including Robust…