Related papers: Parameterized Cast Calculi and Reusable Meta-theor…

Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on hard ones. We adapt Wald's Sequential Probability Ratio Test (SPRT) as a plug-in compute…

Stochastic iterative methods are useful in a variety of large-scale numerical linear algebraic, machine learning, and statistical problems, in part due to their low-memory footprint. They are frequently used in a variety of applications,…

In this work, we address question answering (QA) over a hybrid of tabular and textual data that are very common content on the Web (e.g. SEC filings), where discrete reasoning capabilities are often required. Recently, large language models…

Text-based automated Cognitive Distortion detection is a challenging task due to its subjective nature, with low agreement scores observed even among expert human annotators, leading to unreliable annotations. We explore the use of Large…

We propose Conformal Lie-group Action Prediction Sets (CLAPS), a symmetry-aware conformal prediction-based algorithm that constructs, for a given action, a set guaranteed to contain the resulting system configuration at a user-defined…

Recent advances in Transformer-based large language models (LLMs) have led to significant performance improvements across many tasks. These gains come with a drastic increase in the models' size, potentially leading to slow and costly use…

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…

Characterizing the patterns of errors that a system makes helps researchers focus future development on increasing its accuracy and robustness. We propose a novel form of "meta learning" that automatically learns interpretable rules that…

Emerging generative world models and vision-language-action (VLA) systems are rapidly reshaping automated driving by enabling scalable simulation, long-horizon forecasting, and capability-rich decision making. Across these directions,…

Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be…

The model checking problem for CTL is known to be P-complete (Clarke, Emerson, and Sistla (1986), see Schnoebelen (2002)). We consider fragments of CTL obtained by restricting the use of temporal modalities or the use of…

Previous work on controllable text generation has explored the idea of control from the latent space, such as optimizing a representation with attribute-related classifiers or sampling a representation from relevant discrete samples.…

There is an explosion of data, documents, and other content, and people require tools to analyze and interpret these, tools to turn the content into information and knowledge. Topic modeling have been developed to solve these problems.…

Methods based on weight compensation, which iteratively apply quantization and weight compensation to minimize the output error, have recently demonstrated remarkable success in quantizing Large Language Models (LLMs). The representative…

This paper considers parametricity and its consequent free theorems for nested data types. Rather than representing nested types via their Church encodings in a higher-kinded or dependently typed extension of System F, we adopt a functional…

In this article we propose and validate an unsupervised probabilistic model, Gaussian Latent Dirichlet Allocation (GLDA), for the problem of discrete state discovery from repeated, multivariate psychophysiological samples collected from…

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

Calibrated probability outputs of trained classifiers are increasingly used as inputs to downstream regression estimands such as effects, prevalences, or disparities for a latent group observed only on a small labelled subset. A standard…

Generalized metrics, arising from Lawvere's view of metric spaces as enriched categories, have been widely applied in denotational semantics as a way to measure to which extent two programs behave in a similar, although non equivalent, way.…

Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce…