Related papers: JAX Autodiff from a Linear Logic Perspective (Exte…
Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in natural language. Recent works show that such models can also produce the reasoning steps (i.e., the…
Activity diagrams (ADs) have recently become widely used in the modeling of workflows, business processes, and web-services, where they serve various purposes, from documentation, requirement definitions, and test case specifications, to…
Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric…
Data-aware modal logics offer a powerful formalism for reasoning about semi-structured queries in languages such as DataGL, XPath, and GQL. In brief, these logics can be viewed as modal systems capable of expressing both reachability…
The open-source CARFAC (Cascade of Asymmetric Resonators with Fast-Acting Compression) cochlear model is upgraded to version 2, with improvements to the Matlab implementation, and with new Python/NumPy and JAX implementations -- but C++…
Taha and Nielsen have developed a multi-stage calculus {\lambda}{\alpha} with a sound type system using the notion of environment classifiers. They are special identifiers, with which code fragments and variable declarations are annotated,…
With a view towards models of quantum computation and/or the interpretation of linear logic, we define a functional language where all functions are linear operators by construction. A small step operational semantic (and hence an…
Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens from a fully masked sequence. Their standard confidence-based unmasking strategy systematically defers high-entropy logical connective tokens, degrading…
We define an extension of lambda-calculus with dependents types that enables us to encode transparent and opaque probabilistic programs and prove a strong normalisation result for it by a reducibility technique. While transparent…
Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and…
Linear autoencoders (LAEs) have gained increasing popularity in recommender systems due to their simplicity and strong empirical performance. Most LAE models, including the Emphasized Denoising Linear Autoencoder (EDLAE) introduced by…
We show how forward-mode automatic differentiation (AD) can be employed within larger reverse-mode computations to dynamically differentiate broadcast operations in a GPU-friendly manner. Our technique fully exploits the broadcast…
The evolution of Retrieval-Augmented Generation (RAG) has shifted from static retrieval pipelines to dynamic, agentic workflows where a central planner orchestrates multi-turn reasoning. However, existing paradigms face a critical…
Diffusion models have demonstrated remarkable success in image restoration tasks. However, their multi-step denoising process introduces significant computational overhead, limiting their practical deployment. Furthermore, existing methods…
Autoformalization is the task of automatically translating mathematical content written in natural language to a formal language expression. The growing language interpretation capabilities of Large Language Models (LLMs), including in…
In this paper, we demonstrate that the explicit ADER approach as it is used inter alia in [1] can be seen as a special interpretation of the deferred correction (DeC) method as introduced in [2]. By using this fact, we are able to embed…
The lambda calculus is a widely accepted computational model of higher-order functional pro- grams, yet there is not any direct and universally accepted cost model for it. As a consequence, the computational difficulty of reducing lambda…
Despite a growing body of work at the intersection of deep learning and formal languages, there has been relatively little systematic exploration of transformer models for reasoning about typed lambda calculi. This is an interesting area of…
Proofs (sequent calculus, natural deduction) and imperative algorithms (pseudocodes) are two well-known coexisting concepts. Then what is their relationship? Our answer is that \[ imperative\ algorithms\ =\ proofs\ with\ cuts \] This…
Asking a large language model to respond in JSON should be a formatting choice, not a capability tax. Yet we find that structured output requirements -- JSON, XML, LaTeX, Markdown -- substantially degrade reasoning and writing performance…