Related papers: On Geometry of Interaction for Polarized Linear Lo…
Long-range electrostatics and polarization remain central obstacles to extending machine learning interatomic potentials (MLIPs) to ionic, polar, and interfacial systems. Here, we introduce a semi-local framework for learning electrostatics…
A focused proof system provides a normal form to cut-free proofs that structures the application of invertible and non-invertible inference rules. The focused proof system of Andreoli for linear logic has been applied to both the proof…
Multimodal Large Language Models (MLLMs) have emerged as powerful tools for chart comprehension. However, they heavily rely on extracted content via OCR, which leads to numerical hallucinations when chart textual annotations are sparse.…
Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate…
Modal logics have proved useful for many reasoning tasks in symbolic artificial intelligence (AI), such as belief revision, spatial reasoning, among others. On the other hand, mathematical morphology (MM) is a theory for non-linear analysis…
Large language models (LLMs) possess vast semantic knowledge but often struggle with complex reasoning tasks, particularly in relational reasoning problems such as kinship or spatial reasoning. In this paper, we present Path-of-Thoughts…
Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often…
A categorical model of the multiplicative and exponential fragments of intuitionistic linear logic ($\mathsf{MELL}$), known as a \emph{linear category}, is a symmetric monoidal closed category with a monoidal coalgebra modality (also known…
This article introduces the "Goldilocks model" for a few repulsively interacting particles trapped in a one-dimensional harmonic well and provides exact solutions for the three-particle case. The Goldilocks model shares features with two…
Partially Observable Markov Decision Processes (POMDPs) are a powerful framework for planning under uncertainty. They allow to model state uncertainty as a belief probability distribution. Approximate solvers based on Monte Carlo sampling…
Zero-shot Human-object interaction (HOI) detection aims to locate humans and objects in images and recognize their interactions. While advances in open-vocabulary object detection provide promising solutions for object localization,…
Recent urbanization has coincided with the enrichment of geotagged data, such as street view and point-of-interest (POI). Region embedding enhanced by the richer data modalities has enabled researchers and city administrators to understand…
Deductive verification techniques based on program logics (i.e., the family of Floyd-Hoare logics) are a powerful approach for program reasoning. Recently, there has been a trend of increasing the expressive power of such logics by…
Usually a name of the category is inherited from the name of objects. However more relevant for a category of objects and morphisms is an algebra of morphisms. Therefore we prefer to say a category of graphs if every morphism is a graph. In…
Multimodal large language models (MLLMs) are designed to process and integrate information from multiple sources, such as text, speech, images, and videos. Despite its success in language understanding, it is critical to evaluate the…
In the logic programming paradigm, a program is defined by a set of methods, each of which can be executed when specific conditions are met during the current state of an execution. The semantics of these programs can be elegantly…
Eye-tracking data reveals valuable insights into users' cognitive states but is difficult to analyze due to its structured, non-linguistic nature. While large language models (LLMs) excel at reasoning over text, they struggle with temporal…
Multi-turn instruction following is essential for building intelligent conversational systems that can consistently adhere to instructions across dialogue turns. However, existing approaches to enhancing multi-turn instruction following…
Mathematical geometric reasoning is essential for scientific discovery and educational development, requiring precise logic and rigorous formal verification. While recent advances in Multimodal Large Language Models (MLLMs) have improved…
Mathematical reasoning is a hallmark of human intelligence, requiring logical deduction, symbolic manipulation, and abstract thinking. Recent multimodal large language models (MLLMs) have demonstrated strong performance on geometry problems…