ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “compositionality”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.DBcs.LOcs.PLTheoreticalRecentJun 22, 2026

A Compositional Language for Property Graphs

Marcelo Arenas, Leonid Libkin, Wim Martens

The paper proposes a solution to the lack of compositionality in graph query languages GQL and SQL/PGQ.

View →
cs.ITcs.GTeess.SPTheoreticalRecentJul 20, 2026

Compositional Semantic Communication for Physical AI: Category Theory Meets Game Theory

Christo Kurisummoottil Thomas, Walid Saad, Emilio Calvanese Strinati

This paper proposes a framework for compositional semantic communication (CSC) in physical AI systems, enabling heterogeneous devices to transmit semantic representations that compose meaningfully at…

View →
cs.PLTheoreticalRecentJun 21, 2026

Compositional Generator Equivalence (Extended Version)

Anthony Vandikas, Kiarash Sotoudeh, Marsha Chechik

This paper formalizes the semantics of a popular property-based testing framework and introduces a restricted version with a compositional semantics.

View →
cs.LGcs.AIcs.NEEmpiricalRecentJun 16, 2026

Dimensionality Controls When Modularity Helps in Continual Learning

Kathrin Korte, Christian Medeiros Adriano, Joachim Winther Pedersen, Eleni Nisioti +1 more

This paper studies how modular architecture and representational dimensionality affect compositional continual learning in a sequential A-B-A paradigm.

View →
stat.MLcs.LGTheoreticalRecentJul 7, 2026

A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel

Arkaprabha Ganguli, Emil Constantinescu

This paper characterizes the gap between neural network performance and their neural tangent kernel limit on compositional tasks, attributing it to a mismatch between kernel smoothness bias and target…

View →
cs.LGcs.AIRecentMay 27, 2026

Learning Compositional Latent Structure with Vector Networks

Niclas Pokel, Benjamin F. Grewe

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

View →
cs.MMcs.SEEmpiricalRecentJun 22, 2026

Composition: Building Community with Arts, Math, and Code (Experience Report)

Isidore Mohr, Claire Wang

This paper reports on the Composition event series, covering its structure, artist selection process, outreach efforts, and community response.

View →
cs.AIcs.CLRecentMay 28, 2026

Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents

Anany Kotawala

The paper introduces a metric, the compositional residual eps*, to quantify how multi-component LLM agents violate basic probability axioms when combining local, coherent claims into a global predicti…

View →
cs.CLEmpiricalRecentJul 16, 2026

Language Identification via Compositional Data Analysis: A Linear-Time Classifier Based on Log-Ratio Geometry

Paul-Andrei Pogăcean, Sanda-Maria Avram

This paper proposes a method for language identification using compositional vectors and the centered log-ratio transformation, achieving robust accuracy and strong performance for longer sequences.

View →
cs.PLcs.CRApr 20, 2026

Compositional security definitions for higher-order where declassification

Jan Menz, Andrew K. Hirsch, Peixuan Li, Deepak Garg

The paper develops a compositional security definition for 'where declassification' in higher-order programs, allowing formal guarantees that private data is handled correctly when it is explicitly de…

View →
cs.CCcs.DMTheoreticalRecentJul 9, 2026

The Parameterised Complexity of Temporal Motif Counting, and a Lovász-Style Isomorphism Theorem

Jayakrishnan Madathil, Kitty Meeks, Marc Roth

This paper studies the structural expressivity and parameterized complexity of counting homomorphisms from small temporal patterns to large temporal graphs, proving a temporal Lovász-style theorem, in…

View →
math.COcs.DMmath.CTTheoreticalRecentJul 9, 2026

Subword representations and weak hypercube dimension for acyclic categories

Isaac Carcacía-Campos

This paper introduces a new way to represent finite posets as subwords of finite words in categories, and characterizes the monic categories that admit this representation.

View →
cs.PLEmpiricalRecentOct 25, 2026

PastaLean: Deterministic transpilation from Python to Lean for Verification

Anirudh Gupta, Petros Markopoulos, Siddhartha Gadgil

PastaLean system translates Python code to Lean for verification and provides static typing support for untyped Python code.

View →
cs.CLRecentMay 28, 2026

COMPOSE: Composing Future Theorems from Citations and Formal Structure

David Busbib, Michael Werman

The paper introduces COMPOSE, a dual-graph framework that generates plausible future mathematical theorems by simultaneously conditioning a language model on both the scientific citation context and t…

View →
cs.CRcs.AIcs.CVMar 20, 2026

CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models

Junhoo Lee, Mijin Koo, Nojun Kwak

The paper introduces Compositional Semantic Fingerprinting (CSF), a black-box method that allows IP owners to attribute fine-tuned text-to-image models to their protected lineages using only query acc…

View →
cs.AIcs.CLEmpiricalRecentJul 8, 2026

RL Post-Training Builds Compositional Reasoning Strategies

Azwar Abdulsalam, Nishil Patel, Andrew Saxe

This paper investigates whether RL enhances existing skills or creates new strategies in a rewrite-grammar environment. It shows that RL reorganizes primitive competence into valid compositional proce…

View →
cs.CLRecentMay 29, 2026

Language Models Can Resolve Reference Compositionally, But It's Not Their Native Strength: The Case of the Personal Relation Task

Bart Evelo, Meaghan Fowlie, Denis Paperno

The paper investigates compositional abilities in LLMs and humans using the Personal Relation Task, finding that LLMs excel at the structured (Intensional) task while humans are better at the real-wor…

View →
stat.MLcs.LGmath.STEmpiricalRecentJun 22, 2026

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

Sehwan Kim, Yan Sun, Faming Liang

Sublinearly structured DNNs achieve feature-learning and prediction consistency comparable to classical models

View →