943 citations · 1.3k across the 21 of their papers we have counts for
21 papers
GraphWalk: Enabling Reasoning in Large Language Models through Tool-Based Graph Navigation
Taraneh Ghandi, Hamidreza Mahyar, Shachar Klaiman
The use of knowledge graphs for grounding agents in real-world Q&A applications has become increasingly common. Answering complex queries often requires multi-hop reasoning and the…
GraphSeek: Next-Generation Graph Analytics with LLMs
Maciej Besta, Łukasz Jarmocik, Orest Hrycyna +7
Graphs are foundational across domains but remain hard to use without deep expertise. LLMs promise accessible natural language (NL) graph analytics, yet they fail to process indust…
Demystifying Higher-Order Graph Neural Networks
Maciej Besta, Florian Scheidl, Lukas Gianinazzi +4
Higher-order graph neural networks (HOGNNs) and the related architectures from Topological Deep Learning are an important class of GNN models that harness polyadic relations betwee…
DocReader: Bounding-Box Free Training of a Document Information Extraction Model
Shachar Klaiman, Marius Lehne
Information extraction from documents is a ubiquitous first step in many business applications. During this step, the entries of various fields must first be read from the images o…
Variance of an anisotropic Bose-Einstein condensate
Shachar Klaiman, Raphael Beinke, Lorenz S. Cederbaum +2
The anisotropy of a trap potential can impact the density and variance of a Bose-Einstein condensate (BEC) in an opposite manner. We exemplify this effect for both the ground state…
Solvable Model of a Generic Trapped Mixture of Interacting Bosons: Many-Body and Mean-Field Properties at the Infinite-Particle Limit
S. Klaiman, A. I. Streltsov, O. E. Alon
A solvable model of a generic trapped bosonic mixture, bosons of mass and bosons of mass trapped in an harmonic potential of frequency and interacting b…