2 citations · 2 across the 5 of their papers we have counts for
6 papers
ARdena: Scenario-driven control of real-time LLM agents
Luka Borozan, Domagoj Matijević
Large language models (LLMs) have enabled increasingly capable conversational agents, but reliably controlling their behavior in real-time interactive environments remains a signif…
Learning to Place Guards by Reinforcement: A Geo-Free Neural Policy for the Vertex-Guard Art Gallery Problem
Domagoj Ševerdija, Jurica Maltar, Nathan Chappel +1
Neural combinatorial optimization (NCO) has shown that policies trained by reinforcement can construct strong solutions to NP-hard problems directly from raw instances. What such a…
Compressing Sentence Representation with maximum Coding Rate Reduction
Domagoj Ševerdija, Tomislav Prusina, Antonio Jovanović +3
In most natural language inference problems, sentence representation is needed for semantic retrieval tasks. In recent years, pre-trained large language models have been quite effe…
Anti Tai Mapping for Unordered Labeled Trees
Mislav Blažević, Stefan Canzar, Khaled Elbassioni +1
The well-studied Tai mapping between two rooted labeled trees and defines a one-to-one mapping between nodes in and that preserves ances…
Improved Approximations for Guarding 1.5-Dimensional Terrains
K. Elbassioni, D. Matijevic, J. Mestre +1
We present a 4-approximation algorithm for the problem of placing a fewest guards on a 1.5D terrain so that every point of the terrain is seen by at least one guard. This improves…
Finding the theta-Guarded Region
Domagoj Matijević, Ralf Osbild
We are given a finite set of n points (guards) G in the plane R^2 and an angle 0 < theta < 2 pi. A theta-cone is a cone with apex angle theta. We call a theta-cone empty (with resp…