Dimos Tsouros

Dimos Tsouros

Post-Doc Researcher

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Can LLMs reason, plan and predict? And should they?

5 minute read

Published:

A few days ago, AAAI24 had a nice panel on the implications of LLMs [1], with many interesting ideas and an engaging discussion between the panellists. The first part of the panel basically focused on the question “Can LLMs reason and plan”. There were some disagreements, having their roots mainly on different definitions of reasoning and planning among the panellists.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

publications

Automated collagen proportional area extraction in liver biopsy images using a novel classification via clustering algorithm

Published in In the proceedings of 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), 2017

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Panagiotis Smyrlis, Markos Tsipouras, Dimitrios Tsalikakis, Nikolaos Giannakeas, Alexandros Tzallas, Pinelopi Manousou, "Automated collagen proportional area extraction in liver biopsy images using a novel classification via clustering algorithm." In the proceedings of 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), 2017.

Parallelization and energy evaluation of interframe compression technique for video images QSDPCM

Published in In the proceedings of 2017 27th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS), 2017

Use Google Scholar for full citation

Recommended citation: Panagiotis Smyrlis, Dimosthenis Tsouros, Minas Dasygenis, "Parallelization and energy evaluation of interframe compression technique for video images QSDPCM." In the proceedings of 2017 27th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS), 2017.

Constrained K-Means Classification.

Published in Engineering, Technology & Applied Science Research, 2018

Use Google Scholar for full citation

Recommended citation: Panagiotis Smyrlis, Dimosthenis Tsouros, Markos Tsipouras, "Constrained K-Means Classification.." Engineering, Technology & Applied Science Research, 2018.

Efficient methods for constraint acquisition

Published in In the proceedings of Principles and Practice of Constraint Programming: 24th International Conference, CP 2018, Lille, France, August 27-31, 2018, Proceedings 24, 2018

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Kostas Stergiou, Panagiotis Sarigiannidis, "Efficient methods for constraint acquisition." In the proceedings of Principles and Practice of Constraint Programming: 24th International Conference, CP 2018, Lille, France, August 27-31, 2018, Proceedings 24, 2018.

Random forests with stochastic induction of decision trees

Published in In the proceedings of 2018 IEEE 30th international conference on tools with artificial intelligence (ICTAI), 2018

Use Google Scholar for full citation

Recommended citation: Markos Tsipouras, Dimosthenis Tsouros, Panagiotis Smyrlis, Nikolaos Giannakeas, Alexandros Tzallas, "Random forests with stochastic induction of decision trees." In the proceedings of 2018 IEEE 30th international conference on tools with artificial intelligence (ICTAI), 2018.

An architecture model for smart farming

Published in In the proceedings of 2019 15th International conference on distributed computing in sensor systems (DCOSS), 2019

Use Google Scholar for full citation

Recommended citation: Anna Triantafyllou, Dimosthenis Tsouros, Panagiotis Sarigiannidis, Stamatia Bibi, "An architecture model for smart farming." In the proceedings of 2019 15th International conference on distributed computing in sensor systems (DCOSS), 2019.

Automated assessment of pain intensity based on EEG signal analysis

Published in In the proceedings of 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 2019

Use Google Scholar for full citation

Recommended citation: Panagiotis Bonotis, Dimosthenis Tsouros, Panagiotis Smyrlis, Alexandros Tzallas, Nikolaos Giannakeas, Evripidis Glavas, Markos Tsipouras, "Automated assessment of pain intensity based on EEG signal analysis." In the proceedings of 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 2019.

Data acquisition and analysis methods in UAV-based applications for Precision Agriculture

Published in In the proceedings of 2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS), 2019

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Anna Triantafyllou, Stamatia Bibi, Panagiotis Sarigannidis, "Data acquisition and analysis methods in UAV-based applications for Precision Agriculture." In the proceedings of 2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS), 2019.

Structure-driven multiple constraint acquisition

Published in In the proceedings of Principles and Practice of Constraint Programming: 25th International Conference, CP 2019, Stamford, CT, USA, September 30--October 4, 2019, Proceedings 25, 2019

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Kostas Stergiou, Christian Bessiere, "Structure-driven multiple constraint acquisition." In the proceedings of Principles and Practice of Constraint Programming: 25th International Conference, CP 2019, Stamford, CT, USA, September 30--October 4, 2019, Proceedings 25, 2019.

Omissions in constraint acquisition

Published in In the proceedings of Principles and Practice of Constraint Programming: 26th International Conference, CP 2020, Louvain-la-Neuve, Belgium, September 7--11, 2020, Proceedings 26, 2020

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Kostas Stergiou, Christian Bessiere, "Omissions in constraint acquisition." In the proceedings of Principles and Practice of Constraint Programming: 26th International Conference, CP 2020, Louvain-la-Neuve, Belgium, September 7--11, 2020, Proceedings 26, 2020.

Towards a Fully Open-Source System for Monitoring of Crops with UAVs in Precision Agriculture

Published in In the proceedings of Proceedings of the 24th Pan-Hellenic Conference on Informatics, 2020

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Anastasia Terzi, Stamatia Bibi, Fotini Vakouftsi, Vassilis Pantzios, "Towards a Fully Open-Source System for Monitoring of Crops with UAVs in Precision Agriculture." In the proceedings of Proceedings of the 24th Pan-Hellenic Conference on Informatics, 2020.

Learning max-csps via active constraint acquisition

Published in In the proceedings of 27th International Conference on Principles and Practice of Constraint Programming (CP 2021), 2021

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Kostas Stergiou, "Learning max-csps via active constraint acquisition." In the proceedings of 27th International Conference on Principles and Practice of Constraint Programming (CP 2021), 2021.

Monitoring saffron crops with uavs

Published in In the proceedings of Telecom, 2022

Use Google Scholar for full citation

Recommended citation: Konstantinos Kiropoulos, Dimosthenis Tsouros, Foteini Dimaraki, Anna Triantafyllou, Stamatia Bibi, Panagiotis Sarigiannidis, Pantelis Angelidis, "Monitoring saffron crops with uavs." In the proceedings of Telecom, 2022.

UAV saffran monitoring process

Published in In the proceedings of 2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST), 2022

Use Google Scholar for full citation

Recommended citation: Konstantinos Kiropoulos, Foteini Dimaraki, Dimosthenis Tsouros, Stamatia Bibi, "UAV saffran monitoring process." In the proceedings of 2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST), 2022.

Breaking Constraint Modelling Languages with Metamorphic Testing

Published in In the proceedings of The 22nd workshop on Constraint Modelling and Reformulation, Date: 2023/08/27-2023/08/27, Location: Toronta, Canada, 2023

Use Google Scholar for full citation

Recommended citation: Ignace Bleukx, Wout Vanroose, Jo Devriendt, Dimos Tsouros, H{\'e}l{\`e}ne Verhaeghe, Tias Guns, "Breaking Constraint Modelling Languages with Metamorphic Testing." In the proceedings of The 22nd workshop on Constraint Modelling and Reformulation, Date: 2023/08/27-2023/08/27, Location: Toronta, Canada, 2023.

Guided Bottom-Up Interactive Constraint Acquisition

Published in In the proceedings of 29th International Conference on Principles and Practice of Constraint Programming (CP 2023), 2023

Use Google Scholar for full citation

Recommended citation: Dimos Tsouros, Senne Berden, Tias Guns, "Guided Bottom-Up Interactive Constraint Acquisition." In the proceedings of 29th International Conference on Principles and Practice of Constraint Programming (CP 2023), 2023.

Learning constraint models from data

Published in In the proceedings of Proc. AAAI 2023 Bridge on Constraint Programming and Machine Learning (CPML), 2023

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Tias Guns, Kostas Stergiou, "Learning constraint models from data." In the proceedings of Proc. AAAI 2023 Bridge on Constraint Programming and Machine Learning (CPML), 2023.

Learning constraints through partial queries

Published in Artificial Intelligence, 2023

Use Google Scholar for full citation

Recommended citation: Christian Bessiere, Clement Carbonnel, Anton Dries, Emmanuel Hebrard, George Katsirelos, Nina Narodytska, Claude-Guy Quimper, Kostas Stergiou, Dimosthenis Tsouros, Toby Walsh, "Learning constraints through partial queries." Artificial Intelligence, 2023.

The p-Dispersion Problem with Distance Constraints

Published in In the proceedings of 29th International Conference on Principles and Practice of Constraint Programming (CP 2023), 2023

Use Google Scholar for full citation

Recommended citation: Nikolaos Ploskas, Kostas Stergiou, Dimosthenis Tsouros, "The p-Dispersion Problem with Distance Constraints." In the proceedings of 29th International Conference on Principles and Practice of Constraint Programming (CP 2023), 2023.

A CP/LS Heuristic Method for Maxmin and Minmax Location Problems with Distance Constraints

Published in In the proceedings of 30th International Conference on Principles and Practice of Constraint Programming (CP 2024), 2024

Use Google Scholar for full citation

Recommended citation: Panteleimon Iosif, Nikolaos Ploskas, Kostas Stergiou, Dimosthenis Tsouros, "A CP/LS Heuristic Method for Maxmin and Minmax Location Problems with Distance Constraints." In the proceedings of 30th International Conference on Principles and Practice of Constraint Programming (CP 2024), 2024.

Constraint Modelling with LLMs Using In-Context Learning

Published in In the proceedings of 30th International Conference on Principles and Practice of Constraint Programming, 2024

Use Google Scholar for full citation

Recommended citation: Kostis Michailidis, Dimos Tsouros, Tias Guns, "Constraint Modelling with LLMs Using In-Context Learning." In the proceedings of 30th International Conference on Principles and Practice of Constraint Programming, 2024.

Efficient Modeling of Half-reified Global Constraints

Published in In the proceedings of The 23rd workshop on Constraint Modelling and Reformulation, Date: 2024/09/02-2024/09/02, Location: Gerona, Spain, 2024

Use Google Scholar for full citation

Recommended citation: Ignace Bleukx, H{\'e}l{\`e}ne Verhaeghe, Dimos Tsouros, Tias Guns, "Efficient Modeling of Half-reified Global Constraints." In the proceedings of The 23rd workshop on Constraint Modelling and Reformulation, Date: 2024/09/02-2024/09/02, Location: Gerona, Spain, 2024.

Generalizing Constraint Models in Constraint Acquisition

Published in In the proceedings of CP24 workshop on Progress Towards the Holy Grail, 2024

Use Google Scholar for full citation

Recommended citation: Dimos Tsouros, Steven Prestwich, Tias Guns, "Generalizing Constraint Models in Constraint Acquisition." In the proceedings of CP24 workshop on Progress Towards the Holy Grail, 2024.

Learning to learn in interactive constraint acquisition

Published in In the proceedings of Proceedings of the AAAI Conference on Artificial Intelligence, 2024

Use Google Scholar for full citation

Recommended citation: Dimosthenis Tsouros, Senne Berden, Tias Guns, "Learning to learn in interactive constraint acquisition." In the proceedings of Proceedings of the AAAI Conference on Artificial Intelligence, 2024.

Mutational Fuzz Testing for Constraint Modeling Systems

Published in In the proceedings of 30th International Conference on Principles and Practice of Constraint Programming (CP 2024), 2024

Use Google Scholar for full citation

Recommended citation: Wout Vanroose, Ignace Bleukx, Jo Devriendt, Dimos Tsouros, H{\'e}l{\`e}ne Verhaeghe, Tias Guns, "Mutational Fuzz Testing for Constraint Modeling Systems." In the proceedings of 30th International Conference on Principles and Practice of Constraint Programming (CP 2024), 2024.

talks

Learning constraint models from data

Published:

Constraint programming (CP) is widely used for solving real-world problems. The basic assumption in CP is that the user models the problem and a solver is then used to solve it. Despite the many successful applications of CP on combinatorial problems from various domains, there are still challenges to be faced in order to make CP technology even more widely used. A major bottleneck in the use of CP is modeling. Expressing a combinatorial problem as a set of constraints over decision variables requires substantial expertise, and this non-trivial task is often a major bottleneck for the widespread adoption of CP.

ACP Summer School 2023: Constraint Acquisition - Learning Constraint Models from Data (video)

Published:

The basic assumption in CP is that the user models the problem, and a solver is then used to solve it. However, expressing a combinatorial problem as a constraint model is not always straightforward. As a result, modelling is considered to be a bottleneck for the wider use of CP. To overcome this obstacle, several techniques have been proposed for modeling a constraint problem (semi-)automatically. In constraint acquisition, the model of a constraint problem is acquired (i.e., learned) using a set of examples of solutions, and possibly non-solutions. The talk is an overview of constraint acquisition research, in which learning techniques are used to learn constraint models from data. This is done either in a passive setting, using an existing set of solutions and/or non-solutions of the problem, or in an active setting where the system interacts with the user to model the problem. I discuss both passive and (inter)active learning, the current state-of-the-art and the connections to the machine learning field. Finally, I focus on the current challenges in Constraint Acquisition.

Holy Grail 2.0: From Natural Language to Constraint Models

Published:

Twenty-seven years ago, E. Freuder highlighted that “Constraint programming represents one of the closest approaches computer science has yet made to the Holy Grail of programming: the user states the problem, the computer solves it”. Nowadays, CP users have great modeling tools available (like Minizinc and CPMpy), allowing them to formulate the problem and then let a solver do the rest of the job, getting closer to the stated goal. However, this still requires the CP user to know the formalism and respect it. Another significant challenge lies in the expertise required to effectively model combinatorial problems. All this limits the wider adoption of CP. In this position paper, we investigate a possible approach to leverage pre-trained Large Language Models to extract models from textual problem descriptions. More specifically, we take inspiration from the Natural Language Processing for Optimization (NL4OPT) challenge and present early results with a decomposition-based prompting approach to GPT Models.

Guided Bottom-up Interactive Constraint Acquisition

Published:

Constraint Acquisition (CA) systems can be used to assist in the modeling of constraint satisfaction problems. In (inter)active CA, the system is given a set of candidate constraints and posts queries to the user with the goal of finding the right constraints among the candidates. Current interactive CA algorithms suffer from at least two major bottlenecks. First, in order to converge, they require a large number of queries to be asked to the user. Second, they cannot handle large sets of candidate constraints, since these lead to large waiting times for the user. For this reason, the user must have fairly precise knowledge about what constraints the system should consider. In this presentation, I discuss how we alleviated these bottlenecks in our CP2023 paper, presenting our two novel methods that improve the efficiency of CA.

Explainable Constraint Solving - A Hands-On Tutorial (video)

Published:

Explainable constraint solving is a sub-field of explainable AI (XAI) concerned with explaining constraint (optimization) problems. Although constraint models are explicit: they are written down in terms of individual constraints that need to be satisfied, the solution to such models can be non-trivial to understand. Driven by the use-case of nurse scheduling, we will demonstrate the type of questions a user can have about (non)-solutions, as well as reviewing what kind of computational tools are available today to answer such questions. We will cover classical methods such as MUS/MCS extraction, and more recent advances in the field such as step-wise explanations, constraint relaxation methods and counterfactual solutions. We will demonstrate and give special attention to techniques that we have successfully (re)implemented on top of the CPMpy constraint solving library, and hence can be readily used today.

Invited talk: Chatbots and LLMs for Constraint Programming: Opportunities and Challenges - With Serdar Kadioğlu

Published:

Twenty-seven years ago, E. Freuder highlighted that “Constraint programming represents one of the closest approaches computer science has yet made to the Holy Grail of programming: the user states the problem, the computer solves it”. Nowadays, CP users have great modeling tools available (like Minizinc and CPMpy), allowing them to formulate the problem and then let a solver do the rest of the job, getting closer to the stated goal. However, this still requires the CP user to know the formalism and respect it. Another significant challenge lies in the expertise required to effectively model combinatorial problems. All this limits the wider adoption of CP. In this discussion, we investigated how to leverage NLP approaches to model constraint problems from textual description. We discussed bottom-up and top-down approaches, by either building each required component (e.g., variables, constraints, objective, etc.) and then combining them together, or using pre-trained Large Language Models to directly extract the models. We presented early results with both.

Learning to Learn in Interactive Constraint Acquisition

Published:

Our paper on “Learning to Learn in Interactive Constraint Acquisition” was presented in AAAI24. In Constraint Acquisition (CA), the goal is to assist the user by automatically learning the model. In (inter)active CA, this is done by interactively posting queries to the user, e.g., asking whether a partial solution satisfies their (unspecified) constraints or not. In our proposed approach, the system actually learns (implicitely) the structure of the problem, using classifiers to learn the existing patterns, using a feature representation of the constraints. The query-based learning is making this explicit, confirming it through queries to the user. This resulted in up to 70% reduction in the number of queries needed to learn the correct set of constraints!

Learning to Learn and to Generalize in Interactive Constraint Acquisition

Published:

Constraint Programming (CP) has been successfully used to model and solve complex combinatorial problems. However, modelling is often not trivial and requires expertise, which is a bottleneck to the wider adoption of CP technology. In Constraint Acquisition (CA), the goal is to assist the user by automatically learning the model. In (inter)active CA, this is done by interactively posting queries to the user, e.g., asking whether a (partial) example satisfies their (unspecified) constraints or not. While interactive CA methods learn the constraints of a given problem, the learning is related to symbolic concept learning, as the goal is to learn an exact representation. However, a large number of queries is required by most systems to learn the model, which is a major limitation. In this talk, I discussed how we alleviated this limitation by tightening the connection of CA and Machine Learning (ML), by, for the first time in interactive CA, exploiting statistical ML methods to guide interactive CA queries.

Generalizing Constraint models in Constraint Acquisition

Published:

Our workshop paper on “Generalizing Constraint models in Constraint Acquisition” was presented in the Progress Towards the Holy Grail workshop at the CP Conference.

Abstract: Constraint Acquisition (CA) aims to widen the use of constraint programming by helping users in the modeling process. However, most CA methods learn one ground CSP: a set of individual constraints for a specific problem instance. We focus on generalizing ground CSPs, by learning parameterized constraint models that can model multiple instances of the same problem.

CP24 Tutorial: Constraint Acquisition - A tutorial on Learning Constraint Models

Published:

Constraint Programming (CP) is a powerful paradigm for solving complex combinatorial problems, but its adoption is often hindered by the expertise required for modeling. Constraint Acquisition (CA) aims to mitigate this bottleneck by semi-automating the modeling process. This tutorial provides a comprehensive introduction to CA, covering both passive and interactive learning approaches.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.