Hungarian Machine Learning Days

2025. August 12. - August 14.

Registration deadline: Jul 21, 2025 

About us

The Hungarian Machine Learning Days provide an opportunity for Hungarian machine learning researchers working in foreign institutions to meet each other and connect with those working in Hungary, including the younger generation and Ph.D. students.

The organization and costs are covered by MEC_SZ 149796: Hungarian Machine Learning Meetup with the support of the Hungarian National Artificial Intelligence Laboratory, established in 2020, whose main mission is to unite domestic researchers, organize events (such as AI & AUT EXPO, HUN-REN AI Symposium), and build connections with European AI Centers and ELLIS.

During the 3-day informal summer event, internationally recognized researchers will present tutorials, young researchers will give short presentations, posters, and ideas, and there will be many informal joint programs.

Participation, lunch, and coffee breaks are free of charge but require registration. On-site accommodation can be booked at the organizers at one's own expense.

Mesterséges Intelligencia Nemzeti Labor (MILAB)

Programme


All presentations are in English. For posters, please apply during registration in time. Late poster applications risk no space remaining available.


Day 1 - August 12

9:00-10:00 coffee, welcome

Regular talks

10:00 Gergely Neu (Universitat Pompeu Fabra): Inverse Q-Learning Done Right: Offline imitation learning in Q^pi-realizable MDPs (PPT)
10:30 Balázs Csáji (HUN-REN SZTAKI): Robust Inference with Kernels (PDF)
11:00 Long Tran-Thanh (University of Warwick): Pruning Neural Networks in a Principled Way (PPT)
11:30 Mihaly Petreczky (CNRS, ́Ecole Centrale Lille, University of Lille, CRIStAL): Statistical guarantees for learning dynamical systems (PDF)
12:00 Anna Kerekes (ETH Zürich, Max Planck Institute for Intelligent Systems, Tübingen):  Machine Learning Meets Microbiology: Challenges and Opportunities (PDF)

12:30-14:00 Lunch at the venue


14:00 Poster Booster Session (2 minutes 2 slides each) (PPT)
16:00-18:00 coffee, poster section 

Magyar Machine Learning Találkozó

Day 2 - August 13

9:00-10:00 coffee, welcome

10:00 Gabor Csanyi (University of Cambridge):  ML force fields show extreme generalisation
10:30 Tamás K. Stenczel (University of Cambridge): Optimal Transport for Atom Assignment in Materials Chemistry (PDF)
11:00 Gergely Flamich (University of Cambridge): You Cannot Feed Two Birds With One Score: The Accuracy-Naturalness Tradeoff in Translation (PDF)
11:30 Ádám Zsolt Wagner (Google Deepmind): Finding interesting mathematical objects with ML (PDF)
12:00 Attila Csordás (AgeCurve UK): Non-standard attack on The Riemann Hypothesis with sub-standard AI ‘students' (PDF)

12:30-14:00 Lunch at the venue

Student talks


14:00 Csaba Botos (University of Oxford): Compute Constrained Solutions for the Challenges of Delayed Feedback (PDF)
14:30 Tamás Levente (Technical University of Cluj-Napoca): 3D point cloud processing on edge (PDF)

15:00 Panel: Latest trends at NeurIPS/ICML/ICLR/… - Gábor Csányi - Mihály Petreczky - Gergely Flamich - Csaba Botos - Patrik Reizinger
16:00-18:00 Coffee, poster section

18:00-22:00 BBQ in the garden

Magyar Machine Learning Találkozó

BBQ

Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder

Day 3 - August 14

9:00-10:00 coffee, welcome

Regular talks

10:00 Botond Szabó (Bocconi University): Privacy constrained semi-parametric inference (PDF)
10:30 Tamas Linder (Queen’s University) Communication Complexity of Exact Sampling under Rényi Information (PDF)
11:00 Csaba Beleznai (AIT Austria): Robot perception from geometric cues (PPT)
11:30 Attila Sárkány, Charles University and Czech Academy of Sciences: Quantile Preferences in Portfolio Choice: A Q-DRL Approach to Dynamic Diversification (PDF)
12:00 Patrik Reizinger (Max Planck Institute for Intelligent Systems): Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning (PDF)


12:30-14:00 Lunch at the venue

Short/Student talks

14:00 Bálint Horváth (HUN-REN SZTAKI): Kernel-Based Image Restoration with Uncertainty Guarantees (PDF)
14:20 András Balogh: (University of Szeged): How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct Matching (AAAI 2025) (PDF)
14:40 Miranda Anna Christ (Fazekas Mihály High School; Alfréd Rényi Institute of Mathematics) The Structure of Relation Decoding Linear Operators in Large Language Models (PPT)


15:00 Panel: AI Regulation - Dóra Petrányi - Ferenc Kása - Long Tran-Thanh - Csaba Beleznai

Registration

Registration deadline: Jul 21, 2025
 
Our location is the Budapesti Európai Ifjúsági Központ
(European Youth Centre Budapest)

Budapest, Zivatar Street 1, 1024

Budapesti Európai Ifjúsági Központ Budapest, Zivatar u. 1, 1024

Contact

Location

Budapesti Európai Ifjúsági Központ
(European Youth Centre Budapest)
Budapest, Zivatar u. 1, 1024
www.eycb.coe.int   

Best Website Creator