Our work on how LLMs store relations selected as NeurIPS Spotlight paper

Our paper The Structure of Relation Decoding Linear Operators in Large Language Models by Miranda Anna Christ, Adrián Csiszárik, Gergely Becsó, and Dániel Varga was accepted at the NeurIPS 2025 conference as a Spotlight paper (~3% of submissions).

Healthcare

Prevention & Prediction

Patient Pathways

Patient Pathway Mission

Leveraging Hungary’s healthcare data assets for prevention, prediction, and decision support.

Moreau-Yosida f-divergences

Publication
July 18, 2021
publications
Variational representations of $f$-divergences are central to many machine learning algorithms, with Lipschitz constrained variants recently gaining attention. Inspired by this, we define the Moreau-Yosida approximation of $f$-divergences with respect to the Wasserstein-$1$ metric. The corresponding variational formulas provide a generalization of a number of recent results, novel special cases of interest and a relaxation of the hard Lipschitz constraint. Additionally, we prove that the so-called tight variational representation of $f$-divergences can be to be taken over the quotient space of Lipschitz functions, and give a characterization of functions achieving the supremum in the variational representation.
July 18, 2021

Action convergence of operators and graphs

Publication
September 17, 2020
publications
We present a new approach to graph limit theory that unifies and generalizes the two most well-developed directions, namely dense graph limits (even the more general Lp limits) and Benjamini–Schramm limits (even in the stronger local-global setting). We illustrate by examples that this new framework provides a rich limit theory with natural limit objects for graphs of intermediate density. Moreover, it provides a limit theory for bounded operators (called P-operators) of the form L∞(Ω)→L1(Ω) for probability spaces Ω .
September 17, 2020

Mathematical Foundations of Artificial Intelligence

Grant
September 1, 2018
grants
Artificial intelligence (AI) has long been one of the big promises of computer science, and related research has fundamentally shaped our thinking about the human-machine relationship. For decades, AI has failed to fulfil its promise of solving practical challenges. This is changing now. As the past ten years have given rise to radical changes and major breakthroughs making AI the major solution in many situations. Machine learning is a set of mathematical techniques which powers most current-generation artificial intelligence systems, notably self-driving cars, intelligent assistants, speech recognition and machine translation software.
September 1, 2018

Az Erdős–Moser sejtés bizonyítása

Publication
January 1, 0001
publications
A sík legfeljebb mekkora hányada színezhető ki úgy, hogy két kiszínezett pont nem lehet pontosan egység távolságra egymástól? Ezt a geometriai kérdést Leo Moser fogalmazta meg az 1960-as évek elején, Hadwiger és Nelson egy rokon problémájával kapcsolatban. Leo Moser és Erdős Pál sejtése szerint ez a hányad nem érheti el az $\frac{1}{4}$-et; a jelenleg ismert legerősebb, 0,2293 értékű alsó korlátot Hallard Croft 1967-es konstrukciója adja. A problémával kapcsolatban számos kutatócsoport publikált már részeredményeket, amelyek a kezdeti 0,2857-es felső sűrűség-becslést az elmúlt 60 évben fokozatosan 0.
January 1, 0001
The Team
The AI group at the institute brings together experts with backgrounds in both industry and academia. We place equal emphasis on theoretical foundations, thorough experimentation, and practical applications. Our close collaboration ensures a continuous exchange of knowledge between scientific research and applied projects.
Balázs Szegedy
Mathematical Theory
Attila Börcs, PhD
NLP, Modeling, MLOps
Adrián Csiszárik
Representation Learning, Foundations
Győző Csóka
NLP, MLOps
Domonkos Czifra
NLP, Foundations
Botond Forrai
Modeling
Péter Kőrösi-Szabó
Modeling
Gábor Kovács
NLP, Modeling
Judit Laki, MD PhD
Healthcare
Márton Muntag
Time Series, NLP, Modeling
Dávid Terjék
Generalization, Mathematical Theory
Dániel Varga
Foundations, Computer aided proofs
Pál Zsámboki
Reinforcement Learning, Geometric Deep Learning
Zsolt Zombori
Formal Reasoning
Péter Ágoston
Combinatory, Geometry
Beatrix Mária Benkő
Representation Learning
Jakab Buda
NLP
Diego González Sánchez
Generalization, Mathematical Theory
Melinda F. Kiss
Representation Learning
Ákos Matszangosz
Topology, Foundations
Alex Olár
Foundations
Gergely Papp
Modeling
Open Positions
The Rényi AI group is actively recruiting both theorists and practitioners.
Announcement: December 1, 2023
Deadline: rolling
applications
Rényi Institute is seeking Machine Learning Engineers to join our AI Research & Development team. Preferred Qualifications: • MLOps experience (especially in cloud environments) • Industry experience working on ML solutions
Announcement: December 1, 2023
Deadline: rolling
theory, applications
Rényi Institute is seeking Research Scientists to join our AI Research & Development team. You will have the privilege to work at a renowned academic institute and do what you love: do research and publish in the field of machine learning / deep learning.
Rényi AI - Building bridges between mathematics and artificial intelligence.