András György

DeepMind (United Kingdom) — United Kingdom

Decision Sciences · Social Sciences

28h-index2.6kcitations162works0.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Bandit Algorithms Research(58), Machine Learning and Algorithms(40), Optimization and Search Problems(23), Reinforcement Learning in Robotics(17), Sparse and Compressive Sensing Techniques(17)

Publications162 total

Frontier LLMs Still Struggle with Simple Reasoning Tasks
arXiv (Cornell University)·2025Open Access
Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
arXiv (Cornell University)·2025Open Access
A Scalable Crawling Algorithm Utilizing Noisy Change-Indicating Signals
2025Open Access
Partition Tree Weighting for Non-Stationary Stochastic Bandits
arXiv (Cornell University)·2025Open Access
A Scalable Crawling Algorithm Utilizing Noisy Change-Indicating Signals
arXiv (Cornell University)·2025Open Access
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
arXiv (Cornell University)·2024Open Access
Toward Understanding In-context vs. In-weight Learning
arXiv (Cornell University)·2024Open Access
Learning Continually by Spectral Regularization
arXiv (Cornell University)·2024Open Access
To Believe or Not to Believe Your LLM
arXiv (Cornell University)·2024· 3 citedOpen Access
Mitigating LLM Hallucinations via Conformal Abstention
arXiv (Cornell University)·2024· 2 citedOpen Access
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits
arXiv (Cornell University)·2024Open Access
Approximating the Core via Iterative Coalition Sampling
arXiv (Cornell University)·2024Open Access
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
2024
Online RL in Linearly $q^π$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore
arXiv (Cornell University)·2023Open Access
Author Correction: Perception, performance, and detectability of conversational artificial intelligence across 32 university courses
Scientific Reports·2023· 12 citedOpen Access
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
arXiv (Cornell University)·2023Open Access
Segregated mobility patterns amplify neighborhood disparities in the spread of COVID-19
Network Science·2023· 3 citedOpen Access
A Second-Order Method for Stochastic Bandit Convex Optimisation
arXiv (Cornell University)·2023Open Access
Optimistic Meta-Gradients
arXiv (Cornell University)·2023Open Access
page 1 of 9Next →

Frequent Co-authors

Csaba Szepesvári(14), Tamás Linder(11), Denız Gündüz(9), Gábor Lugosi(9), Elif Tuğçe Ceran(7), Gergely Neu(5), György Ottucsák(3), András Antos(3), Pooria Joulani(3), Ruitong Huang(2), Tor Lattimore(2), Levente Kocsis(2), Muhammad Zaid Hameed(2), Béla Hullár(2), Sándor Laki(2), Joel Veness(2), Andrea Paudice(1), Luis Muñoz-González(1), Emil Lupu(1), T. Linder(1)