Ilija Bogunovic

University College London — United Kingdom

Decision Sciences · Social Sciences

14h-index667citations67works0.12yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Bandit Algorithms Research(26), Machine Learning and Algorithms(18), Gaussian Processes and Bayesian Inference(16), Complexity and Algorithms in Graphs(9), Adversarial Robustness in Machine Learning(9)

Publications67 total

Imagined Autocurricula
arXiv (Cornell University)·2025Open Access
Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
arXiv (Cornell University)·2025Open Access
wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
ArXiv.org·2025Open Access
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
Proceedings of the AAAI Conference on Artificial Intelligence·2025Open Access
Robust Multi-Objective Controlled Decoding of Large Language Models
ArXiv.org·2025Open Access
Mean-Field Bayesian Optimisation
arXiv (Cornell University)·2025Open Access
On Almost Surely Safe Alignment of Large Language Models at Inference-Time
arXiv (Cornell University)·2025Open Access
No-Regret Linear Bandits under Gap-Adjusted Misspecification
arXiv (Cornell University)·2025Open Access
Sample-Efficient Regret-Minimizing Double Oracle in Extensive-Form Games
arXiv (Cornell University)·2024Open Access
Sample-efficient Bayesian Optimisation Using Known Invariances
arXiv (Cornell University)·2024· 2 citedOpen Access
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
arXiv (Cornell University)·2024Open Access
Adversarially Robust Decision Transformer
arXiv (Cornell University)·2024Open Access
Group Robust Preference Optimization in Reward-free RLHF
arXiv (Cornell University)·2024Open Access
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
arXiv (Cornell University)·2024Open Access
Group Robust Preference Optimization in Reward-free RLHF
2024
Adversarially Robust Decision Transformer
2024
REDUCR: Robust Data Downsampling using Class Priority Reweighting
2024
Sample Efficient Preference Alignment in LLMs via Active Exploration
arXiv (Cornell University)·2023· 1 citedOpen Access
REDUCR: Robust Data Downsampling Using Class Priority Reweighting
arXiv (Cornell University)·2023Open Access
Robust Best-arm Identification in Linear Bandits
arXiv (Cornell University)·2023Open Access
page 1 of 4Next →

Frequent Co-authors

Andreas Krause(21), Volkan Cevher(17), Jonathan Scarlett(15), Pier Giuseppe Sessa(9), Maryam Kamgarpour(6), Shyam Sundhar Ramesh(4), Stefanie Jegelka(3), Slobodan Mitrović(3), Ashkan Norouzi-Fard(3), Xiaohang Tang(3), Adish Singla(2), Gábor Bartók(2), Amin Karbasi(2), Andreas Krause(2), Slobodan Mitrović(2), Jakub Tarnawski(2), Junyao Zhao(2), Johannes Kirschner(2), Barna Pásztor(2), Viraj Mehta(2)