Ilija Bogunovic

94 papers A* 22A 10B 1Misc 1Journal 55Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs? CoRR Juliusz Ziomek, William Bankes, Lorenz Wolf, Shyam Sundhar Ramesh, Xiaohang Tang, Ilija Bogunovic
2026	J	`jnl`	Multi-Task GRPO: Reliable LLM Reasoning Across Tasks. CoRR Shyam Sundhar Ramesh, Xiaotong Ji, Matthieu Zimmer, Sangwoong Yoon, Zhiyong Wang, Haitham Bou-Ammar, Aurélien Lucchi, Ilija Bogunovic
2026	J	`jnl`	Overton Pluralistic Reinforcement Learning for Large Language Models. CoRR Yu Fu, Seongho Son, Ilija Bogunovic
2025	J	`jnl`	Almost Surely Safe Alignment of Large Language Models at Inference-Time. CoRR Xiaotong Ji, Shyam Sundhar Ramesh, Matthieu Zimmer, Ilija Bogunovic, Jun Wang, Haitham Bou-Ammar
2025	J	`jnl`	Game-Theoretic Regularized Self-Play Alignment of Large Language Models. CoRR Xiaohang Tang, Sangwoong Yoon, Seongho Son, Huizhuo Yuan, Quanquan Gu, Ilija Bogunovic
2025	J	`jnl`	Imagined Autocurricula. CoRR Ahmet Hamdi Güzel, Matthew Thomas Jackson, Jarek Liesen, Tim Rocktäschel, Jakob Nicolaus Foerster, Ilija Bogunovic, Jack Parker-Holder
2025	J	`jnl`	Mean-Field Bayesian Optimisation. CoRR Petar Steinberg, Juliusz Ziomek, Matej Jusup, Ilija Bogunovic
2025	J	`jnl`	No-Regret Linear Bandits under Gap-Adjusted Misspecification. CoRR Chong Liu, Dan Qiao, Ming Yin, Ilija Bogunovic, Yuxiang Wang
2025	A*	`conf`	PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks. AAAI Chen Feng, Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, Miguel Rodrigues
2025	A*	`conf`	Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift. ICML Seongho Son, William Bankes, Sayak Ray Chowdhury, Brooks Paige, Ilija Bogunovic
2025	J	`jnl`	Robust Bayesian Optimisation with Unbounded Corruptions. CoRR Abdelhamid Ezzerg, Ilija Bogunovic, Jeremias Knoblauch
2025	J	`jnl`	Robust Multi-Objective Controlled Decoding of Large Language Models. CoRR Seongho Son, William Bankes, Sangwoong Yoon, Shyam Sundhar Ramesh, Xiaohang Tang, Ilija Bogunovic
2025	J	`jnl`	Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data. CoRR Ahmet Hamdi Güzel, Ilija Bogunovic, Jack Parker-Holder
2025	J	`jnl`	Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data. Trans. Mach. Learn. Res. Ahmet Hamdi Güzel, Ilija Bogunovic, Jack Parker-Holder
2025	J	`jnl`	This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs. CoRR Lorenz Wolf, Sangwoong Yoon, Ilija Bogunovic
2025	J	`jnl`	wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models. CoRR Xiaohang Tang, Rares Dolga, Sangwoong Yoon, Ilija Bogunovic
2024	J	`jnl`	Adversarial Robust Decision Transformer: Enhancing Robustness of RvS via Minimax Returns-to-go. CoRR Xiaohang Tang, Afonso Marques, Parameswaran Kamalaruban, Ilija Bogunovic
2024	A*	`conf`	Adversarially Robust Decision Transformer. NeurIPS Xiaohang Tang, Afonso Marques, Parameswaran Kamalaruban, Ilija Bogunovic
2024	A	`conf`	Distributionally Robust Model-based Reinforcement Learning with Large State Spaces. AISTATS Shyam Sundhar Ramesh, Pier Giuseppe Sessa, Yifan Hu, Andreas Krause, Ilija Bogunovic
2024	A*	`conf`	Group Robust Preference Optimization in Reward-free RLHF. NeurIPS Shyam Sundhar Ramesh, Yifan Hu, Iason Chaimalas, Viraj Mehta, Pier Giuseppe Sessa, Haitham Bou-Ammar, Ilija Bogunovic
2024	J	`jnl`	Group Robust Preference Optimization in Reward-free RLHF. CoRR Shyam Sundhar Ramesh, Yifan Hu, Iason Chaimalas, Viraj Mehta, Pier Giuseppe Sessa, Haitham Bou-Ammar, Ilija Bogunovic
2024	J	`jnl`	PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks. CoRR Chen Feng, Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, Miguel Rodrigues
2024	A*	`conf`	REDUCR: Robust Data Downsampling using Class Priority Reweighting. NeurIPS William Bankes, George Hughes, Ilija Bogunovic, Zi Wang
2024	J	`jnl`	Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift. CoRR Seongho Son, William Bankes, Sayak Ray Chowdhury, Brooks Paige, Ilija Bogunovic
2024	A	`conf`	Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning. AAMAS Matej Jusup, Barna Pásztor, Tadeusz Janik, Kenan Zhang, Francesco Corman, Andreas Krause, Ilija Bogunovic
2024	J	`jnl`	Sample-Efficient Regret-Minimizing Double Oracle in Extensive-Form Games. CoRR Xiaohang Tang, Chiyuan Wang, Chengdong Ma, Ilija Bogunovic, Stephen McAleer, Yaodong Yang
2024	A*	`conf`	Sample-efficient Bayesian Optimisation Using Known Invariances. NeurIPS Theodore Brown, Alexandru Cioba, Ilija Bogunovic
2024	J	`jnl`	Sample-efficient Bayesian Optimisation Using Known Invariances. CoRR Theodore Brown, Alexandru Cioba, Ilija Bogunovic
2023	J	`jnl`	Distributionally Robust Model-based Reinforcement Learning with Large State Spaces. CoRR Shyam Sundhar Ramesh, Pier Giuseppe Sessa, Yifan Hu, Andreas Krause, Ilija Bogunovic
2023	J	`jnl`	Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning. Trans. Mach. Learn. Res. Barna Pásztor, Andreas Krause, Ilija Bogunovic
2023	A	`conf`	Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning. AISTATS Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári
2023	J	`jnl`	Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning. CoRR Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári
2023	A*	`conf`	Near-optimal Policy Identification in Active Reinforcement Learning. ICLR Xiang Li, Viraj Mehta, Johannes Kirschner, Ian Char, Willie Neiswanger, Jeff Schneider, Andreas Krause, Ilija Bogunovic
2023	J	`jnl`	REDUCR: Robust Data Downsampling Using Class Priority Reweighting. CoRR William Bankes, George Hughes, Ilija Bogunovic, Zi Wang
2023	J	`jnl`	Robust Best-arm Identification in Linear Bandits. CoRR Wei Wang, Sattar Vakili, Ilija Bogunovic
2023	J	`jnl`	Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning. CoRR Matej Jusup, Barna Pásztor, Tadeusz Janik, Kenan Zhang, Francesco Corman, Andreas Krause, Ilija Bogunovic
2023	J	`jnl`	Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration. CoRR Viraj Mehta, Vikramjeet Das, Ojash Neopane, Yijia Dai, Ilija Bogunovic, Jeff G. Schneider, Willie Neiswanger
2022	A*	`conf`	A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits. NeurIPS Ilija Bogunovic, Zihan Li, Andreas Krause, Jonathan Scarlett
2022	J	`jnl`	A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits. CoRR Ilija Bogunovic, Zihan Li, Andreas Krause, Jonathan Scarlett
2022	A*	`conf`	Graph Neural Network Bandits. NeurIPS Parnian Kassraie, Andreas Krause, Ilija Bogunovic
2022	J	`jnl`	Graph Neural Network Bandits. CoRR Parnian Kassraie, Andreas Krause, Ilija Bogunovic
2022	A*	`conf`	Movement Penalized Bayesian Optimization with Application to Wind Energy Systems. NeurIPS Shyam Sundhar Ramesh, Pier Giuseppe Sessa, Andreas Krause, Ilija Bogunovic
2022	J	`jnl`	Movement Penalized Bayesian Optimization with Application to Wind Energy Systems. CoRR Shyam Sundhar Ramesh, Pier Giuseppe Sessa, Andreas Krause, Ilija Bogunovic
2022	J	`jnl`	Near-optimal Policy Identification in Active Reinforcement Learning. CoRR Xiang Li, Viraj Mehta, Johannes Kirschner, Ian Char, Willie Neiswanger, Jeff Schneider, Andreas Krause, Ilija Bogunovic
2021	A*	`conf`	Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning. ICML Sebastian Curi, Ilija Bogunovic, Andreas Krause
2021	J	`jnl`	Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning. CoRR Sebastian Curi, Ilija Bogunovic, Andreas Krause
2021	J	`jnl`	Contextual Games: Multi-Agent Learning with Side Information. CoRR Pier Giuseppe Sessa, Ilija Bogunovic, Andreas Krause, Maryam Kamgarpour
2021	J	`jnl`	Cost-Efficient Online Hyperparameter Optimization. CoRR Jingkang Wang, Mengye Ren, Ilija Bogunovic, Yuwen Xiong, Raquel Urtasun
2021	A*	`conf`	DP-Sniper: Black-Box Discovery of Differential Privacy Violations using Classifiers. SP Benjamin Bichsel, Samuel Steffen, Ilija Bogunovic, Martin T. Vechev
2021	J	`jnl`	Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning. CoRR Barna Pásztor, Ilija Bogunovic, Andreas Krause
2021	A*	`conf`	Misspecified Gaussian Process Bandit Optimization. NeurIPS Ilija Bogunovic, Andreas Krause
2021	J	`jnl`	Misspecified Gaussian Process Bandit Optimization. CoRR Ilija Bogunovic, Andreas Krause
2021	A*	`conf`	Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems. ICML Pier Giuseppe Sessa, Ilija Bogunovic, Andreas Krause, Maryam Kamgarpour
2021	A*	`conf`	Risk-averse Heteroscedastic Bayesian Optimization. NeurIPS Anastasia Makarova, Ilnura Usmanova, Ilija Bogunovic, Andreas Krause
2021	J	`jnl`	Risk-averse Heteroscedastic Bayesian Optimization. CoRR Anastasia Makarova, Ilnura Usmanova, Ilija Bogunovic, Andreas Krause
2021	A	`conf`	Stochastic Linear Bandits Robust to Adversarial Attacks. AISTATS Ilija Bogunovic, Arpan Losalka, Andreas Krause, Jonathan Scarlett
2020	A*	`conf`	Contextual Games: Multi-Agent Learning with Side Information. NeurIPS Pier Giuseppe Sessa, Ilija Bogunovic, Andreas Krause, Maryam Kamgarpour
2020	A	`conf`	Corruption-Tolerant Gaussian Process Bandit Optimization. AISTATS Ilija Bogunovic, Andreas Krause, Jonathan Scarlett
2020	J	`jnl`	Corruption-Tolerant Gaussian Process Bandit Optimization. CoRR Ilija Bogunovic, Andreas Krause, Jonathan Scarlett
2020	A	`conf`	Distributionally Robust Bayesian Optimization. AISTATS Johannes Kirschner, Ilija Bogunovic, Stefanie Jegelka, Andreas Krause
2020	J	`jnl`	Distributionally Robust Bayesian Optimization. CoRR Johannes Kirschner, Ilija Bogunovic, Stefanie Jegelka, Andreas Krause
2020	A*	`conf`	Learning to Play Sequential Games versus Unknown Opponents. NeurIPS Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
2020	J	`jnl`	Learning to Play Sequential Games versus Unknown Opponents. CoRR Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
2020	A	`conf`	Mixed Strategies for Robust Optimization of Unknown Objectives. AISTATS Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
2020	J	`jnl`	Mixed Strategies for Robust Optimization of Unknown Objectives. CoRR Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
2020	J	`jnl`	Stochastic Linear Bandits Robust to Adversarial Attacks. CoRR Ilija Bogunovic, Arpan Losalka, Andreas Krause, Jonathan Scarlett
2019	A*	`conf`	No-Regret Learning in Unknown Games with Correlated Payoffs. NeurIPS Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
2019	J	`jnl`	No-Regret Learning in Unknown Games with Correlated Payoffs. CoRR Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
2019	B	`conf`	Overlapping Multi-Bandit Best Arm Identification. ISIT Jonathan Scarlett, Ilija Bogunovic, Volkan Cevher
2019	—	`—`	Robust Adaptive Decision Making: Bayesian Optimization and Beyond. Ilija Bogunovic
2018	A*	`conf`	Adversarially Robust Optimization with Gaussian Processes. NeurIPS Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher
2018	J	`jnl`	Adversarially Robust Optimization with Gaussian Processes. CoRR Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher
2018	A	`conf`	High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups. AISTATS Paul Rolland, Jonathan Scarlett, Ilija Bogunovic, Volkan Cevher
2018	J	`jnl`	High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups. CoRR Paul Rolland, Jonathan Scarlett, Ilija Bogunovic, Volkan Cevher
2018	A	`conf`	Robust Maximization of Non-Submodular Objectives. AISTATS Ilija Bogunovic, Junyao Zhao, Volkan Cevher
2018	J	`jnl`	Robust Maximization of Non-Submodular Objectives. CoRR Ilija Bogunovic, Junyao Zhao, Volkan Cevher
2017	—	`conf`	A distributed algorithm for partitioned robust submodular maximization. CAMSAP Ilija Bogunovic, Slobodan Mitrovic, Jonathan Scarlett, Volkan Cevher
2017	A*	`conf`	Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization. COLT Jonathan Scarlett, Ilija Bogunovic, Volkan Cevher
2017	J	`jnl`	Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization. CoRR Jonathan Scarlett, Ilija Bogunovic, Volkan Cevher
2017	A*	`conf`	Robust Submodular Maximization: A Non-Uniform Partitioning Approach. ICML Ilija Bogunovic, Slobodan Mitrovic, Jonathan Scarlett, Volkan Cevher
2017	J	`jnl`	Robust Submodular Maximization: A Non-Uniform Partitioning Approach. CoRR Ilija Bogunovic, Slobodan Mitrovic, Jonathan Scarlett, Volkan Cevher
2017	—	`conf`	Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach. NIPS Slobodan Mitrovic, Ilija Bogunovic, Ashkan Norouzi-Fard, Jakub Tarnawski, Volkan Cevher
2017	J	`jnl`	Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach. CoRR Slobodan Mitrovic, Ilija Bogunovic, Ashkan Norouzi-Fard, Jakub Tarnawski, Volkan Cevher
2016	—	`conf`	An Efficient Streaming Algorithm for the Submodular Cover Problem. NIPS Ashkan Norouzi-Fard, Abbas Bazzi, Ilija Bogunovic, Marwa El Halabi, Ya-Ping Hsieh, Volkan Cevher
2016	J	`jnl`	An Efficient Streaming Algorithm for the Submodular Cover Problem. CoRR Ashkan Norouzi-Fard, Abbas Bazzi, Marwa El Halabi, Ilija Bogunovic, Ya-Ping Hsieh, Volkan Cevher
2016	J	`jnl`	Learning-Based Compressive Subsampling. IEEE J. Sel. Top. Signal Process. Luca Baldassarre, Yen-Huan Li, Jonathan Scarlett, Baran Gozcu, Ilija Bogunovic, Volkan Cevher
2016	A	`conf`	Time-Varying Gaussian Process Bandit Optimization. AISTATS Ilija Bogunovic, Jonathan Scarlett, Volkan Cevher
2016	J	`jnl`	Time-Varying Gaussian Process Bandit Optimization. CoRR Ilija Bogunovic, Jonathan Scarlett, Volkan Cevher
2016	—	`conf`	Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation. NIPS Ilija Bogunovic, Jonathan Scarlett, Andreas Krause, Volkan Cevher
2016	J	`jnl`	Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation. CoRR Ilija Bogunovic, Jonathan Scarlett, Andreas Krause, Volkan Cevher
2015	Misc	`conf`	Active learning of self-concordant like multi-index functions. ICASSP Ilija Bogunovic, Volkan Cevher, Jarvis D. Haupt, Jonathan Scarlett
2015	J	`jnl`	Learning-based Compressive Subsampling. CoRR Luca Baldassarre, Yen-Huan Li, Jonathan Scarlett, Baran Gözcü, Ilija Bogunovic, Volkan Cevher
2014	A*	`conf`	Near-Optimally Teaching the Crowd to Classify. ICML Adish Singla, Ilija Bogunovic, Gábor Bartók, Amin Karbasi, Andreas Krause
2014	J	`jnl`	Near-Optimally Teaching the Crowd to Classify. CoRR Adish Singla, Ilija Bogunovic, Gábor Bartók, Amin Karbasi, Andreas Krause