Ilija Bogunovic

发表论文 74 篇 · 总被引 2084 次 · h-index 24

代表论文

• Group Robust Preference Optimization in Reward-free RLHF (2024 · Neural Information Processing Systems · 被引 116)
• wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models (2025 · arXiv.org · 被引 63)
• Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration (2023 · arXiv.org · 被引 34)
• PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks (2024 · AAAI Conference on Artificial Intelligence · 被引 18)
• On Almost Surely Safe Alignment of Large Language Models at Inference-Time (2025 · 被引 12)
• Robust Multi-Objective Controlled Decoding of Large Language Models (2025 · arXiv.org · 被引 12)