Mislav Balunovi'c

发表论文 17 篇 · 总被引 1054 次 · h-index 14

代表论文

• MathArena: Evaluating LLMs on Uncontaminated Math Competitions (2025 · Advances in Neural Information Processing Systems 38 · 被引 303)
• Beyond Memorization: Violating Privacy Via Inference with Large Language Models (2023 · International Conference on Learning Representations · 被引 243)
• AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents (2024 · Neural Information Processing Systems · 被引 140)
• LAMP: Extracting Text from Gradients with Language Model Priors (2022 · Neural Information Processing Systems · 被引 95)
• Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad (2025 · arXiv.org · 被引 90)
• Bayesian Framework for Gradient Leakage (2021 · International Conference on Learning Representations · 被引 55)