• · Rustem Islamov, Yarden As, Ilyas Fatkhulin · ICML 2025 · Paper

    Safe-EF: Error Feedback for Non-smooth Constrained Optimization

    Copy
    • Stochastic Optimization
    • Federated Learning
  • · Xin Chen, Yarden As, Andreas Krause · ICML 2025 (Spotlight) · Paper

    Learning Safety Constraints for Large Language Models

    Copy
    • LLMs
    • AI Safety
  • · Yarden As*, Bhavya Sukhija*, Lenart Treven, Carmelo Sferrazza, Steilan Coros, Andreas Krause · ICLR 2025 · Paper

    ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

    Copy
    • CMDPs
    • Safe Reinforcement Learning
    • Active Learning
  • · Jonas Hübotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause · NeurIPS 2024 · Paper

    Transductive Active Learning: Theory and Applications

    Copy
    • Active Learning
    • Bayesian Optimization
    • Experimental Design
    • Safe Exploration
  • · Lenart Treven, Bhavya Sukhija, Yarden As, Florian Dorfler, Andreas Krause · NeurIPS 2024 · Paper

    When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL

    Copy
    • Reinforcement Learning
  • · Ilnura Unsmanova, Yarden As, Maryam Kamgarpour, Andreas Krause · JMLR · Paper

    Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning

    Copy
    • Constrained Optimization
    • Safe Reinforcement Learning
  • · Jonas Hübotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause · ICLR 2024 @ Bridging the Gap Between Practice and Theory in Deep Learning · Paper

    Active Few-Shot Fine-Tuning

    Copy
    • Active Learning
    • Supervised Learning
  • · Arjun Bhardwaj, Jonas Rothfuss, Bhavya Sukhija, Yarden As, Marco Hutter, Stelian Coros, Andreas Krause · RA-L, IROS 2024 · Paper

    Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning

    Copy
    • Meta Learning
    • Reinforcement Learning
  • · Yarden As, Ilnura Unsmanova, Sebastian Curi, Andreas Krause · ICLR 2022 (Spotlight) · Paper

    Constrained Policy Optimization via Bayesian World Models

    Copy · Code
    • Safe Reinforcement Learning
    • CMDPs