Srivastava, Aviral

3 publications

ICLRW 2025 The Fundamental Limits of LLM Unlearning: Complexity-Theoretic Barriers and Provably Optimal Protocols Aviral Srivastava

NeurIPSW 2024 A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation Aviral Srivastava, Sourav Panda

NeurIPSW 2024 Unlocking New Strategies: Intrinsic Exploration for Evolving Macro and Micro Actions Sourav Panda, Aviral Srivastava, Jonathan Dodge