Conference on Empirical Methods in Natural Language Processing · 2023
Cited
4
Resume (English only)
Background
PhD candidate in Computer Science at the University of Southern California's (USC) Information Sciences Institute (ISI)
Research focuses on building human-centric AI systems that interactively understand and fulfill human goals
Central theme: human-AI context synchronization—expanding shared context about knowledge, goals, and capabilities to balance AI utility with human agency and privacy
Creates virtual environments with user models and task-specific interfaces to simulate noisy human-AI interactions in complex real-world scenarios
Explores high-fidelity simulations for large-scale synthetic data generation and designs novel reward functions for reinforcement learning and rejection sampling