Xinyi Cheng

Decomposing Prompts, Composing Actions: A Multi-Granularity Prompting Approach for Incremental Action Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Continual learning for action recognition is a critical capability for next-generation Extended Reality (XR) systems. Yet it faces a severe real-world challenge: strict user privacy that prohibits data rehearsal. While recent prompt-based continual learning methods …