Tianmin Shu

The Mind2Dialogue framework proposes a psychology-guided simulator that preserves personal characteristics while updating mental states through interaction to generate coherent conversations, and trains models on the Oracle's well-informed responses to assist users without direct access to their mental states at deployment.

Instead of stuffing raw context with dialogue history or brittle retrieval vectors, treating user personalization as particle-filtered hypothesis tracing over natural language resolves the tension between fleeting intent and long-term preferences.

MindZero reveals that mental reasoning can be learned as a self-supervised skill, dramatically enhancing the performance of MLLMs in real-time AI assistance tasks.

Agents struggle to match human performance in long-horizon tasks, revealing critical gaps in their learning capabilities during deployment.