Ziqi Huang

A novel two-axis framework unifies the study of multimodal agent memory, revealing distinct tiers of memory adaptation from static reuse to self-evolving policies.

Unified models can master multi-turn visual self-correction through end-to-end trajectory RL, eliminating the need for external critic models or inference-time verifiers while yielding double-digit visual alignment gains.

Models trained with VBVR-Pro not only excel in a controlled task space but also show significant transferability to external benchmarks, revealing critical insights into visual reasoning mechanisms.