Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

ArXi:2603.22070v1 Announce Type: new Multimodal 3D vision-language models show strong generalization across diverse 3D tasks, but their performance still degrades notably under domain shifts. This has motivated recent studies on test-time adaptation (TTA), which enables models to adapt online using test-time data. Among existing TTA methods, cache-based mechanisms are widely adopted for leveraging previously observed samples in online prediction refinement. However, they only limited historical information, leading to progressive information loss as the test stream evolves.