cs.AI, cs.CV

Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs

arXiv:2604.02689v1 Announce Type: new
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substantial size of 3D MLLMs an…