AI RESEARCH
Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
arXiv CS.AI
•
ArXi:2604.02689v1 Announce Type: cross 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 and the high dimensionality of input features