Visual Representation Alignment for Multimodal Large Language Models Paper โข 2509.07979 โข Published Sep 9 โข 83
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation Paper โข 2506.11924 โข Published Jun 13 โข 34
Fine-Grained Perturbation Guidance via Attention Head Selection Paper โข 2506.10978 โข Published Jun 12 โข 25