2 papers
cs.CV2026
Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering
Ruei-Chi Lai, Bolivar Solarte, Chin-Hsuan Wu +2
Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks. However, extending these models to the 3D question answeri…
cs.CV2025
Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning
Tzu-Chun Chien, Chieh-Kai Lin, Shiang-Feng Tsai +3
Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual grounding, establishing themselves as a general interface for various vision-language…