Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
Shuyao Shi, Kang G. Shin
Recent Multimodal Large Language Models (MLLMs) have shown high potential for spatial reasoning within 3D scenes. However, they typically rely on computationally expensive 3D repre…
cs.CV2026
Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception
Liangkai Liu, Kang G. Shin, Jinkyu Lee +2
Autonomous vehicles (AVs) rely on sensors and deep neural networks (DNNs) to perceive their surrounding environment and make maneuver decisions in real time. However, achieving rea…