Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
Chun-Peng Chang, Shaoxiang Wang, Alain Pagani +2
Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain. We investigate the failure o…
cs.CV2026
Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning
Chun-Peng Chang, Chen-Yu Wang, Holger Caesar +1
A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Visi…