Welcome to the Best of CVPR series — your virtual front row to groundbreaking research, insights, and innovations from one of computer vision's premier conferences. Live from the authors to you.

This talk exposes hidden limitations of frontier multimodal models across reasoning and visual generation, demonstrates the inherent brittleness of VLMs and audio-visual MLLMs, and introduces simple yet effective techniques to build robustness. It also covers human-centric metrics for perceptually accurate evaluation of generative media.

Real-world multimodal data naturally exhibits hierarchical structure, yet standard VLMs like CLIP align images and text in Euclidean space, which cannot preserve tree-like hierarchies. HyperRealm embeds images and text in a Poincaré ball to encode hierarchical relationships, introducing an adaptive entropy-driven entailment loss. Evaluated on 18 zero-shot classification benchmarks, it shows consistent improvements over Euclidean CLIP baselines.

XD-MAP is a framework that transfers semantic knowledge from image datasets to LiDAR by constructing semantic parametric maps from monocular detections and geometric priors. Unlike previous approaches, XD-MAP does not require overlapping sensor views and enables scalable 360° supervision for LiDAR perception without manual annotation.