3 papers
cs.CV2026
Foveated Probes Recover Localized Binding Information in Vision Foundation Models
Mateusz Michalkiewicz, Mahsa Baktashmotlagh, Guha Balakrishnan
Frozen vision foundation models are commonly evaluated through a single global image embedding, but this interface can conflate missing information with information lost at readout…
cs.CV2026
GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra
Mateusz Michalkiewicz, Anekha Sokhal, Tadeusz Michalkiewicz +4
Modern monocular 3D reconstruction methods and vision-language models (VLMs) demonstrate impressive results on standard benchmarks, yet recent works cast doubt on their true unders…
cs.CV2024
Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models
Mateusz Michalkiewicz, Sheena Bai, Mahsa Baktashmotlagh +2
In this paper, we analyze the viewpoint stability of foundational models - specifically, their sensitivity to changes in viewpoint- and define instability as significant feature va…