2 papers
cs.CV2026
Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
Arslan Artykov, Tom Ravaud, Nicolás Violante-Grezzi +1
Retrieving the 3D kinematics of articulated objects from monocular video is a fundamental challenge in computer vision. Existing methods rely on complex video setups or cues such a…
cs.CV2026
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
David Picard, Nicolas Dufour, Lucas Degeorge +14
This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates inpu…