Thomas O'Connell — accepted AI-conference papers

2026

GenMatter: Perceiving Physical Objects with Generative Matter Models

Eric Li, Arijit Dasgupta, Yoni Friedman, Mathieu Huot, Vikash Mansinghka, Thomas O'Connell +2

CVPR 2026

Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter, whether observing sparse moving dots, textured surfaces, or na

Cited by 0 Source ↗Scholar ↗

2024

Evaluating Multiview Object Consistency in Humans and Image Models

tyler bonnen, Stephanie Fu, Yutong Bai, Thomas O'Connell, Yoni Friedman, Nancy Kanwisher +2

NeurIPS 2024poster

We introduce a benchmark to directly evaluate the alignment between human observers and vision models on a 3D shape inference task. We leverage an experimental design from the cognitive sciences: given a set of images, participants identify which contain the same/different objects, despite considera…

Cited by 5 Source ↗code ↗Scholar ↗