activity
20242026
collaborators

16 papers

cs.CV2026

Ill-Posed by Design: Probing Evidence Use in VLMs

Boaz Meivar, Shaked Perek, Shani Shvartzman +2

Counterfactual analysis is widely used to study evidence use in vision-language models, but its diagnostic value is limited on well-posed tasks: when several cues independently sup…

cs.CV2026

Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentation

Nadav Orenstein, Aviad Cohen Zada, Shai Avidan +1

Texture segmentation stresses foundation segmentation because meaningful regions are defined by material or repeated appearance rather than object identity. Segment Anything Models…

cs.CV2026

Sub-Semantic Image Segmentation

Aviad Cohen Zada, Nadav Orenstein, Shai Avidan +1

Images can be segmented based on visual cues (i.e., texture segmentation) or into objects (i.e., semantic segmentation). We propose a new category of sub-semantic image segmentatio…

cs.CV2026

Optimal Transport Flow Matching by Design

Shimon Malnick, Matan Rusanovsky, Ohad Fried +1

Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via optimal transport (OT), the l…

cs.CV2026

Scene Grounding In the Wild

Tamir Cohen, Leo Segre, Shay Shomer-Chai +2

Reconstructing accurate 3D models of large-scale real-world scenes from unstructured, in-the-wild imagery remains a core challenge in computer vision, especially when the input vie…

cs.CV2026

Edge Weight Prediction For Category-Agnostic Pose Estimation

Or Hirschorn, Shai Avidan

Category-Agnostic Pose Estimation (CAPE) localizes keypoints across diverse object categories with a single model, using one or a few annotated support images. Recent works have sh…