LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published May 26 • 145
InstructSAM: Segment Any Instance with Any Instructions Paper • 2605.26102 • Published May 25 • 18 • 3
Pixel-Level Pavement Distress Assessment Using Instance Segmentation Paper • 2605.26095 • Published May 25
PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity Paper • 2510.23603 • Published Oct 27, 2025 • 26