Back to papers
May 21, 2026cs.CVcs.LGcs.MMeess.IV

SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

Zhenyu Lu, Liupeng Li, Jinpeng Wang, Haoqian Kang, Yan Feng, Ke Chen, Yaowei Wang
Read on arXivDownload PDF
Categories

cs.CV, cs.LG, cs.MM, eess.IV