Back to papers
June 5, 2026cs.CVcs.AIcs.CLcs.LG

TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment

Sweta Mahajan, Sukrut Rao, Jiahao Xie, Alexander Koller, Bernt Schiele
Read on arXivDownload PDF
Categories

cs.CV, cs.AI, cs.CL, cs.LG