Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

Jihoon Kwon, Kyle Min 0002, Jy-yong Sohn. Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions. In Danielle Belgrave, Cheng Zhang 0005, Laura N. Montoya, Hsuan-Tien Lin, Razvan Pascanu, Piotr Koniusz, Marzyeh Ghassemi, Nancy Chen, Iván Vladimir Meza Ruíz, Arturo Loaiza-Bonilla, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diago, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025. 2025. [doi]

Authors

Jihoon Kwon

This author has not been identified. Look up 'Jihoon Kwon' in Google

Kyle Min 0002

This author has not been identified. Look up 'Kyle Min 0002' in Google

Jy-yong Sohn

This author has not been identified. Look up 'Jy-yong Sohn' in Google