Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

Han Lin, Jaemin Cho 0001, Amir Zadeh, Chuan Li, Mohit Bansal. Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents. 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

Han Lin

This author has not been identified. Look up 'Han Lin' in Google

Jaemin Cho 0001

This author has not been identified. Look up 'Jaemin Cho 0001' in Google

Amir Zadeh

This author has not been identified. Look up 'Amir Zadeh' in Google

Chuan Li

This author has not been identified. Look up 'Chuan Li' in Google

Mohit Bansal

This author has not been identified. Look up 'Mohit Bansal' in Google