Artificial Intelligence & Machine Learning

Artificial intelligence (AI), machine learning (ML), and deep learning (DL) are powering Adobe’s products and businesses. At Adobe, we use AI, ML, and DL to solve problems in content understanding (including images, videos, documents, audio, and more); recommendations and personalization; search and information retrieval; prediction and journey analysis; content segmentation, organization, editing, and generation; and more. 

Adobe Research scientists and engineers are developing the next generation of AI, ML, and DL-driven tools and features, inventing a future where Adobe enables new forms of creativity, and frees people from routine tasks, and allows enterprises to understand and act quickly on customer and business insights. Our team also leverages new approaches such as GANs (generative adversarial networks).    

Meet some of our researchersView More

Giuseppe Vecchio

Reseach Scientist

Jérémy Levallois

Research Engineer

Krishna Kumar Singh

Research Scientist

View our latest publicationsView More

A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality

Elmoghany, M., Rossi, R., Yoon, D., Mukherjee, S., Bakr, E., Mathur, P., Wu, G., Lai, V., Lipka, N., Zhang, R., Manjunatha, V., Nguyen, C., Dangi, D., Salinas, A., Taesiri, M., Chen, H., Huang, X., Barrow, J., Ahmed, N., Eldardiry, H., Park, N., Wang, Y., Cho, J., Nguyen, A., Tu, Z., Nguyen, T., Manocha, D., Elhoseiny, M., Dernoncourt, F. (Oct. 20, 2025)

ICCV 2025 LongVid Foundations Workshop

Long-lrm: Long-sequence large reconstruction model for wide-coverage gaussian splats

Ziwen, C., Tan, H., Zhang, K., Bi, S., Luan, F., Hong, Y., Li, F., Xu, Z. (Oct. 19, 2025)

ICCV 2025

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

Yu, S., Liu, D., Ma, Z., Hong, Y., Zhou, Y., Tan, H., Chai, J., Bansal, M. (Oct. 19, 2025)

ICCV 2025

Project Know How

Project Know How allows users to track the origins of images and videos, even if they’ve been printed and captured from physical objects. Adobe’s implementation of Content Credentials is durable because of a combination of secure metadata, invisible watermarking, and fingerprinting technology. This project is an example of how Adobe aims to build trust by transparently showing the content’s origin, whether digital or physical.

View our latest newsView All News

Join us!

We are looking for researchers, engineers, and interns to take our technologies to the next level. We're recruiting, and we would love to hear from you!