Document Intelligence

In today’s digital and connected environments, documents are playing an increasingly central role in human communications and workplace productivity. Document intelligence focuses on reinventing the document to deliver magical experiences for document creation, consumption, and collaboration. At Adobe, research scientists from multiple disciplinaries, such as natural language understanding, document imaging analysis, and human computer interaction, work together in designing and architecting novel methods to unlock the value in documents. Researchers are exploring deep structural and semantic understanding so that users can easily extract relevant information, navigate in large document collections, and collaborate with others more efficiently and effectively. 

Meet some of our researchersView More

Digbalay Bose

Research Scientist

Saransh Sharma

Research Associate

Srikrishna Karanam

Research Scientist

View our latest publicationsView More

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

Van Nguyen, C., Hegde, C., Pham, V., Rossi, R., Dernoncourt, F., Nguyen, T. (Dec. 12, 2026)

Spotlight paperNeurIPS 2026

Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization

Joonho_Yang, J., Yoon, D., Chang, H., Kim, B., Lee, H. (Nov. 10, 2026)

AACL-IJCNLP 2026

CRISP: Cliff-aware Residual-free Input-adaptive Sparse Prefilling with Entropy-Motivated Routing

Nguyen, H., Van Nguyen, C., Dernoncourt, F., Rossi, R., Van, L., Chen, J., Nguyen, T. (Oct. 29, 2026)

EMNLP 2026

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!