Dr Balaji Vasan Srinivasan
Date : 07/11/2025
Recent advancements in generative models have unlocked transformative workflows for creative content generation. To make these models practical for businesses and individual users, it is essential to ensure that generated content aligns with specific constraints, such as business requirements or user preferences. In this talk, I will introduce the concept of constraints in generative models and share insights from our work on enabling models to produce content that adheres to such constraints in the domains of image and graphic design. For images, I will explore approaches to control diffusion models to meet color and conceptual needs. For graphic designs, where generation involves layered compositions, I will present our iterative layer-by-layer approach to design creation. Additionally, I will introduce an inference-time strategy to constrain design generation to conceptual and color requirements, similar to image workflows. Finally, I will discuss mechanisms for automatic evaluation in an agentic setup, demonstrating how these methods can scale to test and refine constrained generation workflows effectively."
Bio:
Balaji Vasan Srinivasan is a principal scientist in Adobe Research focused on next generation technologies for enabling several content creation workflows. His current areas of research include multimodal content understanding, autogeneration of single-page graphic design, automatic translations of content across different modalities and informing content autogeneration with user-behavior data. In the past, he has worked on problems in text mining, social data analytics, high performance computing, scalable machine learning and speaker recognition. He has published several papers published in top NLP, Vision, HCI and AI conferences; and has 50+ issued patents in related areas. Balaji completed his Ph.D. in computer science at the University of Maryland in September 2011. His thesis was on Scalable Learning Methods for Speaker Recognition and Geostatistics. He completed his M.S. in electrical engineering from University of Maryland in 2008 and B.E. in electrical engineering from Anna University (India) in 2006. His work experience includes research internships at National Institutes of Health, Bethesda, MD (May – Aug 2007) and Xerox Research Center, Webster, NY (May – Aug 2011).