< session />
Beyond Transformers: State Space Models as the Next Paradigm in AI
State space models (SSMs) are emerging as a compelling alternative to transformer-based architectures, providing a mathematically grounded and computationally efficient framework for modeling long-range dependencies in sequential data. While transformers rely on attention mechanisms that scale quadratically with sequence length, SSMs use linear recurrence relations and convolutional structures to capture temporal dynamics with far greater efficiency and scalability.
This session explores how state space models enable high-performance learning across modalities such as natural language, vision, and time series while reducing latency and memory overhead. Attendees will learn about the key innovations behind Structured State Space Sequence models (S4), Mamba, and Hyena, and how these architectures are redefining what is possible in long-context understanding. The talk will highlight why state space models may represent the next paradigm in AI, one that balances accuracy, efficiency, and scalability in the era beyond transformers.
What You Will Learn
-
The core principles behind state space models and how they differ from transformers
-
How architectures like S4, Mamba, and Hyena achieve efficient long-context reasoning
-
Practical insights into the potential of SSMs as the foundation for next-generation AI models
Who Should Attend
AI researchers, ML engineers, and data scientists interested in cutting-edge model architectures, efficient sequence modeling, and the future of large-scale AI systems.
< speaker_info />
About the speaker
Badri Narayana Patro
Senior Research Scientist Lead, Microsoft
Dr. Badri Narayana Patro is a Senior Research Scientist Lead at Microsoft, where he spearheads cutting-edge research in computer vision and natural language processing, with a focus on Deep Learning, Transformers, and Large Language Models (LLMs). His academic journey includes a Ph.D. in Electrical Engineering from the Indian Institute of Technology Kanpur and an M.Tech. from IIT Bombay, laying the foundation for a career that bridges rigorous scholarship and impactful innovation.
Before joining Microsoft, Dr. Patro held prestigious postdoctoral positions at KU Leuven, Belgium, and Google Research, India, contributing to foundational advancements in AI. His industry experience spans roles at Samsung R&D, Harman International, and Larsen & Toubro, where he led engineering efforts across software and systems.
Dr. Patro is a prolific contributor to the research community, with publications in top-tier conferences such as CVPR, ICCV, NeurIPS, AAAI, EMNLP, BMVC, WACV, MM, and ICASSP, and journals including TIP, PR, Neurocomputing, EAAI, and Image Vision Computing. He actively serves as a reviewer for leading venues like CVPR, ICCV, ECCV, NeurIPS, ICLR, ACL, EMNLP, NAACL, and journals such as T-PAMI, TIP, TMM, and PR. He is a proud member of CVF and ACL, and is deeply committed to advancing the frontiers of AI research.
