Explore cutting-edge sequence processing architectures that go beyond traditional transformer models in this comprehensive 3-hour tutorial from JSALT 2025. Learn from leading experts Jan Chorowski from Pathway, Marek Adamczyk from Warsaw University, and Adrian Łańcucki from NVIDIA as they present the latest developments in neural sequence modeling. Discover innovative architectural approaches that address the limitations of transformers and examine emerging paradigms for processing sequential data more efficiently. Gain insights into state-of-the-art methods that are shaping the future of natural language processing, speech recognition, and other sequence-based machine learning applications through detailed slide presentations and expert analysis from the Johns Hopkins University Center for Language & Speech Processing.