Session

DescriptionThis session explores advances in sparse matrix computation, embedded AI, and system optimization. Topics include multimodal frameworks and tensor compilers that enhance sparse matrix operations, on-device training techniques that optimize neural network fine-tuning on constrained hardware, and AI-driven approaches for improving system security and reliability. Additionally, novel storage optimizations and efficient data processing methods will be presented. By integrating algorithmic innovations with hardware-aware strategies, these software innovations push the boundaries of performance, adaptability, and security in embedded computing.