3 papers
cs.CV2026
Parameter Efficient Continual Learning for Sparse Event-Based Transformers
Vaishnavi Nagabhushana, Kartikay Agrawal, Ayon Borthakur
Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previously learned knowledge under…
cs.LG2026
CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds
Vaishnavi Nagabhushana, Kartikay Agrawal, Ayon Borthakur
Although deep neural networks perform extremely well in controlled environments, they fail in real-world scenarios where data isn't available all at once, and the model must adapt…
cs.LG2025
ASecond-Order SpikingSSM for Wearables
Kartikay Agrawal, Abhijeet Vikram, Vedant Sharma +2
Spiking neural networks have garnered increasing attention due to their energy efficiency, multiplication-free computation, and sparse event-based processing. In parallel, state sp…