Syed Bahauddin Alam

Multi-task scientific foundation models often mistake parameter preservation for true representation reuse, failing to outperform specialized single-task operators across most evaluated physics regimes.

Benign actions can be misclassified as attacks due to causal signal shifts, leading to significant utility loss in tool-using LLMs.

Achieving over five times improvement in Latency-Error-Energy metrics could redefine efficiency standards for edge-deployable virtual sensing systems.

Uniform sampling fails to adequately cover the vulnerability landscape of neural operators, as optimal training data is architecture-dependent, necessitating targeted data generation strategies.

Forget retraining monolithic models: SCNO unlocks zero-forgetting modular expansion for PDE solvers by composing spiking neural operator blocks, outperforming traditional methods with fewer parameters.