2 papers
cs.CL2026
Brevity Constraints Reverse Performance Hierarchies in Language Models
MD Azizul Hakim
Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger language models underperform smaller ones by 28.4 p…
cs.NE2026
Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks
MD Azizul Hakim
Artificial neural networks achieve strong performance on benchmark tasks but remain fundamentally brittle under perturbations, limiting their deployment in real-world settings. In…