3 papers
cs.LG2026
Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
Dong-Xiao Zhang, Hu Lou, Jun-Jie Zhang +2
Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems, each addressed with modality-specific patches. This s…
cs.LG2026
Hardware-Friendly Input Expansion for Accelerating Function Approximation
Hu Lou, Yin-Jun Gao, Dong-Xiao Zhang +3
One-dimensional function approximation is a fundamental problem in scientific computing and engineering applications. While neural networks possess powerful universal approximation…
cs.LG2026
A Geometric Probe of the Accuracy-Robustness Trade-off: Sharp Boundaries in Symmetry-Breaking Dimensional Expansion
Yu Bai, Zhe Wang, Jiarui Zhang +3
The trade-off between clean accuracy and adversarial robustness is a pervasive phenomenon in deep learning, yet its geometric origin remains elusive. In this work, we utilize Symme…