4 papers · 1 filter
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…
Phase-space entropy at acquisition reflects downstream learnability
Xiu-Cheng Wang, Jun-Jie Zhanga, Nan Cheng +3
Modern learning systems work with data that vary widely across domains, but they all ultimately depend on how much structure is already present in the measurements before any model…
Is AI Robust Enough for Scientific Research?
Jun-Jie Zhang, Jiahao Song, Xiu-Cheng Wang +14
We uncover a phenomenon largely overlooked by the scientific community utilizing AI: neural networks exhibit high susceptibility to minute perturbations, resulting in significant d…
Symmetry Breaking in Neural Network Optimization: Insights from Input Dimension Expansion
Jun-Jie Zhang, Nan Cheng, Fu-Peng Li +4
Understanding the mechanisms behind neural network optimization is crucial for improving network design and performance. While various optimization techniques have been developed,…