Jiayu Yao

Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

2018 · arXiv (Cornell University)

As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing uncertainty over the parameters of …

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

2025 · arXiv (Cornell University)

Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment direction - defined by weight differences …