Yibing Song

Advancing Textual Prompt Learning with Anchored Attributes

2024 · arXiv (Cornell University)

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current training …

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 …