A training-free method that robustifies LLM safety alignment against fine-tuning by extrapolating low-rank safety subspaces, significantly reducing attack success rates while preserving model utility.
Continual Test-time Adaptation (CTA) is a promising art to secure accuracy gains in continually-changing environments. The state-of-the-art adaptations improve out-of-distribution model accuracy via computation-efficient online test-time gradient …
Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without requiring raw data to be shared. One major challenge of FL comes from heterogeneity in users, which may have …
Instead of isolated properties, we target on a holistic trustworthiness covering every properties in one solution.