← Search

Yongcan Yu

2 accepted papers

2026

Mitigating the Safety–Utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

ICML 2026poster

While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and utility. However, prevailing alignment strategies typically co…

Cited by 0SourceScholar
2025

Cooperative Pseudo Labeling for Unsupervised Federated Classification

ICCV 2025poster

Unsupervised federated learning (UFL) aims to collaboratively train a global model across distributed clients without data sharing and label information. Previous UFL works have predominantly focused on representation learning and clustering tasks. Recently, vision language models (e.g., CLIP) have…