2 papers
cs.CL2025
Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization
Zhijin Dong
Post-training alignment of large language models (LLMs) is a critical challenge, as not all tokens contribute equally to model performance. This paper introduces a selective alignm…
stat.ML2024
Multi-Normal Prototypes Learning for Weakly Supervised Anomaly Detection
Zhijin Dong, Hongzhi Liu, Boyuan Ren +2
Anomaly detection is a crucial task in various domains. Most of the existing methods assume the normal sample data clusters around a single central prototype while the real data ma…