Yixuan Li

A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges

2021 · arXiv (Cornell University)

Machine learning models often encounter samples that are diverged from the training distribution. Failure to recognize an out-of-distribution (OOD) sample, and consequently assign that sample to an in-class label significantly compromises the reliability of a …

Learning to Augment Distributions for Out-of-Distribution Detection

2023 · arXiv (Cornell University)

Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD detection. Advanced works, despite their promising progress, may still fail in the open …

Your Weak LLM is Secretly a Strong Teacher for Alignment

2024 · arXiv (Cornell University)

The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constraints either in the form …