4 papers
Feature Protection For Out-of-distribution Generalization
Lu Tan, Huei Zhou, Yinxiang Huang +2
With the availability of large pre-trained models, a modern workflow for building real-world machine learning solutions is to fine-tune such models on a downstream task with a rela…
Continuous Invariance Learning
Yong Lin, Fan Zhou, Lu Tan +8
Invariance learning methods aim to learn invariant features in the hope that they generalize under distributional shifts. Although many tasks are naturally characterized by continu…
Spurious Feature Diversification Improves Out-of-distribution Generalization
Yong Lin, Lu Tan, Yifan Hao +5
Generalization to out-of-distribution (OOD) data is a critical challenge in machine learning. Ensemble-based methods, like weight space ensembles that interpolate model parameters,…
Mitigating the Alignment Tax of RLHF
Yong Lin, Hangyu Lin, Wei Xiong +14
LLMs acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, w…