3 papers
cs.LG2024
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
Yifei He, Yuzheng Hu, Yong Lin +2
Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing…
cs.LG2024
On the Benefits of Over-parameterization for Out-of-Distribution Generalization
Yifan Hao, Yong Lin, Difan Zou +1
In recent years, machine learning models have achieved success based on the independently and identically distributed assumption. However, this assumption can be easily violated in…
cs.CV2024
A Sober Look at the Robustness of CLIPs to Spurious Features
Qizhou Wang, Yong Lin, Yongqiang Chen +3
Large vision language models, such as CLIP, demonstrate impressive robustness to spurious features than single-modal models trained on ImageNet. However, existing test datasets are…