2 papers
cs.LG2024
CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning
Yiping Wang, Yifang Chen, Wendan Yan +4
Data selection has emerged as a core issue for large-scale visual-language model pretaining (e.g., CLIP), particularly with noisy web-curated datasets. Three main data selection ap…
cs.LG2024
Decoding-Time Language Model Alignment with Multiple Objectives
Ruizhe Shi, Yifang Chen, Yushi Hu +4
Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on…