NeurIPS 2025poster0 citations

Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment

Hua Ye, Hang Ding, Siyuan Chen, Yiyang Jiang, Zhang Changyuan, Xuan Zhang

Abstract

Most multimodal models treat every negative pair alike, ignoring the ambiguous negatives that differ from the positive by only a small detail. We propose Boundary-A ware Curriculum with Local Attention(BACL), a lightweight add-on that turns these borderline cases into a curriculum signal. A Boundary-aware Negative Sampler gradually raises difficulty, while a Contrastive Local Attention loss highlights where the mismatch occurs. The two modules are fully differentiable and work with any off-the-shelf dual encoder. Theory predicts a fast $\tilde{\mathcal{O}}(1/n)$ error rate; practice shows up to +32 \% R@1 over CLIP and new SOTA on four large-scale benchmarks, all without extra labels.

Multimodal AlignmentCurriculum LearningContrastive Local Attention
BibTeX
@inproceedings{
ye2025aligning,
title={Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment},
author={Hua Ye and Hang Ding and Siyuan Chen and Yiyang Jiang and Zhang Changyuan and Xuan Zhang},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=OpAGOfAhT0}
}
Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment · NeurIPS 2025