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

0
Citations
#1628
in NeurIPS 2025
of 5858 papers
6
Authors
4
Data Points

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-Aware 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 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.

Citation History

Jan 25, 2026
0
Jan 27, 2026
0
Jan 27, 2026
0
Jan 31, 2026
0