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

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.

Cite

Text

Ye et al. "Aligning by Misaligning: Boundary-Aware Curriculum Learning for Multimodal Alignment." Advances in Neural Information Processing Systems, 2025.

Markdown

[Ye et al. "Aligning by Misaligning: Boundary-Aware Curriculum Learning for Multimodal Alignment." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/ye2025neurips-aligning/)

BibTeX

@inproceedings{ye2025neurips-aligning,
  title     = {{Aligning by Misaligning: Boundary-Aware Curriculum Learning for Multimodal Alignment}},
  author    = {Ye, Hua and Ding, Hang and Chen, Siyuan and Jiang, Yiyang and Changyuan, Zhang and Zhang, Xuan},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2025},
  url       = {https://mlanthology.org/neurips/2025/ye2025neurips-aligning/}
}