← Back to all news
arXiv Machine Learning By Tiantian Peng, Yuyang Liu, Shuo Yang, Qiuhe Hong, YongHong Tian

Stabilizing the Modality Gap: Null-Space Projected Continual Learning for Vision-Language Models

Read the original on arXiv Machine Learning →

The paper introduces FPCD, a framework that stabilizes the modality gap in vision‑language models during continual learning. It combines Fast Null‑space Projection, which projects gradients onto approximate null spaces to reduce interference, with Contrastive Distillation that aligns image‑to‑text and text‑to‑image similarity distributions using a small reference set. On the 11‑task MTIL benchmark, FPCD achieves strong performance, maintaining stable modality gaps and superior zero‑shot retrieval on COCO Captions and Flickr30k.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jun 8

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.

By Xiaomin Yu, Yi Xin, Yuhui Zhang, Wenjie Zhang, Chonghan Liu, Hanzhen Zhao, Chen Liu, Xiaoxing Hu, Ziyue Qiao, Hao Tang, Xiaobin Hu, Chengwei Qin, Hui Xiong, Yu Qiao, Shuicheng Yan
llmsragfine-tuningmultimodalsafety
More like this →
arXiv Machine Learning
Jul 31

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

arXiv:2508. 04227v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs), spanning predictive architectures to generative Multimodal Large Language Models (MLLMs), have revolutionized artificial intelligence through powerful cross-modal alignment and zero-shot generalization.

By Yuyang Liu, Qiuhe Hong, Linlan Huang, Alexandra Gomez-Villa, Dipam Goswami, Tiantian Peng, Xialei Liu, Joost van de Weijer, Yonghong Tian
llmsagentsroboticsmultimodalbenchmarkssafety
More like this →
arXiv Machine Learning
Jul 31

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation

arXiv:2603. 12055v3 Announce Type: replace-cross Abstract: Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and previous stages, allowing new-task supervision to induce geometric distortion.

By Chiyuan He, Zihuan Qiu, Fanman Meng, Runtong Zhang, Linfeng Xu, Qingbo Wu, Hongliang Li
llmsefficiencymultimodalbenchmarkssafety
More like this →
arXiv AI
Sep 30

One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models

The paper investigates how the modality gap— the separation between image and text representations in contrastive vision‑language models—affects different downstream tasks. By showing that a single dominant direction accounts for most of the image‑text mean separation, the authors explain why reducing or removing this gap can improve zero‑shot classification, degrade retrieval, or restore performance depending on the task. The study provides a geometric framework that clarifies when and why gap interventions should be applied in vision‑language systems.

By Aditya Sharma, Divya Saxena
llmsragmultimodalsafety
More like this →