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
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
arXiv:2610.33798v1 Announce Type: cross
Abstract: An image is rarely described only once. Retrieval benchmarks and many collections attach several captions to each picture, yet dual encoders still ju...
By Khang Nhat Hoang Vo, Belal Shoer, Abhirama Subramanyam Penamakuri
arXiv:2609.23717v1 Announce Type: new
Abstract: Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which regi...
By Liuyang Song, Yi Zhang, Zhongyi Deng, Daqian Yang, Hongbo Zhang
arXiv:2506. 08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways.
By Fan Xu, Luis A. Leiva
TokenSwap introduces a method to benchmark and reduce the modality gap in multimodal large language models (MLLMs) by interleaving semantically aligned images with text tokens. By transforming text-only benchmarks like MMLU into image‑interleaved versions (TokenSwap‑Bench), the authors reveal a pervasive performance drop—averaging 19.6%—across 42 MLLMs, with reasoning models showing smaller gaps. Training with TokenSwap mitigates this gap while maintaining strong text‑only and vision‑language performance.
By Andong Hua, Colton Bishop, Igor Mordatch, Arian Hosseini, Jindong Gu, Aleksandra Faust, Rebecca Roelofs, Yao Qin
The paper introduces HN-CLIP, a new objective for dense-caption retrieval that adapts similarity margins per negative example using the text encoder’s own geometry. By adding a detached caption‑similarity matrix to the negative logits, HN‑CLIP addresses the issue of near‑duplicate captions that cause premature loss saturation in InfoNCE training. Experiments on four benchmarks show that HN‑CLIP outperforms leading methods by 2.4–4.3 R@1, trains 2.4× faster than GOAL and 5.4× faster than StructXLIP, and achieves the best full‑data baseline with only 20% of the training data.
By Haoyue Liu, Ye Chen, Zhichao Wang, Xiaoying Tang
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.
By Jonas Klotz, Cassio F. Dantas, Pallavi Jain, Diego Marcos, Beg\"um Demir
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.
By Tiantian Peng, Yuyang Liu, Shuo Yang, Qiuhe Hong, YongHong Tian
Omni-Embed-Mini is a 0.9B‑parameter model that embeds text, speech, audio, images, video, and visually‑rich documents into a single shared cosine space without updating any text‑side parameters. It uses a dense cascaded caption as a teacher signal, allowing the teacher and student to share identical backbone weights and requiring only lightweight projectors and phased LoRA adapters for alignment. The model achieves strong text retrieval performance (49.57 nDCG@10 on MTEB‑v2 BEIR‑8) while extending to five additional modalities and is significantly smaller than other open omni‑modal embedders.
By Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Sahal Shaji Mullappilly, Ivan Laptev, Hisham Cholakkal
arXiv:2608. 18339v1 Announce Type: cross Abstract: Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.
By Qi Yu, Zhichen Zeng, Katherine Tieu, Xiyuan Yang, Ruizhong Qiu, Yuchen Yan, Lihui Liu, Yanjun Zhao, Lingjie Chen, Jingrui He, Hanghang Tong
Flow-CLIP introduces a method to improve compositional image-text matching by refining global image-text alignment with image-conditioned changes in token–patch evidence. It combines Global Compatibility Calibration (GCC) for sentence-level similarity, Image-Conditioned Evidence Refinement (ICER) to incorporate visual patch context, and Cross-Image Margin Ranking (CIMR) to enhance ranking margins when images support correct descriptions. Experiments demonstrate that Flow-CLIP outperforms pretrained CLIP and other global alignment approaches on binding accuracy and reduces reliance on language priors.
By Minghong Wei, Enguang Zhu, Pu Cao, Lu Yang, Qing Song