arXiv Computer Vision October 9, 2026 By Mengping Dong, Jinbao Li, Fei Li

DiscoVL: Unveiling Disentangled C ross-Modal Representation Learning via Orthogonal Adversarial Regularization for V ision-Language Models

Read the original on arXiv Computer Vision →

DiscoVL introduces a disentangled cross‑modal representation learning framework for vision‑language models, combining orthogonal adversarial regularization with a multi‑branch low‑rank residual aligner to enhance bidirectional visual‑textual interaction. The method decomposes representations into subspaces, enabling cross‑modal feedback at each layer and preventing centroid collapse through an orthogonal adversarial triplet loss. Across 15 benchmarks, DiscoVL consistently outperforms state‑of‑the‑art approaches in base‑to‑novel generalization, cross‑dataset evaluation, and few‑shot learning.

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 Computer Vision.

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

llms rag fine-tuning multimodal safety

arXiv Machine Learning

Jun 4

RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

arXiv:2606. 05109v1 Announce Type: new Abstract: To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information.

By Vasiliki Rizou, Pascal Frossard, Dorina Thanou

rag multimodal benchmarks safety

Hugging Face Trending Papers

Jun 3

RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information. Learning disentangled representations is a principled way to identify these underlying shared and unique factors that are hidden in observational data.

rag multimodal benchmarks safety

arXiv Machine Learning

Jul 2

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

arXiv:2602. 21397v2 Announce Type: replace-cross Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights.

By Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani

llms rag multimodal benchmarks safety

arXiv Computer Vision

Oct 7

Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling

arXiv:2610.07689v1 Announce Type: new Abstract: Vision-Language Models (VLMs) such as CLIP excel in global semantic alignment but often lack fine-grained perceptual capabilities. This hinders dense p...

By Juntong Li, Lingwei Dang, Haomin Wu, Ziyan Qiu, Qingxin Xiao, Qingyao Wu

llms rag efficiency multimodal safety

arXiv AI

Jun 30

SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

arXiv:2602. 23353v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world.

By Simon Roschmann, Paul Krzakala, Sonia Mazelet, Quentin Bouniot, Zeynep Akata

llms rag multimodal safety

One email a morning, machine-written

Related stories

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

RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling

SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport