arXiv Computer Vision October 23, 2026 By Enzhe Zhao, Marco Fiorucci, Lamberto Ballan

RankAlign: Vision-Language Representation Alignment via Rank Transformation

Read the original on arXiv Computer Vision →

RankAlign introduces a rank-based normalization technique for aligning vision and language representations without cross-modal supervision. By converting within-modality similarity kernels into ordinal relational representations, it preserves the relative ordering of similarities while remaining invariant to strictly increasing reparameterizations. The method offers theoretical guarantees for exact and partial ordinal agreement and shows improved, more stable class-level correspondence recovery across various frozen encoders and datasets, even under label corruption and domain shift.

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 30

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

arXiv:2606. 29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets.

By Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon

llms rag efficiency multimodal benchmarks 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

arXiv Machine Learning

Oct 15

Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning

arXiv:2604.26370v2 Announce Type: replace-cross Abstract: Vision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-l...

By Junwon You, Mihyun Jang, Sangwoo Mo, Jae-Hun Jung

llms multimodal safety

arXiv AI

Jun 24

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

arXiv:2606. 23885v1 Announce Type: cross Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder.

By Davide Caffagni, Alberto Compagnoni, Federico Melis, Sara Sarto, Pier Luigi Dovesi, Mark Granroth-Wilding, Marcella Cornia, Lorenzo Baraldi

llms multimodal benchmarks safety

arXiv AI

Jul 7

Multi-Way Representation Alignment

arXiv:2602. 06205v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces.

By Akshit Achara, Tatiana Gaintseva, Mateo Mahaut, Pritish Chakraborty, Viktor Stenby Johansson, Melih Barsbey, Emanuele Rodol\`a, Donato Crisostomi

safety

arXiv Computer Vision

Sep 22

BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring

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

benchmarks

One email a morning, machine-written

Related stories

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

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

Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

Multi-Way Representation Alignment

BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring