The paper proposes replacing the unit-sphere embedding space used by multimodal contrastive models with the probability simplex. By adding lightweight softmax adapters and measuring similarity with Total Variation, the authors reduce the modality gap by 97–99% on five retrieval benchmarks, showing that simplicial geometry can align modalities as well as or better than unconstrained 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.
arXiv:2607. 13660v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyperspherical geometry.
The paper investigates the expressive power of multimodal contrastive learning architectures by treating them as parameterized families of joint density estimators. It shows that the classic two‑tower CLIP model is a universal approximator for two modalities, while a common extension that sums pairwise similarities fails to approximate arbitrary joint distributions when three or more modalities are involved, though it can match all pairwise conditionals. To address this limitation, the authors introduce Hadamard‑CLIP, which adds a single learned weight vector to restore universal approximation for any number of modalities while retaining CLIP’s efficient retrieval capabilities.
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.
arXiv:2506. 08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways.
The paper proposes that independently trained multimodal models often share a common geometric structure, allowing cross‑modal alignment without paired data. Using a Wasserstein Procrustes approach with a coarse geometric initialization, the authors align two disjoint embedding sets by estimating a single orthogonal map, achieving consistent alignment across datasets and modalities. While paired examples can further improve performance, the method already outperforms existing techniques in the few‑pair regime and enables text‑to‑image generation without paired data.
arXiv:2608. 10857v1 Announce Type: new Abstract: Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning.
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.
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...
arXiv:2610.04792v2 Announce Type: replace Abstract: Missing modality remains a longstanding challenge in multimodal learning. Existing methods typically address this issue through modality recovery o...
arXiv:2609.39836v1 Announce Type: new Abstract: Contrastive vision-language models map visual and textual representations into a shared normalized embedding space, making cosine similarity the natura...
arXiv:2601.21670v4 Announce Type: replace-cross Abstract: Multimodal fusion is often treated as an optimization-balancing problem, where training signals are adjusted to prevent one modality from dom...