arXiv:2504. 16318v3 Announce Type: replace Abstract: Cosine similarity is a standard comparison rule for learned representations in information retrieval, natural language processing, computer vision, and multimodal learning.
The standard way to compare two text embeddings is cosine similarity. Scattered studies report that a different metric does better, but never pin down the geometric condition that decides when, or why.
arXiv:2602. 19393v2 Announce Type: replace Abstract: Steck, Ekanadham, and Kallus [arXiv:2403.
arXiv:2609.15152v1 Announce Type: cross Abstract: Multimodal embedding models encode heterogeneous inputs into a shared embedding space, enabling efficient similarity computation across modalities an...
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:2506. 08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways.
arXiv:2608.30263v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) incur substantial inference costs due to their long and highly redundant visual-token sequences. Diversity-based...
arXiv:2606. 30625v1 Announce Type: cross Abstract: Contrastive embedding models trained with scale-invariant losses are typically paired with distance metrics like cosine similarity, effectively ignoring embedding magnitudes.
arXiv:2606. 15054v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm.
arXiv:2606. 28330v1 Announce Type: cross Abstract: Embedding-based retrieval systems rely on the assumption that geometric proximity in highdimensional representation spaces reflects semantic relevance.
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:2609.06663v1 Announce Type: cross Abstract: Although multimodal Large Language Models (MLLMs) excel in diverse tasks, their scalability remains limited by the memory and computational overhead...
arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.