arXiv AI
Jul 28
What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features
arXiv:2607. 23271v1 Announce Type: cross Abstract: Contrastive vision-language models such as CLIP map semantically opposite phrases (e.
Contrastive vision-language learning with paraphrasing and negation
arXiv:2511. 16527v2 Announce Type: replace-cross Abstract: Contrastive vision-language models continue to be the dominant approach for image-text retrieval.
Related stories
arXiv AI
4d ago
One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models
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 AI
Aug 20
Which Negatives Matter? Ask Your Text Encoder: Adaptive Similarity Margins for Dense-Caption Retrieval
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.
arXiv AI
Jul 7
Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning
arXiv:2607. 03143v1 Announce Type: cross Abstract: Vision-language alignment powers open-vocabulary recognition, retrieval, and LVLM grounding, yet natural captions are often underspecified, making similarity brittle and overly confident under paraphrase and omitted details.
arXiv AI
Aug 28
Subspace Alignment for Vision-Language Model Test-time Adaptation
The paper introduces SubTTA, a test-time adaptation method for vision‑language models that aligns the semantic subspaces of visual and textual modalities to improve zero‑shot predictions. It addresses two issues: the modality gap caused by distribution shifts and visual nuisance that masks task‑specific semantics. By minimizing chordal distance between principal subspaces and projecting visual features onto a task‑specific textual subspace, SubTTA refines decision boundaries and achieves an average 2.24% improvement over existing TTA methods.
arXiv Machine Learning
Jun 10
Closing the Modality Gap in Zero-Shot HAR: Contrastive Training and Separability-Optimized Prototypes on IMU Data
arXiv:2606. 10789v1 Announce Type: new Abstract: Zero-shot learning (ZSL) for inertial measurement unit (IMU)-based human activity recognition (HAR) faces a central challenge: bridging the gap between sensor embeddings and semantic class representations.
arXiv AI
Aug 11
Vision-Language Grounding as Bidirectional Concept Correspondence
arXiv:2608. 07886v1 Announce Type: cross Abstract: Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region.
arXiv Computer Vision
Sep 1
What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?
arXiv:2505.22850v3 Announce Type: replace Abstract: Referring Expression Counting (REC) requires distinguishing visually similar objects described by fine-grained text cues. Existing methods tackle t...
arXiv Computer Vision
Sep 15
HANCLIP: A Family of Hyperbolic Angular Negation Vision Language Models
arXiv:2606.23843v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve strong cross-modal alignment but remain brittle to negation, often relying on shallow word associations rathe...
Hugging Face Trending Papers
Jun 9
Closing the Modality Gap in Zero-Shot HAR: Contrastive Training and Separability-Optimized Prototypes on IMU Data
Zero-shot learning (ZSL) for inertial measurement unit (IMU)-based human activity recognition (HAR) faces a central challenge: bridging the gap between sensor embeddings and semantic class representations. We systematically evaluate seven configurations combining three inference methods with two training pipelines on the PAMAP2 dataset, using 14 seen and 4 unseen activity classes with subjects 108 and 109 held out for testing.
arXiv AI
Sep 1
Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training
arXiv:2608.29313v1 Announce Type: cross Abstract: CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embed...
arXiv AI
Jun 6
Noise-Aware Visual Representation Learning for Medical Visual Question Answering
arXiv:2606. 05535v1 Announce Type: cross Abstract: Medical visual question answering (Med-VQA) has strong potential for clinical decision support by enabling AI models to interpret medical images and answer clinically relevant queries.