Embedding norms in contrastive models encode semantic properties via optimization dynamics under scale-invariant losses.
InAdvances in Neural Information Processing Systems, Vol
8 Pith papers cite this work, alongside 98 external citations. Polarity classification is still indexing.
8
Pith papers citing it
98
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.
DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.
GELATO extends frozen Jina Embeddings v5 text models with locked non-text encoders, training only connectors to produce competitive multimodal embeddings while preserving exact text performance.
Global prompt integration, visual-textual relation distillation and selective fusion make visual prompts discriminative enough for DETR-ViP to beat prior visual-prompt detectors by several mAP points.
TaDSE learns dialogue sentence embeddings via template-guided self-supervised contrastive learning plus synthetic slot-filling augmentation and reports gains on five downstream benchmarks.
GeoStack composes multiple domain experts into VLMs with preserved base knowledge and O(1) inference time via geometric stacking and a weight-folding property.
citing papers explorer
-
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
Embedding norms in contrastive models encode semantic properties via optimization dynamics under scale-invariant losses.
-
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
-
SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning
SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.
-
DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift
DeconDTN-Toolkit simulates provenance shifts to expose ERM vulnerabilities and provides tools plus a robust OOD indicator for mitigating confounding by data provenance.
-
jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
GELATO extends frozen Jina Embeddings v5 text models with locked non-text encoders, training only connectors to produce competitive multimodal embeddings while preserving exact text performance.
-
DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts
Global prompt integration, visual-textual relation distillation and selective fusion make visual prompts discriminative enough for DETR-ViP to beat prior visual-prompt detectors by several mAP points.
-
Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings
TaDSE learns dialogue sentence embeddings via template-guided self-supervised contrastive learning plus synthetic slot-filling augmentation and reports gains on five downstream benchmarks.
-
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
GeoStack composes multiple domain experts into VLMs with preserved base knowledge and O(1) inference time via geometric stacking and a weight-folding property.