No article text was recorded for this version.
modality gap (cross-modal embedding misalignment)
Version 1 of 1111 papers132 conceptsfrozen 2026-10-04
Papers in this version
- Blog: When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
- Blog: Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
- Blog: Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models
- Blog: Why do LLaVA Vision-Language Models Reply to Images in English?
- Blog: Bridge the Modality and Capability Gaps in Vision-Language Model Selection
- Blog: Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP
- Blog: Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure
- Blog: iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
- Blog: ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
- Blog: Label Propagation for Zero-shot Classification with Vision-Language Models
- Blog: Bridging the Modality Gap: Training-free Adaptation of Vision-Language Models for Remote Sensing via Visual Prototypes
- Blog: Attention Guided Alignment in Efficient Vision-Language Models
- Blog: Language-only Efficient Training of Zero-shot Composed Image Retrieval
- Blog: On the Multi-modal Vulnerability of Diffusion Models
- Blog: From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping
- Blog: Post-pre-training for Modality Alignment in Vision-Language Foundation Models
- Blog: MLLM-I2W: Harnessing Multimodal Large Language Model for Zero-Shot Composed Image Retrieval
- Blog: Will It Zero-Shot?: Predicting Zero-Shot Classification Performance For Arbitrary Queries
- Blog: Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness
- Blog: SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
- Blog: Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
- Blog: Text as Image: Learning Transferable Adapter for Multi-Label Classification
- Blog: Zero-Shot Image Captioning with Multi-type Entity Representations
- Blog: Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
- Blog: Mitigating the Modality Gap in Vision–Language Models with Fractal Spectral Geometry
- Blog: KPL: Training-Free Medical Knowledge Mining of Vision-Language Models
- Blog: Feature Distillation Improves Zero-Shot Transfer from Synthetic Images
- Blog: AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models
- Blog: LVP-CLIP: Revisiting CLIP for Continual Learning with Label Vector Pool
- Blog: Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment
- Blog: A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
- Blog: Textual Inversion and Self-supervised Refinement for Radiology Report Generation
- Blog: Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis
- Blog: A Crowd-AI Collaborative Duo Relational Graph Learning Framework towards Social Impact Aware Photo Classification
- Blog: Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation
- Blog: Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation
- Blog: A Retrospect to Multi-prompt Learning across Vision and Language
- Blog: Online Zero-Shot Classification with CLIP
- Blog: Multimodal foundation world models for generalist embodied agents
- Blog: StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
- Blog: Semantic Robustness Certification for Vision-Language Models
- Blog: Attribute Based Interpretable Evaluation Metrics for Generative Models
- Blog: Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training
- Blog: Deep Pre-Alignment for VLMs
- Blog: Mitigate the Gap: Improving Cross-Modal Alignment in CLIP
- Blog: Visual Perception by Large Language Model’s Weights
- Blog: Calibrated Cache Model for Few-Shot Vision-Language Model Adaptation
- Blog: Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
- Blog: PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards
- Blog: As Pseudo-Label Free as Possible: Leveraging Adaptive Feature Generation for Sparsely Annotated Object Detection
- Blog: Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
- Blog: SuS-X: Training-Free Name-Only Transfer of Vision-Language Models
- Blog: TLDR: Text Based Last-Layer Retraining for Debiasing Image Classifiers
- Blog: DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation
- Blog: CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models
- Blog: Improving Contrastive Learning for Referring Expression Counting
- Blog: CAST: Cross-modal Alignment Similarity Test for Vision Language Models
- Blog: Closing the Modality Gap for Mixed Modality Search
- Blog: Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification
- Blog: CLIPMasterPrints: Fooling Contrastive Language-Image Pre-training Using Latent Variable Evolution
Showing 60 of 111 papers.
History & citation
Current · Permanent link
- This direction split from The Modality Gap in Contrastive Vision-Language Models (90% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_modality_gap_cross_modal_embedding_misal_d8b08b3c,
title = {modality gap (cross-modal embedding misalignment)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/modality-gap-cross-modal-embedding-misalignment/rdr_d8b08b3cc61d48b9a03b566053ec7261},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_modality_gap_cross_modal_embedding_misal_d8b08b3c_v1,
title = {modality gap (cross-modal embedding misalignment)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/modality-gap-cross-modal-embedding-misalignment/rdr_d8b08b3cc61d48b9a03b566053ec7261/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}