Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that deep vision-only and language-only models project inputs into a partially aligned representational space. |
| Approach: | They investigate whether a model's representational code is semantically shared . they find that alignment peaks in mid-to-late layers of both model types . |
| Outcome: | a forced-choice "Pick-a-Pic" task shows human preferences for image-caption matches are mirrored in embedding spaces across vision-language model pairs. |
Similar Papers
Probing Contextual Language Models for Common Ground with Visual Representations (2021.naacl-main)
Copied to clipboard
| Challenge: | Contextual language models have attracted great interest in probing what is encoded in their representations. |
| Approach: | They propose a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. |
| Outcome: | The proposed model outperforms text-only language models in instance retrieval, but underperform humans. |
Vision-Language Models Align with Human Neural Representations in Concept Processing (2026.eacl-long)
Copied to clipboard
| Challenge: | Recent studies suggest that transformer-based vision-language models capture the multimodality of concept processing in the human brain. |
| Approach: | They analysed multiple VLMs employing different strategies to integrate visual and textual modalities, along with language-only counterparts. |
| Outcome: | The transformer-based vision-language models outperform language-only models in two experimental conditions, while only some outperformed the language-based models. |
Deep Generative Model for Joint Alignment and Word Representation (N18-1)
Copied to clipboard
| Challenge: | EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. |
| Approach: | They exploit translation as a distributional context and embed words as posterior probability densities, rather than point estimates, which allows them to compare words in context using a measure of overlap between distributions. |
| Outcome: | The proposed model performs on a range of lexical semantics tasks and achieves competitive results on benchmarks including natural language inference, paraphrasing, and text similarity. |
Understanding Cross-Lingual Alignment—A Survey (2024.findings-acl)
Copied to clipboard
| Challenge: | Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models. |
| Approach: | They propose a taxonomy of methods to improve cross-lingual alignment . they argue that an effective trade-off between language-neutral and language-specific information is key . |
| Outcome: | The proposed methods can be applied to encoder models and encoder-decoder-only models . they show that language-neutral and language-specific information is key . |
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes (2024.naacl-long)
Copied to clipboard
| Challenge: | Modern neural language models (LMs) require distinctly un-human-like ways to achieve these results. |
| Approach: | They train a diverse set of LM architectures with and without auxiliary visual supervision on datasets of varying scales. |
| Outcome: | The proposed models exhibit better learning of syntactic categories, lexical relations, semantic features, word similarity and alignment with human neural representations. |
Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | a recent study shows that vision-language models have modality gaps that persist even in well-aligned models. |
| Approach: | They propose a modality-dominance score to measure and leverage modality gaps . they propose automatic interpretability metrics to evaluate these features in a scalable manner . |
| Outcome: | The proposed framework allows for training-free probing and editing methods for understanding model perception across genders and generating adversarial examples. |
Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning (2025.acl-short)
Copied to clipboard
| Challenge: | Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages. |
| Approach: | They propose to use image captions to implicitly align text representations between languages to make them usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval. |
| Outcome: | The proposed approach is usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval. |
Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models have demonstrated robust performance on various language tasks using zero-shot or few-shot learning paradigms. |
| Approach: | They propose to use open-source, open-access language models to make visual input accessible to the model using separate verbalisation models. |
| Outcome: | The proposed model can handle visual input but also require strong reasoning component. |
Does Vision Accelerate Hierarchical Generalization in Neural Language Learners? (2025.coling-main)
Copied to clipboard
| Challenge: | Neural language models (LMs) are arguably less data-efficient than humans from a language acquisition perspective. |
| Approach: | They investigate the advantage of grounded language acquisition over visual input to improve syntactic generalization. |
| Outcome: | The proposed model is less efficient than humans in language acquisition . it shows that visual input helps syntactic generalization, but not vision . |
Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing vision-and-language models perform better on multimodal tasks, but there is little understanding of how multimodal learning can help visual representations. |
| Approach: | They conduct a probing analysis of visual representations in existing vision-and-language models and vision-only models by probing on a broad range of tasks. |
| Outcome: | The proposed model improves vision-and-language models on label and attribute prediction tasks while vision-only models are stronger on dense prediction tasks. |