Haruto Yoshida, Keito Kudo, Yoichi Aoki, Ryota Tanaka, Itsumi Saito, Keisuke Sakaguchi, Kentaro Inui
| Challenge: | Experimental results show vision models struggle to identify diagram attributes such as node colors and shapes, along with edge colors and connection patterns. |
| Approach: | They evaluated vision models and retrieving diagrams using text queries to determine how well they recognize diagram attributes and edge connection patterns. |
| Outcome: | The models can recognize node colors, shapes, and edge colors, but struggle to identify differences in edge connection patterns that play a pivotal role in the semantics of diagrams. |
Similar Papers
Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that CLIP models struggle with visual reasoning tasks . despite the success of Contrastive Language-Image Pretraining, there are still limitations . |
| Approach: | They propose to use a visual encoder to train CLIP-like models for fine-grained visual reasoning tasks. |
| Outcome: | The proposed models outperform CLIP-like encoders in visual reasoning tasks . the study highlights the importance of VLM architectural choices . |
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. |
Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that direct generation of diagram descriptions is costly and biased against blind and low-vision (BLV) users. |
| Approach: | They ask sighted individuals to assess diagram descriptions generated by vision-language models . they use latent supervision to guide the models with latent inference . |
| Outcome: | The results show that visual descriptions generated by vision-language models are effective and useful to educators who are themselves BLV and teach visually impaired learners. |
Do Vision-Language Models Understand Compound Nouns? (2024.naacl-short)
Copied to clipboard
| Challenge: | Open-vocabulary vision-language models (CLIP) are emerging as a promising new paradigm for text-to-image retrieval. |
| Approach: | They propose a benchmark to evaluate the effectiveness of open-vocabulary vision-language models (CLIP) for text-to-image retrieval using contrastive loss. |
| Outcome: | The proposed framework improves CN understanding of CLIP by 8.25% on Compun. |
If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies assume that VLMs prioritize visual attributes to represent concepts. |
| Approach: | They propose a novel approach to characterize features important for VLMs using reinforcement learning. |
| Outcome: | The proposed approach characterizes features that are important for VLMs . it shows that spurious descriptions have a major role in VLM representations despite providing no helpful information. |
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. |
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities (2025.acl-long)
Copied to clipboard
| Challenge: | Vision-language Models have been shown to be highly capable but lacking basic visual understanding skills. |
| Approach: | They propose to examine the limitations of vision-language models on visual tasks by constructing a series of tests that probe which components of design may be lacking. |
| Outcome: | The proposed tests compare VLMs to other models on visual encoders, intermediate vision-language projection and LLM-decoder outputs. |
Can VLMs Actually See and Read? A Survey on Modality Collapse in Vision-Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Vision-language models integrate textual and visual information, enabling them to process visual inputs and generate predictions. |
| Approach: | They review work on modality collapse analysis to provide insights into the reason for this unintended behavior and review probing studies for fine-grained vision-language understanding. |
| Outcome: | The proposed models can achieve competitive performance in vision-language tasks despite relying heavily on textual information and ignoring visual information. |
Delving into the Openness of CLIP (2023.findings-acl)
Copied to clipboard
| Challenge: | Contrastive Language-Image Pre-training (CLIP) allows for open-vocabulary visual recognition, where the model can recognize images from an open class set in a zero-shot manner. |
| Approach: | They propose to use image classification as an image-to-text matching task instead of discrete category IDs to achieve open-vocabulary visual recognition. |
| Outcome: | The proposed model can recognize images from an open vocabulary in a zero-shot manner, but its performance deteriorates as the vocabulary expands. |
Paparazzi: A Deep Dive into the Capabilities of Language and Vision Models for Grounding Viewpoint Descriptions (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing language and vision models can be used for language understanding in 3D environments . however, existing models lack specific properties and biases that limit their performance . |
| Approach: | They propose a framework that uses a camera to generate images from different viewpoints and evaluate them in terms of their similarity to natural language descriptions. |
| Outcome: | The proposed model performs poorly on most canonical views and fine-tunes using hard negative sampling and random contrasting yields good results even under conditions with little available training data. |