Challenge: PIXEL is a vision transformer that has been pre-trained on rendered text . however, it is not able to outperform monolingual subwords like BERT .
Approach: They propose to use PIXEL as a vision transformer to train on rendered text to explore the gap between its visual and linguistic understanding.
Outcome: The proposed model outperforms monolingual subword models in most other contexts, but it lacks the linguistic knowledge to perform in language tasks.

Similar Papers

Evaluating Pixel Language Models on Non-Standardized Languages (2025.coling-main)

Copied to clipboard

Challenge: pixel-based models can be used to transfer learning from standard languages to dialects . pretrained language models achieve strong results for languages seen during training, but their performance declines with out-of-domain dialects.
Approach: They compare pixel-based models to token-based ones to evaluate dialects . standard german is tokenized in a more meaningful way, whereas the Bern dialect is tokenize in pixel form .
Outcome: The proposed models outperform token-based models in part-of-speech tagging, dependency parsing and intent detection for zero-shot dialect evaluation by up to 26 percentage points in some scenarios, though not in Standard German.
Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer (2023.emnlp-main)

Copied to clipboard

Challenge: Recent work shows that pixel representations can be finetuned across scripts without vocabulary extensions, adapters, or transliteration.
Approach: They propose to use pixel representations to train multilingual machine translation models . they explore parameter sharing within and across scripts to better understand where they lead to positive transfer .
Outcome: The proposed model improves on two multilingual datasets with different language coverage compared to subword embeddings . the proposed model can be finetuned cross-lingually or to unseen scripts, and is more data-efficient than other alternatives such as vocabulary expansion .
Multilingual Pretraining for Pixel Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: PIXEL-M4 model pretrains on four visually and linguistically diverse languages . previous work on pixel-based language models focused on monolingual pretraining on English data .
Approach: They propose a pixel-based language model that is pretrained on four visually diverse languages.
Outcome: The proposed model outperforms an English-only counterpart on non-Latin scripts on semantic and syntactic tasks.
Text Rendering Strategies for Pixel Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Recent approaches to rendering text use a large set of almost-equivalent input patches, which may prove sub-optimal for downstream tasks due to redundancy in the input representations.
Approach: They propose four approaches to rendering text in a PIXEL model using character bigrams and patch frequency biases.
Outcome: The proposed models perform better on sentence-level tasks without compromising performance on token-level or multilingual tasks.
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.
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.
From Words to Pixels: A Comprehensive Survey on Large Language Models in Visual Segmentation (2026.acl-long)

Copied to clipboard

Challenge: Visual segmentation with instruction has been a challenging task for many years . large language models and large multimodal models have spurred a new wave of research .
Approach: They review recent works in LLM-based visual segmentation and analyze their architectural innovations, training strategies, and benchmark performance.
Outcome: The present study reviews the most recent works in LLM-driven visual segmentation . it identifies key challenges and promising future directions .
Autoregressive Pre-Training on Pixels and Texts (2024.emnlp-main)

Copied to clipboard

Challenge: pixel-based language modeling integrates visual and textual data to improve performance of language models.
Approach: They propose a method that integrates visual and textual data into an autoregressive framework.
Outcome: The proposed method improves performance of pixel-based language models by incorporating visual and textual data.
PIXAR: Auto-Regressive Language Modeling in Pixel Space (2024.findings-acl)

Copied to clipboard

Challenge: Recent work shows the possibility of building open-vocabulary large language models that operate on pixel representations.
Approach: They propose a pixel-based autoregressive LLM that performs generative tasks . they propose an adversarial pretraining stage that improves the readability and accuracy of PIXAR by 8.1 on LAMBADA and 8.5 on bAbI.
Outcome: The proposed model performs free-form generative tasks while keeping the number of parameters on par with previous encoder-decoder models.
Are Visual-Linguistic Models Commonsense Knowledge Bases? (2022.coling-1)

Copied to clipboard

Challenge: PTLMs are used to extract knowledge from text on demand.
Approach: They compare visual-linguistic and language-only visual-language models in a zero-shot commonsense question answering inference task.
Outcome: The proposed models are highly promising on certain types of commonsense knowledge associated with the visual world.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations