arXiv Computation and Language
On the Design Fundamentals of Pixel Text Representation Learning
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Oct 2
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
LensVLM is an inference framework and post‑training recipe that lets Vision‑Language Models (VLMs) process compressed images of text by selectively expanding only the relevant parts back to full resolution. Using Qwen3.5‑9B‑Base, LensVLM achieves accuracy comparable to full‑text models at 4.3× compression and outperforms other compression baselines up to 10.1× across seven text QA benchmarks, while also improving performance on multimodal document and code tasks as compression increases.
arXiv Computation and Language
4d ago
More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training
arXiv:2610.19443v1 Announce Type: new Abstract: Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual input...
arXiv Computer Vision
Sep 10
Let ViT Speak: Generative Language-Image Pre-training
arXiv:2605.00809v3 Announce Type: replace Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining...
arXiv Computation and Language
Sep 1
Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation
arXiv:2608.30541v1 Announce Type: new Abstract: Pixel-based language models (LMs) replace traditional tokenizers by processing rendered images of text, making cross-lingual transfer heavily dependent...
arXiv AI
Jun 2
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.
arXiv Machine Learning
Aug 13
Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
arXiv:2605. 16409v3 Announce Type: replace-cross Abstract: Optical character recognition (OCR) and multilingual scene-text understanding remain challenging for multimodal large language models (MLLMs), particularly in real-world images containing small or degraded text, cluttered layouts, occlusion, handwriting, and complex typography.