arXiv Computation and Language
Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation
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 Computation and Language
2d ago
On the Design Fundamentals of Pixel Text Representation Learning
arXiv:2609.01147v1 Announce Type: cross Abstract: Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders strug...
arXiv Computer Vision
4d ago
What Can Low Resource Languages Learn From Each Other?
The paper examines OCR adaptation for low‑resource languages, noting that fine‑tuning often hits a performance ceiling in data‑scarce settings. It identifies that lower layers of language‑specific models learn redundant features while higher layers capture script nuances, leading to a structural inefficiency. To address this, the authors propose PSMC, a framework that pre‑trains a base model, specializes it per language, merges the experts via task arithmetic, and co‑trains a unified multilingual backbone, achieving about a 2% improvement in Word Recognition Rate across 10 Indian scripts without adding parameters.
arXiv AI
Aug 12
On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation
arXiv:2608. 11002v1 Announce Type: cross Abstract: Text-to-image (T2I) generation has achieved remarkable progress in recent years.
arXiv Computation and Language
Aug 28
Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation
The paper introduces PuMVR, a benchmark of 1,000 Punjabi image‑text pairs spanning three scripts—Gurmukhi, Shahmukhi, and Roman—to evaluate Vision‑Language Models (VLMs). Testing ten state‑of‑the‑art VLMs reveals a significant Script Gap: models perform well in one script but poorly in another, with accuracy differences up to 16%. The authors propose the Script Consistency Rate (SCR) as a new metric, noting it can be as low as 24.8% on their benchmark, and argue that current multilingual VLMs are not truly multi‑script.
arXiv AI
Jun 2
Hot-Start Chinese Language Modeling:Visual Glyphs Accelerate Sample-Efficient Learning
arXiv:2601. 09566v4 Announce Type: replace-cross Abstract: In this work, we study whether rendering Chinese characters as visual glyph images, rather than discrete token IDs as mainstream LLMs do, providing an inductive bias for character-level language modeling.
arXiv AI
Jul 7
Full Glyph Images Beat Token Embeddings: A Controlled Study for Transformers
arXiv:2607. 03994v1 Announce Type: cross Abstract: Modern language models generally represent text as sequences of discrete token embeddings, an assumption deeply rooted in current practice but rarely questioned.