On the Design Fundamentals of Pixel Text Representation Learning

arXiv:2609.01147 · cs.CV, cs.CL · Submitted 2026-09-01 · Read on arXiv

cs.CV, cs.CL

Submitted: 2026-09-01

Updated: 2026-09-01

Code: https://github.com/Pixel-Linguist/PixelLinguist-II

Terminology

• Grounding — 23× in this paper · explained in 3 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Representation Learning — 14× in this paper · explained in 2 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Visual Document Retrieval — 8× in this paper
• Downstream Tasks — 5× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Contrastive Learning — 4× in this paper · explained in 5 episodes
• Semantic Understanding — 4× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Semantic Alignment — 2× in this paper · explained in 3 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Structural Integrity — 1× in this paper · explained in 3 episodes

Sources

• Qwen2.5-VL Technical Report
• Glyph: Scaling Context Windows via Visual-Text Compression
• Scaling Language-Free Visual Representation Learning
• Unsupervised Dense Information Retrieval with Contrastive Learning
• Representation Learning with Contrastive Predictive Coding
• Qwen2.5 Technical Report
• Language Modelling with Pixels
• Pixel Sentence Representation Learning
• EVA-CLIP: Improved Training Techniques for CLIP at Scale
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• DeepSeek-OCR: Contexts Optical Compression

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models