OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
cs.CL
Submitted: 2026-11-10
Updated: 2026-11-11
Code: https://github.com/brighterr/OpticalRAG
Terminology
Sources
- M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
- AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
- META-RAG: Meta-Analysis-Inspired Evidence-Re-Ranking Method for Retrieval-Augmented Generation in Evidence-Based Medicine
- TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
- Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
- General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
- DeepSeek-OCR: Contexts Optical Compression
- DeepSeek-OCR 2: Visual Causal Flow
- Qwen2.5 Technical Report
- Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
- LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data