Smart Content Ingestion for Generative AI Workloads

arXiv:2610.07091 · cs.AI, cs.CL, cs.CV, cs.IR · Submitted 2026-10-05 · Read on arXiv

cs.AI, cs.CL, cs.CV, cs.IR

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/VikParuchuri/marker

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generative AI — 1× in this paper · explained in 2 episodes

Sources

• Docling Technical Report
• Nougat: Neural Optical Understanding for Academic Documents
• The Faiss library
• Gemini: A Family of Highly Capable Multimodal Models
• Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
• SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
• MinerU: An Open-Source Solution for Precise Document Content Extraction

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems