Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding

arXiv:2609.00756 · cs.CL · Submitted 2026-09-01 · Read on arXiv

cs.CL

Submitted: 2026-09-01

Updated: 2026-09-01

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

Terminology

• Accuracy — 36× in this paper · explained in 1 episode
• Mutual Reinforcement Effect — 5× in this paper
• Ablation — 4× in this paper · explained in 1 episode
• Distillation — 4× in this paper · explained in 2 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• M-MRE: Extending the Mutual Reinforcement Effect to Multimodal Information Extraction
• Unifying distillation and privileged information
• Understanding intermediate layers using linear classifier probes
• Qwen3-VL Technical Report
• Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Learning by Distilling Context
• Spatial Dual-Modality Graph Reasoning for Key Information Extraction

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering