Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?
Jiankun Wang, Yisen Gao, Ziwei Zhang, Xingcheng Fu, Jiaxin Bai, Chen Gao
cs.CL, cs.CV
Submitted: 2026-08-07
Updated: 2026-08-10
Code: https://github.com/wjkuser/ECF
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs
- LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
- RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding
- Large Language Diffusion Models
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents
- InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts
- Autoregressive Models in Vision: A Survey
- Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone
- LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
- Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models
- Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective
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