cross-modal reasoning

4 papers

• Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering
• C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction
• TRAP: Targeted Redirecting of Agentic Preferences
• Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation