Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1. 1MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models2025
2. 2Latent Visual Reasoning2025
3. 3Progressive Visual Rationale for Multimodal Chain-of-Thought in Large Vision-Language ModelsOriginal Research · 2026
4. 4Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning2025
5. 5Enhancing Large Vision-Language Models via Quantized Grounded Reasoning2025