VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Also Consider

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

1. 1Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy2025
2. 2Spatial 3D-LLM: Exploring Spatial Awareness in 3D Vision-Language Models2025
3. 3Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning2025
4. 4OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision2025
5. 5SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models2025