visual question-answering

5 papers

• Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search
• MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
• MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
• SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
• mmWalk: Towards Multi-modal Multi-view Walking Assistance