6 results for “topic:3d-llms”
[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
[CVPR 2025 Highlight🔥] Official code repository for "Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning"
[NeurIPS 2024] MSR3D: Advanced Situated Reasoning in 3D Scenes
[ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness
[ICLR 2026] SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes
🌐 Develop a unified 3D reconstruction and spatial reasoning model that combines geometry with vision and language tasks for enhanced AI understanding.