跨房间3D场景理解遇上拓扑感知多模态大模型，突破单一空间局限，推动空间智能新边界。
arXiv:2607.06534v1 Announce Type: new Abstract: Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in si…
用文本精准描述3D场景，为多模态理解开辟新方向，论文含金量十足。
arXiv:2607.02908v1 Announce Type: new Abstract: This work introduces holo-captioning, a novel task that strives to seek the text equivalent of 3D scen…
ICRA挑战赛技术报告：用DINOv3搞定户外机器人场景的细粒度语义分割，鲁棒又精准。
arXiv:2606.18582v1 Announce Type: new Abstract: The GOOSE 2D Fine-Grained Semantic Segmentation Challenge at the ICRA 2026 Workshop on Field Robotics …
用全景画布统一多视图特征，无需复杂几何编码器，实现轻量级3D场景理解。
arXiv:2606.19253v1 Announce Type: cross Abstract: Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on comple…
结合密集3D场景补全与生成式新视角合成，显著提升视图生成的几何一致性和质量。
arXiv:2506.10981v2 Announce Type: replace Abstract: Generative models have shown great promise for novel view synthesis (NVS) by leveraging strong ima…
用强化学习微调视频输入，让3D场景理解精度与泛化性同步提升
arXiv:2603.04976v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative para…
零样本本体对齐新突破，用LLM将USD场景自动转化为知识图谱，机器人语义理解再进一步。
arXiv:2606.09134v1 Announce Type: cross Abstract: Constructing knowledge graphs from 3D simulation scenes is essential for robot task reasoning, but t…
突破性提出统一3D多模态大模型，部件感知表示让场景理解更细粒度。
arXiv:2606.06485v1 Announce Type: new Abstract: Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3…
利用图像基础模型实现可扩展的3D人体放置，虚拟场景与AI融合的前沿突破。
arXiv:2604.19673v2 Announce Type: replace Abstract: Training embodied agents to understand 3D scenes as humans do requires large-scale data of people …
EgoVis 2026 CASTLE挑战赛亚军方案的技术报告，详解多模态场景理解新方法MARS，视觉AI进阶必读
arXiv:2605.18176v1 Announce Type: new Abstract: This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system fo…
实时理解多模态世界的AI模型，开创实时世界模型新范式
The first real-time multimodal world model Discussion | Link