spatial-intelligence topic
SPA
[ICLR 2025] SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
SpatialLM
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
awesome-3d-4d-world-models
🌐 3D and 4D World Modeling: A Survey
LiDARCrafter
[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
HourVideo
[NeurIPS 2024] Official code for HourVideo: 1-Hour Video Language Understanding
Aether
[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling
SpatialVID
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Spatial-MLLM
Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
G2VLM
G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
Mirage
Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)