[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

🌐 3D and 4D World Modeling: A Survey

InternRobotics' open platform for building generalized navigation foundation models.

[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling

[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

[NeurIPS 2025] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

[CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

[CVPR 2025] Source codes for the paper "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning"

[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D

[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

Visual Spatial Tuning

Scaling Spatial Intelligence with Multimodal Foundation Models

[ICLR 2025] SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

[ICCV 2025] Perspective-Invariant 3D Object Detection

[NeurIPS 2024] Official code for HourVideo: 1-Hour Video Language Understanding

🌐 Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

[NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"

[CVPR 2025] Code for "StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation".

[CVPR 2026] Thinking in 360°: Humanoid Visual Search in the Wild

Holistic Evaluation of Multimodal LLMs on Spatial Intelligence

[Awesome-Spatial-VLMs] This repository is the official, community-maintained resource for the survey paper: Spatial Intelligence in Vision-Language Models: A Comprehensive Survey;

[ICLR 2025] Where Am I and What Will I See : An Auto-Regressive Model for Spatial Localization and View Prediction

[NeurIPS 2025] SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

Official repository for "Vid2World: Crafting Video Diffusion Models to Interactive World Models" (ICLR 2026), https://arxiv.org/abs/2505.14357

Multimodal datasets for spatial intelligence

[ICRA 2026] Official codebase for NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions

🌐 A Roadmap for 3D Scene Understanding in the Wild