mlsanityData to 14 Oct 2026

Scaling Spatial Intelligence with Multimodal Foundation Models

arXiv 2511.13719 ↗First posted 17 Nov 2025cs.CV cs.AI cs.LGcited by 82

Not on the map. Why?

Cited by 52 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the SenseNova-SI family, built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and generation models (i.e., Bagel). We take a principled approach to constructing high-performing and robust spatial intelligence by systematically curating SenseNova-SI-8M: eight million diverse data samples under a rigorous taxonomy of spatial capabilities. SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks: 68.8% on VSI-Bench, 43.3% on MMSI, 85.7% on MindCube, 54.7% on ViewSpatial, 47.7% on SITE, 63.9% on BLINK, 55.5% on 3DSR, and 72.0% on EmbSpatial, while maintaining strong general multimodal understanding (e.g., 84.9% on MMBench-En). More importantly, we analyze the impact of data scaling, discuss early signs of emergent generalization capabilities enabled by diverse data training, analyze the risk of overfitting and language shortcuts, present a preliminary study on spatial chain-of-thought reasoning, and validate the potential downstream application. All newly trained multimodal foundation models are publicly released.

Key facts. Cited by 82 papers in the map (data through 14 Oct 2026). Builds on 54 of its 66 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

54 of 66 references.

References · 54

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  6. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  8. 2015VQA: Visual Question Answeringcited by 2,506
  9. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  10. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  11. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  12. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
38 more
  1. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  2. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  3. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  4. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  5. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  6. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  7. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  8. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 611
  9. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 490
  10. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  11. 2025Seed1.5-VL Technical Reportcited by 373
  12. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 311
  13. 2022Visual Spatial Reasoningcited by 293
  14. 2021IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoningcited by 267
  15. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 221
  16. 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligencecited by 217
  17. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligencecited by 183
  18. 2025VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstructioncited by 166
  19. 2025SpaceR: Reinforcing MLLMs in Video Spatial Reasoningcited by 159
  20. 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawingcited by 136
  21. 2025Cambrian-S: Towards Spatial Supersensing in Videocited by 134
  22. 2025ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Modelscited by 118
  23. 2024SAT: Dynamic Spatial Aptitude Training for Multimodal Language Modelscited by 114
  24. 2025OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Modelscited by 114
  25. 2024Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Modelscited by 113
  26. 2025MindCube: Spatial Mental Modeling from Limited Viewscited by 95
  27. 2025SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Modelscited by 90
  28. 2025Visual Spatial Tuningcited by 89
  29. 2025Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Viewscited by 65
  30. 2025Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awarenesscited by 63
  31. 2019AI2D-RST: A multimodal corpus of 1000 primary school science diagramscited by 60
  32. 2025Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Modelscited by 52
  33. 2023Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understandingcited by 46
  34. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  35. 2024Cubify Anything: Scaling Indoor 3D Object Detectioncited by 39
  36. 2024Core Knowledge Deficits in Multi-Modal Language Modelscited by 38
  37. 2020Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3Dcited by 30
  38. 2025SITE: towards Spatial Intelligence Thorough Evaluationcited by 29

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 81.

82 papers.

Sort:

By area:

  1. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 50
  2. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 32
  3. 2026Think3D: Thinking with Space for Spatial Reasoningcited by 24
  4. 2026Thinking with Geometry: Active Geometry Integration for Spatial Reasoningcited by 18
  5. 2026Wall-OSS-0.5 Technical Reportcited by 12
  6. 2026CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environmentscited by 11
  7. 2026On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMscited by 11
  8. 2026ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creationcited by 7
  9. 2026SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Taskscited by 7
  10. 2026Vision as Unified Multimodal Generationcited by 7
  11. 2026Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoningcited by 6
  12. 2026Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligencecited by 6
38 more
  1. 2026OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligencecited by 6
  2. 2026GEM: Generative Supervision Helps Embodied Intelligencecited by 6
  3. 2026OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMscited by 6
  4. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 6
  5. 2026Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Modelscited by 6
  6. 2025A Benchmark for Omni-Modal Reasoning in Long Videoscited by 5
  7. 2026Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiationcited by 5
  8. 2026SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environmentscited by 5
  9. 2026Cambrian-P: Pose-Grounded Video Understandingcited by 5
  10. 2026Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulatorscited by 5
  11. 2026Orthogonal Model Mergingcited by 4
  12. 2026See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoningcited by 4
  13. 2026Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMscited by 4
  14. 2026ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Modelscited by 4
  15. 2026Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streamscited by 4
  16. 2026MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photoscited by 4
  17. 2026Towards Spatial Supersensing in the Wildcited by 4
  18. 2026Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMscited by 4
  19. 2026MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Modelcited by 3
  20. 2026HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Modelscited by 3
  21. 2026Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Viewscited by 3
  22. 2026SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoningcited by 2
  23. 2026Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sportscited by 2
  24. 2026DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Drivingcited by 2
  25. 2026ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMscited by 2
  26. 2026SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motioncited by 2
  27. 2026OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mappingcited by 2
  28. 2026Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMscited by 2
  29. 20263D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understandingcited by 1
  30. 2026Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Modelscited by 1
  31. 2026SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMscited by 1
  32. 2026Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligencecited by 1
  33. 2026Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMscited by 1
  34. 2026SpaceDG: Benchmarking Spatial Intelligence under Visual Degradationcited by 1
  35. 2026Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoningcited by 1
  36. 2026GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understandingcited by 1
  37. 2026SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Modelscited by 1
  38. 2026From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning?cited by 0

50 most cited of 82 All 82 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence
  2. 2025SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
  3. 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
  4. 2025Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
  5. 2025Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study
  6. 2026Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
  7. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
  8. 2025Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics