mlsanityData to 14 Oct 2026

Spatia: Video Generation with Updatable Spatial Memory

arXiv 2512.15716 ↗First posted 17 Dec 2025cs.CV cs.AIcited by 40

Not on the map. Why?

Cited by 20 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To overcome this limitation, we propose Spatia, a spatial memory-aware video generation framework that explicitly preserves a 3D scene point cloud as persistent spatial memory. Spatia iteratively generates video clips conditioned on this spatial memory and continuously updates it through visual SLAM. This dynamic-static disentanglement design enhances spatial consistency throughout the generation process while preserving the model's ability to produce realistic dynamic entities. Furthermore, Spatia enables applications such as explicit camera control and 3D-aware interactive editing, providing a geometrically grounded framework for scalable, memory-driven video generation.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 101 of its 117 references that are in the map. First posted on arXiv 17 Dec 2025.

Builds on

101 of 117 references.

References · 101

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  7. 2022Scalable Diffusion Models with Transformerscited by 6,054
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  9. 2022Flow Matching for Generative Modelingcited by 5,702
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  12. 2023Qwen Technical Reportcited by 3,344
38 more
  1. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  4. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  6. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  7. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  10. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  11. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  12. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  13. 2024SnapKV: LLM Knows What You are Looking for Before Generationcited by 880
  14. 2023H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Modelscited by 832
  15. 2024Genie: Generative Interactive Environmentscited by 747
  16. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 681
  17. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 652
  18. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  19. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 579
  20. 2025Kimi K2: Open Agentic Intelligencecited by 567
  21. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  22. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 535
  23. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  24. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 457
  25. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 433
  26. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  27. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  28. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  29. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 349
  30. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  31. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  32. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 328
  33. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  34. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 313
  35. 2023Effective Long-Context Scaling of Foundation Modelscited by 303
  36. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 300
  37. 2024Diffusion Models Are Real-Time Game Enginescited by 296
  38. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 296

50 most cited of 101 All 101 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 40.

40 papers.

Sort:

By area:

  1. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 44
  2. 2026MIND: Benchmarking Memory Consistency and Action Control in World Modelscited by 35
  3. 2026LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Modelscited by 28
  4. 2026MosaicMem: Hybrid Spatial Memory for Controllable Video World Modelscited by 27
  5. 2026Latent Spatial Memory for Video World Modelscited by 17
  6. 2026MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Enginescited by 16
  7. 2026AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memoriescited by 15
  8. 2026EgoSim: Egocentric World Simulator for Embodied Interaction Generationcited by 14
  9. 2026Out of Sight, Out of Mind? Evaluating State Evolution in Video World Modelscited by 13
  10. 2026Current World Models Lack a Persistent State Corecited by 12
  11. 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generationcited by 11
  12. 2026MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Datacited by 10
28 more
  1. 2026Evolution of Video Generative Foundationscited by 7
  2. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  3. 2026Echo-Memory: A Controlled Study of Memory in Action World Modelscited by 6
  4. 2026WorldOlympiad: Can Your World Model Survive a Triathlon?cited by 6
  5. 2026AlayaWorld: Long-Horizon and Playable Video World Generationcited by 6
  6. 2026From Pixels to States: Rethinking Interactive World Models as Game Enginescited by 4
  7. 2026SpatialCrafter: Single Image World Modeling with Generative 3D Proxiescited by 3
  8. 2026I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generationcited by 2
  9. 2026E3C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Controlcited by 2
  10. 2026DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memorycited by 2
  11. 2026MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generationcited by 2
  12. 2026Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Modelscited by 1
  13. 2026Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generationcited by 1
  14. 2026OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mappingcited by 1
  15. 2026ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integrationcited by 0
  16. 2026Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generationcited by 0
  17. 2026Code Plans, Diffusion Renders: Open-Ended Generative World Modelingcited by 0
  18. 2026Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Modelscited by 0
  19. 2026Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generationcited by 0
  20. 2026Honeycomb: Constant-Size Scene Memory Representation for Video World Modelscited by 0
  21. 2026LongLive-Plug: Once-for-All Distillation for Video Generationcited by 0
  22. 2026Enhancing Autoregressive Video Generation via Representation Adversarial Distillationcited by 0
  23. 2026WorldAlign: Decoupled 4D Reward for World-Consistent Video Generationcited by 0
  24. 2026Totem: Object-Centric 3D Memory for World-Consistent Video Generationcited by 0
  25. 2026World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Modelscited by 0
  26. 20264LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modelingcited by 0
  27. 2026Long-horizon Video Generation with Slot Memory Addressed By Region Tokenscited by 0
  28. 2026Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generationcited by 0