mlsanityData to 7 Oct 2026

Infinite Worlds with Versatile Interactions

arXiv 2607.07534 ↗First posted 8 Jul 2026cs.CVcited by 37

Not on the map. Why?

Cited by 27 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. (1) Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. (2) Through distilling a real-time variant from the base model, our system guarantees rapid response time, sufficient to drive 720p video streams at 60 fps. (3) Compared to the previous version, this update introduces highly diverse interactive elements, comprising a broader spectrum of actions (e.g., attacking, archery, spell-casting, and shooting) alongside a richer variety of text-driven events. (4) We pioneer the integration of an agentic harness within the domain of world modeling, wherein a pilot agent is tasked with planning and executing character behaviors, while a director agent is responsible for synthesizing novel environmental elements as the scene progresses. Additionally, to facilitate a shared experience, we develop an interface that permits multiple players to simultaneously immerse themselves in this vivid world simulator. We pair our primary 14B model with a lightweight 1.3B counterpart, which supports effortless deployment on a single GPU.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 51 of its 59 references that are in the map. First posted on arXiv 8 Jul 2026.

Builds on

51 of 59 references.

References · 51

  1. 2023Consistency Modelscited by 1,778
  2. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  3. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  4. 2024LTX-Video: Realtime Video Latent Diffusioncited by 549
  5. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  6. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 401
  7. 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 389
  8. 2024OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationcited by 332
  9. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 314
  10. 2025MAGI-1: Autoregressive Video Generation at Scalecited by 262
  11. 2025LongLive: Real-time Interactive Long Video Generationcited by 237
  12. 2020The EPIC-KITCHENS Dataset: Collection, Challenges and Baselinescited by 221
38 more
  1. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  2. 2019Understanding and Improving Layer Normalizationcited by 213
  3. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 191
  4. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 174
  5. 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 166
  6. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 159
  7. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  8. 2026Advancing Open-source World Modelscited by 144
  9. 2025PaddleOCR 3.0 Technical Reportcited by 136
  10. 2024Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Contentcited by 132
  11. 2024GameGen-X: Interactive Open-world Game Video Generationcited by 124
  12. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 97
  13. 2026Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memorycited by 86
  14. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  15. 2023LLM-grounded Video Diffusion Modelscited by 83
  16. 2022My View is the Best View: Procedure Learning from Egocentric Videoscited by 81
  17. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 81
  18. 2025Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rolloutcited by 78
  19. 2025Yume-1.5: A Text-Controlled Interactive World Generation Modelcited by 77
  20. 2023Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animatorcited by 74
  21. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 72
  22. 2024VidGen-1M: A Large-Scale Dataset for Text-to-video Generationcited by 60
  23. 2025GigaWorld-0: World Models as Data Engine to Empower Embodied AIcited by 60
  24. 2024xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelismcited by 55
  25. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 50
  26. 2026Solaris: Building a Multiplayer Video World Model in Minecraftcited by 38
  27. 2026DreamX-World 1.0: A General-Purpose Interactive World Modelcited by 33
  28. 2024StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaborationcited by 28
  29. 2025StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generationcited by 27
  30. 2026LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generationcited by 25
  31. 2026ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignmentcited by 23
  32. 2026minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Modelscited by 19
  33. 2026ActWorld: From Explorable to Interactive World Model via Action-Aware Memorycited by 13
  34. 2026MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generationcited by 8
  35. 2026CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narrativescited by 8
  36. 2026MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanismcited by 6
  37. 2025ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Accesscited by 5
  38. 2026WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memorycited by 4

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 37.

37 papers.

Sort:

By area:

  1. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 30
  2. 2026Alaya-EVOKE: From Linear-Scaling Supervision to Endless Worldcited by 13
  3. 2026Code World Model: Coding Agent as World Braincited by 9
  4. 2026SolarWM: Open Data and Scalable Training for Long-Horizon Video World Modelscited by 9
  5. 2026Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memorycited by 7
  6. 2026Programmable World Modelcited by 7
  7. 2026Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillationcited by 5
  8. 2026H3-World: Turning Language Understanding into World Controlcited by 4
  9. 2026HarnessEval-W: Agentifying the Evaluation of Visual Worldscited by 3
  10. 2026Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Controlcited by 3
  11. 2026Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attentioncited by 2
  12. 2026ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadowcited by 2
25 more
  1. 2026Sekai2: From World Exploration to Interactive World Modelingcited by 2
  2. 2026ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Modelscited by 2
  3. 2026Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rolloutcited by 2
  4. 2026WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotationscited by 1
  5. 2026ConsistWorld: Evidence Routing for Consistent Multi-Agent World Modelscited by 1
  6. 2026WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memorycited by 1
  7. 2026GameDirector: Decoupling Gameplay Logic from Rendering for Player-Configurable Game World Modelscited by 1
  8. 2026Precise Editing and Flexible Referencing for Interactable Worldscited by 1
  9. 2026Oneira: From Open-Ended Generation to Open-World Interaction in Video World Modelscited by 1
  10. 2026MiniWorld: Democratizing the Training of Video World Models from Scratchcited by 0
  11. 2026SCOPE: Score-Isolated Agentic Optimization for Video World Modelscited by 0
  12. 2026N0-Foundation: Towards the Age of Tactile Intelligencecited by 0
  13. 2026World in World: Explore the World with World Modelscited by 0
  14. 2026HappyWorld-Benchcited by 0
  15. 2026QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video Generationcited by 0
  16. 2026Code Plans, Diffusion Renders: Open-Ended Generative World Modelingcited by 0
  17. 2026HelloWorld: Towards Practical Applications of Generative Driving World Modelscited by 0
  18. 2026OPIS: An Input-Grounded Benchmark for Multi-Object Memory in Video World Modelscited by 0
  19. 2026WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizoncited by 0
  20. 2026One-Step Next-Latent Prediction Is Not a World Modelcited by 0
  21. 2026HelixWorld: A Real-time Interactive Audio-Visual World Modelcited by 0
  22. 2026DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistencycited by 0
  23. 2026Memorizon: Training World Models Beyond Their Context Windowcited by 0
  24. 2026Towards Subject Consistency over Dynamic Subject Sets in Video Generationcited by 0
  25. 2026AgentGarten: Code Worlds for Evolving Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AlayaWorld: Long-Horizon and Playable Video World Generation
  2. 2026Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
  3. 2026ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
  4. 2025Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model
  5. 2026MultiWorld: Scalable Multi-Agent Multi-View Video World Models
  6. 2026GameWAM: A World Action Model for Video Games
  7. 2026From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
  8. 2026PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives