World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
hub Canonical reference
Video world models with long-term spatial memory
Canonical reference. 89% of citing Pith papers cite this work as background.
15
Pith papers citing it
Background
89% of classified citations
hub tools
citation-role summary
background 8
baseline 1
citation-polarity summary
representative citing papers
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
A curiosity-based 3D exploration policy that pairs persistent online 3D reconstruction with episodic sequence modeling over RGB to outperform active-mapping baselines on HM3D and transfer zero-shot to Gibson and synthetic worlds.
GeoFlow adds a geometry-consistency reward based on rigid camera flow and object appearance preservation, integrated via reinforcement fine-tuning to improve geometric coherence in video generation.
Warp-as-History enables zero-shot camera trajectory following in frozen video models by supplying camera-warped pseudo-history, with single-video LoRA fine-tuning improving generalization to unseen videos.
SWIFT introduces a semantic injection cache with head-wise updates and an adaptive dynamic window plus segment anchors to achieve efficient multi-prompt long video generation at 22.6 FPS while preserving quality in causal diffusion models.
Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
DecMem proposes a decoupled memory system using sparse global and anchored local components to enable consistent minute-long controllable video generation in world models.
InSpatio-WorldFM is a frame-independent generative model that uses explicit 3D anchors and spatial memory to deliver real-time multi-view consistent spatial intelligence via a three-stage training pipeline from pretrained diffusion models.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
Latent State Design for World Models under Sufficiency Constraints
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
-
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
-
Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
A curiosity-based 3D exploration policy that pairs persistent online 3D reconstruction with episodic sequence modeling over RGB to outperform active-mapping baselines on HM3D and transfer zero-shot to Gibson and synthetic worlds.
-
GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
GeoFlow adds a geometry-consistency reward based on rigid camera flow and object appearance preservation, integrated via reinforcement fine-tuning to improve geometric coherence in video generation.
-
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Warp-as-History enables zero-shot camera trajectory following in frozen video models by supplying camera-warped pseudo-history, with single-video LoRA fine-tuning improving generalization to unseen videos.
-
SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
SWIFT introduces a semantic injection cache with head-wise updates and an adaptive dynamic window plus segment anchors to achieve efficient multi-prompt long video generation at 22.6 FPS while preserving quality in causal diffusion models.
-
Lyra 2.0: Explorable Generative 3D Worlds
Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
-
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
-
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
-
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
DecMem proposes a decoupled memory system using sparse global and anchored local components to enable consistent minute-long controllable video generation in world models.
-
InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model
InSpatio-WorldFM is a frame-independent generative model that uses explicit 3D anchors and spatial memory to deliver real-time multi-view consistent spatial intelligence via a three-stage training pipeline from pretrained diffusion models.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
- World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
- CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
- From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation