MemLearner introduces a learning-based adaptive context query method using query tokens in video world models to improve long-term scene consistency over rule-based retrieval.
hub Canonical reference
Video world models with long-term spatial memory
Canonical reference. 89% of citing Pith papers cite this work as background.
29
Pith papers citing it
Background
89% of classified citations
hub tools
citation-role summary
background 8
baseline 1
citation-polarity summary
representative citing papers
What-If World is a new paired-prompt benchmark showing that nine state-of-the-art video generation models achieve at most 52% on causal intervention tests and cluster near 28% for open-source systems.
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
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 generative video model conditioned on pixel-aligned 3D renderings produces consistent dynamic 3D Gaussian splats from monocular video and sets new SOTA in 4D reconstruction.
Pano2World generates an explorable 3D Gaussian scene directly from a single indoor panorama via coarse proxy rendering, view-aware joint denoising, and a latent feature adapter.
PermaVid disentangles spatial context into semantic appearance and geometric structure via multi-modal memory banks and edit-aware updates to maintain long-term consistency in video generation after edits.
Envision4D presents a feed-forward 4D Gaussian Splatting framework with future pose prediction, temporal attention, and conditioned motion lifting for pose-free extrapolation in autonomous driving scenes.
Mirage stores and queries 3D scene information in diffusion latent space via depth-guided lifting and warping, yielding 10.57× faster generation and 55× smaller memory than explicit RGB point-cloud baselines while reaching SOTA on WorldScore.
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
MetaWorld scales multi-agent video world models from single-view videos using monocular decomposition into ego-motion and trajectories, subject-aware generation, and cross-attention alignment for consistency.
GIM-World adds a camera-queryable geometry distillation head and pruning rule to implicit memory in video world models, claiming better long-horizon geometric consistency on the MIND benchmark than explicit and implicit baselines.
Robust Dreamer uses Latent Gaussian Memory anchored to diffusion latents and Deviation Learning with a Dynamic Deviation Archive to reduce drift in long-horizon action-controlled image-to-video generation, reporting SOTA results on ScanNet, DL3DV, and OmniWorldGame.
E³C is a video diffusion model that disentangles persistent 3D scene structure via point-cloud memory from human dynamics via ego-exo pose controls for improved egocentric video generation on the Nymeria dataset.
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.
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
WorldOlympiad is a new benchmark decomposing world-model evaluation into physical, geometry, and interaction tracks using segmentation, MLLM judges, Gaussian splatting, and action prompts on diverse scenarios.
DecMem proposes a decoupled memory system using sparse global and anchored local components to enable consistent minute-long controllable video generation in world models.
citing papers explorer
-
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.