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
Context as memory: Scene-consistent interactive long video generation with memory retrieval.arXiv preprint arXiv:2506.03141
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative 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.
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
Target-Bench shows the best off-the-shelf video world model scores only 0.341 on semantic target-approaching and directional consistency, with fine-tuning on a small robot dataset yielding measurable gains.
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.
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.
Light Interaction accelerates interactive video world models up to 2.59x via adaptive context management, denoising cache acceleration, and 3D block sparse attention without retraining.
A multi-agent video world model using simplex rotary agent encoding and sparse hub attention achieves better fidelity, controllability, and consistency than baselines while generalizing from 2 to 4 players.
Head Forcing assigns tailored KV cache strategies to local, anchor, and memory attention heads plus head-wise RoPE re-encoding to extend autoregressive video generation from seconds to minutes without training.
Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
A real-time video diffusion world model that uses dual action control, reframed position encodings, and context-aligned distillation to keep generated environments consistent over hundreds of frames.
A video world model framework that uses LLM-orchestrated 3D trajectories as control signals for generation to achieve persistent dynamic object memory and viewpoint freedom.
DecMem proposes a decoupled memory system using sparse global and anchored local components to enable consistent minute-long controllable video generation in world models.
HY-World 2.0 generates and reconstructs high-fidelity navigable 3D Gaussian Splatting worlds from text, images, or videos via upgraded panorama, planning, expansion, and composition modules, with released code claiming open-source SOTA performance.
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
-
MemLearner: Learning to Query Context memory for Video World Models
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.
-
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.
-
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
-
Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?
Target-Bench shows the best off-the-shelf video world model scores only 0.341 on semantic target-approaching and directional consistency, with fine-tuning on a small robot dataset yielding measurable gains.
-
PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
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.
-
Latent Spatial Memory for Video World Models
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.
-
Echo-Memory: A Controlled Study of Memory in Action World Models
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: Scaling Multi-Agent Video World Model from Single-view Video Data
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.
-
Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
Light Interaction accelerates interactive video world models up to 2.59x via adaptive context management, denoising cache acceleration, and 3D block sparse attention without retraining.
-
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
A multi-agent video world model using simplex rotary agent encoding and sparse hub attention achieves better fidelity, controllability, and consistency than baselines while generalizing from 2 to 4 players.
-
Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity
Head Forcing assigns tailored KV cache strategies to local, anchor, and memory attention heads plus head-wise RoPE re-encoding to extend autoregressive video generation from seconds to minutes without training.
-
Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
-
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
A real-time video diffusion world model that uses dual action control, reframed position encodings, and context-aligned distillation to keep generated environments consistent over hundreds of frames.
-
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory
A video world model framework that uses LLM-orchestrated 3D trajectories as control signals for generation to achieve persistent dynamic object memory and viewpoint freedom.
-
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.
-
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
HY-World 2.0 generates and reconstructs high-fidelity navigable 3D Gaussian Splatting worlds from text, images, or videos via upgraded panorama, planning, expansion, and composition modules, with released code claiming open-source SOTA performance.
-
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.
- FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion