Pith. sign in

REVIEW 26 cited by

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.03141 v2 pith:AQ4KYZHH submitted 2025-06-03 cs.CV

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

classification cs.CV
keywords contextmemorygenerationvideocontext-as-memoryframeshistoricalinteractive
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we propose Context-as-Memory, which utilizes historical context as memory for video generation. It includes two simple yet effective designs: (1) storing context in frame format without additional post-processing; (2) conditioning by concatenating context and frames to be predicted along the frame dimension at the input, requiring no external control modules. Furthermore, considering the enormous computational overhead of incorporating all historical context, we propose the Memory Retrieval module to select truly relevant context frames by determining FOV (Field of View) overlap between camera poses, which significantly reduces the number of candidate frames without substantial information loss. Experiments demonstrate that Context-as-Memory achieves superior memory capabilities in interactive long video generation compared to SOTAs, even generalizing effectively to open-domain scenarios not seen during training. The link of our project page is https://context-as-memory.github.io/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 26 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MemLearner: Learning to Query Context memory for Video World Models

    cs.CV 2026-06 unverdicted novelty 7.0

    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.

  2. FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion

    cs.CV 2026-06 unverdicted novelty 7.0

    FadeMem introduces distance-aware KV memory consolidation for autoregressive video diffusion that builds a temporal hierarchy with power-law merging to preserve short-term dynamics and long-range coherence under fixed...

  3. MultiWorld: Scalable Multi-Agent Multi-View Video World Models

    cs.CV 2026-04 unverdicted novelty 7.0

    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.

  4. SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

    cs.AI 2026-04 unverdicted novelty 7.0

    SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.

  5. Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?

    cs.CV 2025-11 unverdicted novelty 7.0

    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.

  6. Wonder: Video World Model Done Better

    cs.CV 2026-07 conditional novelty 6.0

    Wonder generates minute-scale, real-time camera-controllable video worlds from a single image or video at 16 FPS, using a rendered coordinate-field control signal, sparse full-fidelity memory, and stage-specialized di...

  7. StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation

    cs.CV 2026-07 conditional novelty 6.0

    A streaming image-to-video model that assigns block-specific sink/local memory and learned RoPE distance scaling preserves long human-object interactions under bounded latency.

  8. SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation

    cs.CV 2026-07 conditional novelty 6.0

    SlotMem keeps a compact, updateable memory slot for each recurring character and injects it only into that character's tokens, reporting improved long-range identity consistency in narrative video generation.

  9. PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

    cs.CV 2026-06 unverdicted novelty 6.0

    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.

  10. Latent Spatial Memory for Video World Models

    cs.CV 2026-06 unverdicted novelty 6.0

    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 rea...

  11. Echo-Memory: A Controlled Study of Memory in Action World Models

    cs.CV 2026-06 unverdicted novelty 6.0

    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 meas...

  12. MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data

    cs.CV 2026-06 unverdicted novelty 6.0

    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.

  13. Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models

    cs.CV 2026-05 unverdicted novelty 6.0

    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.

  14. Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

    cs.CV 2026-05 unverdicted novelty 6.0

    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.

  15. Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity

    cs.CV 2026-05 unverdicted novelty 6.0

    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.

  16. Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

    cs.CV 2026-04 unverdicted novelty 6.0

    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.

  17. UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models

    cs.CV 2026-02 conditional novelty 6.0

    A video-generation world model that warps positional encodings of memory frames to target viewpoints achieves state-of-the-art long-term consistency and camera control.

  18. CustomX: Unified Character, Action, and Scene Customization in Video World Models

    cs.CV 2025-12 conditional novelty 6.0

    AniX generates controllable videos of a user-supplied character performing typed actions inside a user-supplied 3D scene by fine-tuning a pre-trained video generator on small locomotion datasets.

  19. WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

    cs.CV 2025-12 unverdicted novelty 6.0

    WorldPlay uses dual action representation, reconstituted context memory, and context forcing distillation to produce consistent 720p streaming video at 24 FPS for interactive world modeling.

  20. WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

    cs.CV 2025-12 conditional novelty 6.0

    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.

  21. WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

    cs.CV 2026-07 unverdicted novelty 5.0

    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.

  22. DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

    cs.CV 2026-05 unverdicted novelty 5.0

    DecMem proposes a decoupled memory system using sparse global and anchored local components to enable consistent minute-long controllable video generation in world models.

  23. Vision-Language Memory for Spatial Reasoning

    cs.CV 2025-11 conditional novelty 5.0

    A video-based vision-language model with 3D-aligned visual features and bounded dual memory achieves state-of-the-art scores on four spatial reasoning benchmarks.

  24. Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

    cs.CV 2025-11 conditional novelty 5.0

    Augmenting a diffusion video transformer with an RNN memory block and frame-wise overlapping attention improves long-horizon consistency, with simple LSTM matching newer Mamba2 and TTT memory blocks.

  25. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

    cs.CV 2026-04 unverdicted novelty 4.0

    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 claimin...

  26. Evolution of Video Generative Foundations

    cs.CV 2026-04 unverdicted novelty 2.0

    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.