SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation

• URL: http://arxiv.org/abs/2605.31033v1
• Date: Fri, 29 May 2026 09:04:26 GMT
• Title: SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
• Abstract summary: SlotMemory is an object-centric Key-Value memory mechanism for streaming video diffusion.<n>Our approach shifts the memory abstraction from "when" an event occurred to "what" is being represented by decomposing the transformer's key-value manifold.
• Score: 30.157534925157844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Streaming video generation models typically rely on temporal-centric memory, which organizes historical context as raw frames, chunk segments, or unclustered tokens. This organization frequently leads to identity drift and semantic inconsistency when entities exit the frame or during interactive prompt transitions. To address these limitations, we propose SlotMemory, an object-centric Key-Value memory mechanism for streaming video diffusion. Our approach shifts the memory abstraction from "when" an event occurred to "what" is being represented by decomposing the transformer's key-value manifold into discrete, reusable semantic slots. By utilizing these slots as routing addresses to index and store high-fidelity key-value tokens, we enable entity-level persistence and prompt-aware retrieval across long horizons. Evaluated on 60-second interactive narratives using the Wan2.1-T2V-1.3B backbone, SlotMemory achieves a state-of-the-art quality score of 81.61 and a 22.8 percent relative improvement in dynamic consistency over the strongest existing streaming baseline. Our results demonstrate that structured semantic representation, rather than raw temporal capacity, is the essential primitive for persistent long-form video synthesis. Our codes and checkpoints are available at https://tj12323.github.io/SlotMemory/.

Related papers

• ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding [50.17161313335395]
  ObjectStream is a training-free framework that treats latent objects as memory anchors for streaming video understanding.<n>It preserves three complementary forms of evidence: persistent object histories, transient object changes, and recent visual context.<n>Experiments on online streaming and offline long-video benchmarks demonstrate both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-07-30T14:47:00Z)
• FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion [59.207505503284715]
  FadeMem organizes historical KV blocks into a temporal hierarchy under a fixed cache budget.<n>New history is inserted as fine-grained entries, while older adjacent entries are progressively merged.<n>Experiments show improved subject consistency, background stability, and temporal coherence over existing bounded-cache strategies.
  arXiv  Detail & Related papers  (2026-06-09T10:22:18Z)
• Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory [79.01059178883817]
  IAMFlow is a training-free identity-aware memory framework that explicitly models and tracks persistent entity identities.<n>A VLM asynchronously verifies and refines attributes from rendered frames, enabling explicit entity tracking in place of implicit similarity-based matching.<n>NarraStream-Bench is a benchmark for narrative streaming video generation that features 324 multi-prompt scripts spanning six dimensions.
  arXiv  Detail & Related papers  (2026-05-18T17:54:34Z)
• SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation [31.105007908298003]
  Streaming long-video generation faces a central challenge in continuous semantic switching.<n>Current approaches rely on cache rebuilding at prompt boundaries or fixed memory budgets.<n>We present SWIFT, a training-free framework for multi-prompt long-video generation.
  arXiv  Detail & Related papers  (2026-05-10T09:37:56Z)
• Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding [55.7992006853979]
  SAVEMem is a framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.<n>We present SAVEMem, a training-free dual-stage framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.
  arXiv  Detail & Related papers  (2026-05-08T15:40:40Z)
• Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory [50.30283773196725]
  Existing approaches rely on key-value caching to accumulate frame-level details over time, but use a limited number of tokens per frame.<n>We propose scaling the token budget to enable more granular-temporal understanding and reasoning.
  arXiv  Detail & Related papers  (2026-02-20T18:59:50Z)
• VideoMemory: Toward Consistent Video Generation via Memory Integration [28.605816634949814]
  VideoMemory integrates narrative planning with visual generation through a Dynamic Memory Bank.<n>The Dynamic Memory Bank stores explicit visual and semantic descriptors for characters, props, and backgrounds.<n>This retrieval-update mechanism enables consistent portrayal of entities across distant shots and supports coherent long-form generation.
  arXiv  Detail & Related papers  (2026-01-07T07:10:32Z)
• Fast SAM2 with Text-Driven Token Pruning [52.8350457627401]
  Segment Anything Model 2 (SAM2), a vision computation model has significantly advanced in prompt-driven video object segmentation.<n>SAM2 pipelines propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object.<n>We introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation.
  arXiv  Detail & Related papers  (2025-12-24T18:59:05Z)
• Temporally Consistent Referring Video Object Segmentation with Hybrid Memory [98.80249255577304]
  We propose an end-to-end R-VOS paradigm that explicitly models temporal consistency alongside the referring segmentation. Features of frames with automatically generated high-quality reference masks are propagated to segment remaining frames. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin.
  arXiv  Detail & Related papers  (2024-03-28T13:32:49Z)
• Dual Temporal Memory Network for Efficient Video Object Segmentation [42.05305410986511]
  One of the fundamental challenges in Video Object (VOS) is how to make the most use of the temporal information to boost the performance. We present an end-to-end network which stores short- and long-term video sequence information preceding the current frame as the temporal memories. Our network consists of two temporal sub-networks including a short-term memory sub-network and a long-term memory sub-network.
  arXiv  Detail & Related papers  (2020-03-13T06:07:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.