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

arXiv: https://arxiv.org/abs/2605.31033 · HTML: https://mlsanity.com/paper/2605.31033/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 27 of 27)

- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations](https://mlsanity.com/paper/1907.13052/) (2019)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval](https://mlsanity.com/paper/2506.03141/) (2025)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [FIFO-Diffusion: Generating Infinite Videos from Text without Training](https://mlsanity.com/paper/2405.11473/) (2024)
- [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025)
- [VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2411.13503/) (2024)
- [MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives](https://mlsanity.com/paper/2512.14699/) (2025)
- [Temporally Consistent Object-Centric Learning by Contrasting Slots](https://mlsanity.com/paper/2412.14295/) (2024)
- [DORSal: Diffusion for Object-centric Representations of Scenes et al](https://mlsanity.com/paper/2306.08068/) (2023)
- [Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion](https://mlsanity.com/paper/2603.13405/) (2026)
- [InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO](https://mlsanity.com/paper/2505.17574/) (2025)
- [Explicitly Disentangled Representations in Object-Centric Learning](https://mlsanity.com/paper/2401.10148/) (2024)
- [DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization](https://mlsanity.com/paper/2305.00393/) (2023)

## Built on by (most cited first, 6 of 6)

- [DIM-WAM: World-Action Modeling with Diverse Historical Event Memory](https://mlsanity.com/paper/2606.27677/) (2026)
- [R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models](https://mlsanity.com/paper/2608.27328/) (2026)
- [LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation](https://mlsanity.com/paper/2608.28460/) (2026)
- [Compress to Remember: Learning Compact Memory via On-Policy Distillation for Long Video Generation](https://mlsanity.com/paper/2609.36364/) (2026)
- [DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency](https://mlsanity.com/paper/2609.39096/) (2026)
- [EVEWorld: Physical Evolution Supervision for Embodied World Models](https://mlsanity.com/paper/2610.03374/) (2026)

## Abstract (arXiv)

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/.