# Long-horizon Video Generation with Slot Memory Addressed By Region Tokens

arXiv: https://arxiv.org/abs/2610.19257 · HTML: https://mlsanity.com/paper/2610.19257/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 46 of its 53 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 30 of 46)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control](https://mlsanity.com/paper/2503.03751/) (2025)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [MineRL: A Large-Scale Dataset of Minecraft Demonstrations](https://mlsanity.com/paper/1907.13440/) (2019)
- [History-Guided Video Diffusion](https://mlsanity.com/paper/2502.06764/) (2025)
- [WorldMem: Long-term Consistent World Simulation with Memory](https://mlsanity.com/paper/2504.12369/) (2025)
- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025)
- [TTT3R: 3D Reconstruction as Test-Time Training](https://mlsanity.com/paper/2509.26645/) (2025)
- [Cameras as Relative Positional Encoding](https://mlsanity.com/paper/2507.10496/) (2025)
- [CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models](https://mlsanity.com/paper/2503.10592/) (2025)
- [GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers](https://mlsanity.com/paper/2310.10375/) (2023)
- [Gated Slot Attention for Efficient Linear-Time Sequence Modeling](https://mlsanity.com/paper/2409.07146/) (2024)

## Abstract (arXiv)

Memory for long-horizon video generation must satisfy two competing requirements: it must remain bounded so generation can continue indefinitely, while still recovering what was observed at a place when the camera returns, regardless of how long ago it was seen. Reconstruction-based memories provide spatial recall by caching and reprojecting explicit geometry, but require growing storage and depend on estimated 3D structure. Recurrent memories keep a constant-size state, but retention is governed by temporal recurrence, causing old observations to fade with time. We introduce SMART, a slot memory addressed by region tokens, which combines bounded storage with spatially addressed recall. SMART stores content in a constant-size slot recurrence whose writes are addressed by the observing camera and whose reads are queried by the rendering camera, without constructing an explicit 3D representation or maintaining a growing cache. Consequently, recall is conditioned on inter-view geometry rather than on recency. Each read additionally provides a confidence estimate that conditions a chunk-causal diffusion transformer, allowing it to selectively trust retrieved content while relying on its generative prior elsewhere. On long trajectories in Memory Maze and Minecraft, SMART maintains high-fidelity recall far beyond its training horizon while using constant memory and per-step cost.