# EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation

arXiv: https://arxiv.org/abs/2605.23610 · HTML: https://mlsanity.com/paper/2605.23610/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 22 May 2026.

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

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [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)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance](https://mlsanity.com/paper/2406.07209/) (2024)
- [Phantom: Subject-consistent video generation via cross-modal alignment](https://mlsanity.com/paper/2502.11079/) (2025)
- [Long Context Tuning for Video Generation](https://mlsanity.com/paper/2503.10589/) (2025)
- [MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence](https://mlsanity.com/paper/2407.16655/) (2024)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model](https://mlsanity.com/paper/2504.08685/) (2025)
- [Vlogger: Make Your Dream A Vlog](https://mlsanity.com/paper/2401.09414/) (2024)
- [Multi-subject Open-set Personalization in Video Generation](https://mlsanity.com/paper/2501.06187/) (2025)
- [VideoStudio: Generating Consistent-Content and Multi-Scene Videos](https://mlsanity.com/paper/2401.01256/) (2024)
- [Magic-Me: Identity-Specific Video Customized Diffusion](https://mlsanity.com/paper/2402.09368/) (2024)
- [Captain Cinema: Towards Short Movie Generation](https://mlsanity.com/paper/2507.18634/) (2025)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models](https://mlsanity.com/paper/2505.07652/) (2025)
- [MultiShotMaster: A Controllable Multi-Shot Video Generation Framework](https://mlsanity.com/paper/2512.03041/) (2025)
- [OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory](https://mlsanity.com/paper/2512.07802/) (2025)
- [Pack and Force Your Memory: Long-form and Consistent Video Generation](https://mlsanity.com/paper/2510.01784/) (2025)
- [LoViC: Efficient Long Video Generation with Context Compression](https://mlsanity.com/paper/2507.12952/) (2025)
- [Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset](https://mlsanity.com/paper/2506.18851/) (2025)

## Built on by (most cited first, 3 of 3)

- [FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling](https://mlsanity.com/paper/2607.19038/) (2026)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)
- [REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation](https://mlsanity.com/paper/2610.16632/) (2026)

## Abstract (arXiv)

Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory. However, full-frame storage entangles persistent entity information with transient scene context, leading to irrelevant information leakage and high computational cost. We propose an entity-centric memory in the form of an entity-indexed bank of latent patches. We introduce sparse token conditioning compatible with pretrained models, restricting self-attention to entity-relevant tokens and reducing computational cost. To support this, we introduce a structured multi-shot script format. We additionally propose a budgeted memory update strategy to maintain a compact, evolving memory. Finally, we equip the entity representation with a noise-injection mechanism that enables fine-grained appearance control, preventing leakage of irrelevant information. Our method improves prompt adherence and efficiency while preserving subject consistency.