# SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling

arXiv: https://arxiv.org/abs/2609.34502 · HTML: https://mlsanity.com/paper/2609.34502/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 73 of its 80 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 30 of 73)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding](https://mlsanity.com/paper/2312.04461/) (2023)
- [Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://mlsanity.com/paper/2304.01186/) (2023)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2406.01900/) (2024)
- [TransNet V2: An effective deep network architecture for fast shot transition detection](https://mlsanity.com/paper/2008.04838/) (2020)
- [ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://mlsanity.com/paper/2402.04324/) (2024)
- [ID-Animator: Zero-Shot Identity-Preserving Human Video Generation](https://mlsanity.com/paper/2404.15275/) (2024)
- [Long Context Tuning for Video Generation](https://mlsanity.com/paper/2503.10589/) (2025)
- [DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting](https://mlsanity.com/paper/2412.10859/) (2024)
- [DiT4Edit: Diffusion Transformer for Image Editing](https://mlsanity.com/paper/2411.03286/) (2024)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)

## Built on by (most cited first, 1 of 1)

- [Memory Forcing: Attendable Mid-Horizon History for Streaming Video Generation](https://mlsanity.com/paper/2610.11756/) (2026)

## Abstract (arXiv)

We present SubjectAnchor, a Subject-Aware Memory-to-Video paradigm for multi-shot storytelling in which the current shot is generated by conditioning on explicit visual memories extracted from previous shots. The objective is to preserve subject identity and scene consistency across cuts while retaining the controllability of shot-wise prompting. Built on Wan2.2-I2V-A14B, SubjectAnchor contains three key components: subject-related memory construction, subject-aware temporal rotary position encoding, and memory-aware attention partition. For each target shot, the method constructs a compact memory bank by tracing each required subject to its historical appearance and retrieving the most relevant precomputed keyframes. These memory frames are encoded into the model input as explicit visual conditions, while different subjects are assigned to separated negative temporal slots to reduce identity interference. In addition, memory-aware attention partition regulates the interaction between memory tokens and generated content within a shared backbone. This formulation preserves the appearance anchoring of explicit visual memory while remaining compatible with script-driven shot-by-shot generation. Experiments show that SubjectAnchor improves cross-shot identity consistency over representative memory-based and holistic baselines while maintaining competitive visual quality.