# ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

arXiv: https://arxiv.org/abs/2603.25746 · HTML: https://mlsanity.com/paper/2603.25746/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 47 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [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)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [MAGI-1: Autoregressive Video Generation at Scale](https://mlsanity.com/paper/2505.13211/) (2025)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)
- [Scaling Autoregressive Video Models](https://mlsanity.com/paper/1906.02634/) (2019)
- [TransNet V2: An effective deep network architecture for fast shot transition detection](https://mlsanity.com/paper/2008.04838/) (2020)
- [UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining](https://mlsanity.com/paper/2304.09151/) (2023)
- [Generalization in Generation: A closer look at Exposure Bias](https://mlsanity.com/paper/1910.00292/) (2019)
- [Long Context Tuning for Video Generation](https://mlsanity.com/paper/2503.10589/) (2025)
- [Elucidating the Exposure Bias in Diffusion Models](https://mlsanity.com/paper/2308.15321/) (2023)
- [Loong: Generating Minute-level Long Videos with Autoregressive Language Models](https://mlsanity.com/paper/2410.02757/) (2024)
- [Mixture of Contexts for Long Video Generation](https://mlsanity.com/paper/2508.21058/) (2025)
- [Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout](https://mlsanity.com/paper/2511.20649/) (2025)
- [Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation](https://mlsanity.com/paper/2512.04678/) (2025)
- [Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression](https://mlsanity.com/paper/2512.05081/) (2025)

## Built on by (most cited first, 28 of 28)

- [LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation](https://mlsanity.com/paper/2605.18739/) (2026)
- [Self Gradient Forcing: Native Long Video Extrapolation](https://mlsanity.com/paper/2607.20368/) (2026)
- [CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives](https://mlsanity.com/paper/2605.12496/) (2026)
- [MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation](https://mlsanity.com/paper/2605.20183/) (2026)
- [Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation](https://mlsanity.com/paper/2605.16003/) (2026)
- [EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation](https://mlsanity.com/paper/2605.15199/) (2026)
- [CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation](https://mlsanity.com/paper/2606.09639/) (2026)
- [OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data](https://mlsanity.com/paper/2606.13432/) (2026)
- [UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating](https://mlsanity.com/paper/2606.21661/) (2026)
- [GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling](https://mlsanity.com/paper/2606.20799/) (2026)
- [Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds](https://mlsanity.com/paper/2608.23383/) (2026)
- [RECAP-Forcing: Retaining Content Appearances for Long Video Generation](https://mlsanity.com/paper/2608.26671/) (2026)
- [Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation](https://mlsanity.com/paper/2605.14382/) (2026)
- [TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting](https://mlsanity.com/paper/2607.28261/) (2026)
- [LogiShot: Logically Coherent Cross-Shot Video Generation](https://mlsanity.com/paper/2608.08820/) (2026)
- [CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation](https://mlsanity.com/paper/2606.13768/) (2026)
- [Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation](https://mlsanity.com/paper/2607.06481/) (2026)
- [ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing](https://mlsanity.com/paper/2608.04956/) (2026)
- [PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation](https://mlsanity.com/paper/2608.16717/) (2026)
- [Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation](https://mlsanity.com/paper/2609.06373/) (2026)
- [ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation](https://mlsanity.com/paper/2609.28923/) (2026)
- [Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation](https://mlsanity.com/paper/2609.37407/) (2026)
- [FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation](https://mlsanity.com/paper/2609.38839/) (2026)
- [In-Distribution Forcing for Long Video Generation at Test Time](https://mlsanity.com/paper/2610.03120/) (2026)
- [Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation](https://mlsanity.com/paper/2610.03510/) (2026)
- [Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation](https://mlsanity.com/paper/2610.14553/) (2026)
- [Structured Stateful Relational Scripts with a High-Quality Dataset for Multi-Shot Audio-Visual Video Generation](https://mlsanity.com/paper/2610.15512/) (2026)
- [CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation](https://mlsanity.com/paper/2610.17926/) (2026)

## Abstract (arXiv)

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame generation. By reformulating the task as next-shot generation conditioned on historical context, ShotStream allows users to dynamically instruct ongoing narratives via streaming prompts. We achieve this by first fine-tuning a text-to-video model into a bidirectional next-shot generator, which is then distilled into a causal student via Distribution Matching Distillation. To overcome the challenges of inter-shot consistency and error accumulation inherent in autoregressive generation, we introduce two key innovations. First, a dual-cache memory mechanism preserves visual coherence: a global context cache retains conditional frames for inter-shot consistency, while a local context cache holds generated frames within the current shot for intra-shot consistency. And a RoPE discontinuity indicator is employed to explicitly distinguish the two caches to eliminate ambiguity. Second, to mitigate error accumulation, we propose a two-stage distillation strategy. This begins with intra-shot self-forcing conditioned on ground-truth historical shots and progressively extends to inter-shot self-forcing using self-generated histories, effectively bridging the train-test gap. Extensive experiments demonstrate that ShotStream generates coherent multi-shot videos with sub-second latency, achieving 16 FPS on a single GPU. It matches or exceeds the quality of slower bidirectional models, paving the way for real-time interactive storytelling. Training and inference code, as well as the models, are available on our