CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

• URL: http://arxiv.org/abs/2605.12496v1
• Date: Tue, 12 May 2026 17:59:51 GMT
• Title: CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
• Abstract summary: CausalCine is an interactive autoregressive framework that transforms multi-shot video generation into an online directing process.<n>CausalCine generates causally across shot changes, accepts dynamic prompts on the fly, and reuses context without regenerating previous shots.
• Score: 117.85963914353904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot boundaries. Existing autoregressive models often struggle in this setting. Trained primarily for short-horizon continuation, they treat long sequences as extended single shots, inevitably suffering from motion stagnation and semantic drift during long rollouts. To bridge this gap, we introduce CausalCine, an interactive autoregressive framework that transforms multi-shot video generation into an online directing process. CausalCine generates causally across shot changes, accepts dynamic prompts on the fly, and reuses context without regenerating previous shots. To achieve this, we first train a causal base model on native multi-shot sequences to learn complex shot transitions prior to acceleration. We then propose Content-Aware Memory Routing (CAMR), which dynamically retrieves historical KV entries according to attention-based relevance scores rather than temporal proximity, preserving cross-shot coherence under bounded active memory. Finally, we distill the causal base model into a few-step generator for real-time interactive generation. Extensive experiments demonstrate that CausalCine significantly outperforms autoregressive baselines and approaches the capability of bidirectional models while unlocking the streaming interactivity of causal generation. Demo available at https://yihao-meng.github.io/CausalCine/

Related papers

• CausalDrive: Real-time Causal World Models for Autonomous Driving [60.66609721457312]
  We present CausalDrive, a controllable, real-time foundation driving world.<n>CaulDrive operates solely on the initial front-view frame, the ego-vehicle's trajectory, and a macroscopic text prompt.<n>We demonstrate its versatility across three downstream applications: (1) generative closed-loop evaluation with significantly mitigated collision artifacts, (2) large-scale Reinforcement Learning (RL) post-training driven by a Video2Reward module, and (3) real-time human-in-the-loop simulation.
  arXiv  Detail & Related papers  (2026-06-13T15:04:44Z)
• Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration [61.98029663481308]
  Soap2Soap is a multi-agent framework that enforces long-term visual consistency through a DualBridge mechanism.<n>A closed-loop verification agent audits identity, stability, and alignment to trigger selective regeneration.
  arXiv  Detail & Related papers  (2026-05-17T12:38:21Z)
• RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control [30.825728569025525]
  Real-time camera-controlled video-to-video (V2V) generation has immense potential for interactive filmmaking and live broadcasting.<n>Existing implicit synthesis methods rely on non-causal, full-sequence processing and rigid prefix-style temporal concatenation.<n>We introduce textttRealCam, a novel autoregressive framework for interactive, real-time camera-controlled V2V generation.
  arXiv  Detail & Related papers  (2026-05-07T11:36:29Z)
• ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling [31.758254551463406]
  ShotStream is a novel causal multi-shot architecture that enables interactive storytelling.<n>It generates coherent multi-shot videos with sub-second latency, achieving 16 FPS on a single GPU.
  arXiv  Detail & Related papers  (2026-03-26T17:59:59Z)
• Inference-based GAN Video Generation [47.53991869205973]
  We propose a new type of video generator by enabling adversarial-based unconditional video generators with a variational encoder.<n>Existing models struggle with the temporal scaling of the generated videos.<n>We employ a novel, memory-efficient approach to generate long videos composed of hundreds or thousands of frames.
  arXiv  Detail & Related papers  (2025-12-25T20:14:38Z)
• VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention [70.61101071902596]
  Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines.<n>We introduce VideoGen-of-Thought (VGoT), a step-by-step framework that automates multi-shot video synthesis from a single sentence.<n>VGoT generates multi-shot videos that outperform state-of-the-art baselines by 20.4% in within-shot face consistency and 17.4% in style consistency.
  arXiv  Detail & Related papers  (2025-03-19T11:59:14Z)
• Long Context Tuning for Video Generation [63.060794860098795]
  Long Context Tuning (LCT) is a training paradigm that expands the context window of pre-trained single-shot video diffusion models.<n>Our method expands full attention mechanisms from individual shots to encompass all shots within a scene.<n>Experiments demonstrate coherent multi-shot scenes and exhibit emerging capabilities, including compositional generation and interactive shot extension.
  arXiv  Detail & Related papers  (2025-03-13T17:40:07Z)
• VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention [76.3175166538482]
  VideoGen-of-Thought (VGoT) is a step-by-step framework that automates multi-shot video synthesis from a single sentence.<n>VGoT addresses three core challenges: Narrative fragmentation, visual inconsistency, and transition artifacts.<n>Combined in a training-free pipeline, VGoT surpasses strong baselines by 20.4% in within-shot face consistency and 17.4% in style consistency.
  arXiv  Detail & Related papers  (2024-12-03T08:33:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.