Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory

• URL: http://arxiv.org/abs/2605.18733v1
• Date: Mon, 18 May 2026 17:54:34 GMT
• Title: Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
• Abstract summary: IAMFlow is a training-free identity-aware memory framework that explicitly models and tracks persistent entity identities.<n>A VLM asynchronously verifies and refines attributes from rendered frames, enabling explicit entity tracking in place of implicit similarity-based matching.<n>NarraStream-Bench is a benchmark for narrative streaming video generation that features 324 multi-prompt scripts spanning six dimensions.
• Score: 79.01059178883817
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory degradation. Most existing solutions either compress historical frames using predefined strategies or retrieve keyframes based on coarse implicit attention signals, both of which fail to handle evolving prompts with shifting entity references, leading to identity drift, character duplication, and attribute loss. To address this, we propose IAMFlow, a training-free identity-aware memory framework that explicitly models and tracks persistent entity identities, enabling consistent generation across prompt transitions. Specifically, an LLM extracts entities with visual attributes from each prompt and assigns unique global IDs for identity-aware memory, while a VLM asynchronously verifies and refines attributes from rendered frames, enabling explicit entity tracking in place of implicit similarity-based matching. To keep the proposed framework computationally practical, we design a systematic inference acceleration pipeline, including asynchronous visual verification, adaptive prompt transition, and model quantization, which achieves faster generation than existing baselines. Furthermore, we introduce NarraStream-Bench, a benchmark for narrative streaming video generation that features 324 multi-prompt scripts spanning six dimensions and a three-dimensional evaluation protocol that integrates both traditional metrics and multimodal large language model-based assessments. Extensive experiments show that IAMFlow, despite being training-free, achieves the best overall performance on NarraStream-Bench, outperforming the strongest baseline by 2.56 points, while achieving a 1.39$\times$ speedup over the most efficient baseline in the 60-second multi-prompt setting.

Related papers

• Closed-Loop Triplet Synergistic Generation for Long-Form Video [61.88597038104749]
  CoSyTriGen is an agentic framework that formulates multi-shot long video generation as a closed-loop visual-text-memory synergy process.<n>A vision-language-model-based analyzer reasons over this triplet and produces updates to both prompts and memory along two pathways.<n> Experiments on our StoryBench benchmark demonstrate substantial improvements in cross-shot consistency, prompt adherence, and cinematic continuity over representative methods.
  arXiv  Detail & Related papers  (2026-06-15T03:56:43Z)
• SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation [30.157534925157844]
  SlotMemory is an object-centric Key-Value memory mechanism for streaming video diffusion.<n>Our approach shifts the memory abstraction from "when" an event occurred to "what" is being represented by decomposing the transformer's key-value manifold.
  arXiv  Detail & Related papers  (2026-05-29T09:04:26Z)
• Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding [0.0]
  Multi-Stream Scene Script (MTSS) is a novel paradigm that replaces monolithic text with factorized and explicitly grounded scene descriptions.<n>Extensive experiments demonstrate that MTSS consistently enhances video understanding across various models.<n>Even without architectural adaptation, replacing monolithic prompts with MTSS in multi-shot video generation yields substantial improvements.
  arXiv  Detail & Related papers  (2026-04-13T09:50:36Z)
• PEARL: Personalized Streaming Video Understanding Model [50.273809779498464]
  multimodal personalization methods are largely limited to static images or offline videos.<n>PEARL-Bench is the first comprehensive benchmark designed specifically to evaluate this challenging setting.<n>PEARL achieves state-of-the-art performance across 8 offline and online models.
  arXiv  Detail & Related papers  (2026-03-20T18:47:54Z)
• VideoMemory: Toward Consistent Video Generation via Memory Integration [28.605816634949814]
  VideoMemory integrates narrative planning with visual generation through a Dynamic Memory Bank.<n>The Dynamic Memory Bank stores explicit visual and semantic descriptors for characters, props, and backgrounds.<n>This retrieval-update mechanism enables consistent portrayal of entities across distant shots and supports coherent long-form generation.
  arXiv  Detail & Related papers  (2026-01-07T07:10:32Z)
• Fast SAM2 with Text-Driven Token Pruning [52.8350457627401]
  Segment Anything Model 2 (SAM2), a vision computation model has significantly advanced in prompt-driven video object segmentation.<n>SAM2 pipelines propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object.<n>We introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation.
  arXiv  Detail & Related papers  (2025-12-24T18:59:05Z)
• Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations [131.33758144860988]
  Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity.<n>Current end-to-end frameworks suffer a critical spatial-temporal trade-off.<n>We propose a simple yet effective spatial-temporal decoupled framework that decomposes representations into spatial features for layouts and temporal features for motion dynamics.
  arXiv  Detail & Related papers  (2025-07-07T06:54:44Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation [47.7036344302777]
  Current Object Video reference methods follow the pipeline of extraction-then-matching.<n>We propose a unified VOS framework, coined as JointFormer, for jointly feature modeling, correspondence, and a compressed memory.
  arXiv  Detail & Related papers  (2023-08-25T17:30:08Z)

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.