Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation

• URL: http://arxiv.org/abs/2604.10103v1
• Date: Sat, 11 Apr 2026 08:54:07 GMT
• Title: Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
• Abstract summary: We propose Hybrid Forcing, which jointly optimize temporal information retention and computational efficiency.<n>Our model achieves real-time, unbounded 832x480 video generation at 29.5 FPS on a single NVIDIA H100 GPU without quantization or model compression.
• Score: 16.611062315689306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Streaming video generation (SVG) distills a pretrained bidirectional video diffusion model into an autoregressive model equipped with sliding window attention (SWA). However, SWA inevitably loses distant history during long video generation, and its computational overhead remains a critical challenge to real-time deployment. In this work, we propose Hybrid Forcing, which jointly optimizes temporal information retention and computational efficiency through a hybrid attention design. First, we introduce lightweight linear temporal attention to preserve long-range dependencies beyond the sliding window. In particular, we maintain a compact key-value state to incrementally absorb evicted tokens, retaining temporal context with negligible memory and computational overhead. Second, we incorporate block-sparse attention into the local sliding window to reduce redundant computation within short-range modeling, reallocating computational capacity toward more critical dependencies. Finally, we introduce a decoupled distillation strategy tailored to the hybrid attention design. A few-step initial distillation is performed under dense attention, then the distillation of our proposed linear temporal and block-sparse attention is activated for streaming modeling, ensuring stable optimization. Extensive experiments on both short- and long-form video generation benchmarks demonstrate that Hybrid Forcing consistently achieves state-of-the-art performance. Notably, our model achieves real-time, unbounded 832x480 video generation at 29.5 FPS on a single NVIDIA H100 GPU without quantization or model compression. The source code and trained models are available at https://github.com/leeruibin/hybrid-forcing.

Related papers

• LiveVVT: High-Fidelity Video Virtual Try-On in Real Time [36.4434648528291]
  Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional modeling.<n>We introduce LiveVVT, a rolling streaming diffusion framework that preserves bidirectional bounded modeling.<n>We show that Experiments on paired and unpaired long-sequence benchmarks demonstrate superior generation quality over similarly sized models.
  arXiv  Detail & Related papers  (2026-08-27T07:06:51Z)
• Towards Error-Free Long Video Generation [56.86952045212838]
  In this paper, we introduce an infinite-length video generation framework that produces high-quality, dynamic, and identity-consistent single-shot long videos.<n>We first finetune a diffusion model as a video extension model on large-scale short video data to autoregressively generate temporally coherent clips.<n>Our framework establishes a new benchmark for realistic and coherent minute-level video synthesis.
  arXiv  Detail & Related papers  (2026-06-21T07:39:37Z)
• Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion [61.57938553036056]
  ARL2 is a hybrid attention module that replaces quadratic cross-frame attention with a fixed-size recurrent state.<n>We decompose self-attention into two branches: an intra-frame softmax branch for spatial detail and local dependencies, and an inter-frame recurrent linear branch that maintains a fixed-size state for streaming context.<n>With 75% of layers replaced by hybrid linear attention, the model achieves up to 2.26 wall-clock speedup and 54% memory reduction, while maintaining comparable quality with improving temporal consistency.
  arXiv  Detail & Related papers  (2026-05-15T19:33:45Z)
• Streaming Autoregressive Video Generation via Diagonal Distillation [50.13573884115673]
  Autoregressive models offer a natural framework for sequential frame synthesis but require heavy computation to achieve high fidelity.<n>We propose Diagonal Distillation to exploit temporal information across both video chunks and denoising steps.<n>Our method generates a 5-second video in 2.61 seconds (up to 31 FPS), achieving a 277.3x speedup over the undistilled model.
  arXiv  Detail & Related papers  (2026-03-10T10:45:24Z)
• ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers [10.830662834634879]
  ReHyAt is a hybrid attention mechanism that combines the fidelity of softmax attention with the efficiency of linear attention.<n>Our experiments demonstrate that ReHyAt achieves state-of-the-art video quality while reducing attention cost from quadratic to linear.
  arXiv  Detail & Related papers  (2026-01-07T19:26:30Z)
• Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation [69.57572900337176]
  We introduce Reward Forcing, a novel framework for efficient streaming video generation.<n> EMA-Sink tokens capture both long-term context and recent dynamics, preventing initial frame copying.<n>Re-DMD biases the model's output distribution toward high-reward regions by prioritizing samples with greater dynamics rated by a vision-language model.
  arXiv  Detail & Related papers  (2025-12-04T11:12:13Z)
• Rolling Forcing: Autoregressive Long Video Diffusion in Real Time [86.40480237741609]
  Rolling Forcing is a novel video generation technique that enables streaming long videos with minimal error accumulation.<n>Rolling Forcing comes with three novel designs. First, instead of iteratively sampling individual frames, which accelerates error propagation, we design a joint denoising scheme.<n>Second, we introduce the attention sink mechanism into the long-horizon stream video generation task, which allows the model to keep key value states of initial frames as a global context anchor.<n>Third, we design an efficient training algorithm that enables few-step distillation over largely extended denoising windows.
  arXiv  Detail & Related papers  (2025-09-29T17:57:14Z)
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion [67.94300151774085]
  We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models.<n>It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs.
  arXiv  Detail & Related papers  (2025-06-09T17:59:55Z)
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models [48.35054927704544]
  Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies.<n>We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly.<n>Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
  arXiv  Detail & Related papers  (2024-12-10T18:59:50Z)

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.