Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model

• URL: http://arxiv.org/abs/2607.03509v1
• Date: Fri, 03 Jul 2026 17:34:14 GMT
• Title: Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
• Abstract summary: We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes.<n>Experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule.
• Score: 88.42070387375679
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models excel at global coherence and visual fidelity but suffer from slow inference, while autoregressive models offer efficient and streaming generation at the cost of long-range consistency and exposure bias. We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes. The core idea is a flexible chunking mechanism jointly defined over the temporal axis and denoising steps. This design allows the model to (1) perform flexible chunking according to different device budgets, (2) perform bidirectional inference across chunks for global structure planning, while generating frames autoregressively within each chunk for efficient and fine-grained synthesis, and (3) perform any-order, any-timestep autoregressive generation without the strict causal constraint. Extensive experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule, while offering faster inference.

Related papers

• FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching [68.01498128172214]
  We propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training.<n>Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via emphTweedie matching to enforce both textbfmanifold constraint and temporal consistency across overlap regions.<n>Our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any
  arXiv  Detail & Related papers  (2026-05-20T08:55:37Z)
• From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation [54.68405211129937]
  Exo-Seqto-Ego video generation aims to synthesize a first-person view from a synchronized third-person and corresponding camera poses.<n> synchronized exo-ego data inherently introduces substantial-temporal discontinuities, violating the smooth-motion assumptions of standard video generation benchmarks.<n>We propose Syn2Ex-Forcing, a sequential sequence model that interpolates between the source and target videos to form a single continuous signal.
  arXiv  Detail & Related papers  (2026-04-15T12:32:25Z)
• DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation [10.575655795360937]
  DCARL is a novel divide-and-conquer, autoregressive framework that combines the structural stability of the divide-and-conquer scheme with the high-fidelity generation of VDMs.<n>Our method achieves superior performance in both visual quality and camera adherence compared to state-of-the-art autoregressive and divide-and-conquer baselines.
  arXiv  Detail & Related papers  (2026-03-25T22:07:09Z)
• LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE [16.561410415129778]
  LongScape is a hybrid framework that combines intra-chunk diffusion denoising with inter-chunk autoregressive causal generation.<n>Our core innovation is an action-guided, variable-length chunking mechanism that partitions video based on the semantic context of robotic actions.
  arXiv  Detail & Related papers  (2025-09-26T02:47:05Z)
• Seedance 1.0: Exploring the Boundaries of Video Generation Models [71.26796999246068]
  Seedance 1.0 is a high-performance and inference-efficient video foundation generation model.<n>It integrates multi-source curation data augmented with precision and meaningful video captioning.<n>Seedance 1.0 can generate a 5-second video at 1080p resolution only with 41.4 seconds ( NVIDIA-L20)
  arXiv  Detail & Related papers  (2025-06-10T17:56:11Z)
• 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)
• AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion [19.98565541640125]
  We introduce Auto-Regressive Diffusion (AR-Diffusion), a novel model that combines the strengths of auto-regressive and diffusion models for flexible video generation.<n>Inspired by auto-regressive generation, we incorporate a non-decreasing constraint on the corruption timesteps of individual frames.<n>This setup, together with temporal causal attention, enables flexible generation of videos with varying lengths while preserving temporal coherence.
  arXiv  Detail & Related papers  (2025-03-10T15:05:59Z)
• Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution [65.91317390645163]
  Upscale-A-Video is a text-guided latent diffusion framework for video upscaling. It ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences. It also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation.
  arXiv  Detail & Related papers  (2023-12-11T18:54:52Z)

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.