SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

• URL: http://arxiv.org/abs/2603.11746v2
• Date: Wed, 18 Mar 2026 19:19:24 GMT
• Title: SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory
• Abstract summary: Autoregressive (AR) diffusion models offer a promising framework for sequential generation tasks such as video synthesis.<n>We propose Neighbor Forcing, a diffusion-step-consistent AR formulation that propagates temporally adjacent frames as latent neighbors under the same noise condition.<n>Our approach significantly improves training convergence, hour-scale generation quality, and inference efficiency compared to existing AR diffusion methods.
• Score: 25.57144961436966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive (AR) diffusion models offer a promising framework for sequential generation tasks such as video synthesis by combining diffusion modeling with causal inference. Although they support streaming generation, existing AR diffusion methods struggle to scale efficiently. In this paper, we identify two key challenges in hour-scale real-time human animation. First, most forcing strategies propagate sample-level representations with mismatched diffusion states, causing inconsistent learning signals and unstable convergence. Second, historical representations grow unbounded and lack structure, preventing effective reuse of cached states and severely limiting inference efficiency. To address these challenges, we propose Neighbor Forcing, a diffusion-step-consistent AR formulation that propagates temporally adjacent frames as latent neighbors under the same noise condition. This design provides a distribution-aligned and stable learning signal while preserving drifting throughout the AR chain. Building upon this, we introduce a structured ConvKV memory mechanism that compresses the keys and values in causal attention into a fixed-length representation, enabling constant-memory inference and truly infinite video generation without relying on short-term motion-frame memory. Extensive experiments demonstrate that our approach significantly improves training convergence, hour-scale generation quality, and inference efficiency compared to existing AR diffusion methods. Numerically, LiveAct enables hour-scale real-time human animation and supports 20 FPS real-time streaming inference on as few as two NVIDIA H100 or H200 GPUs. Quantitative results demonstrate that our method attains state-of-the-art performance in lip-sync accuracy, human animation quality, and emotional expressiveness, with the lowest inference cost.

Related papers

• DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation [24.843472730316503]
  Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications.<n>We present DSA, a confidence-guided adaptive framework for AR video diffusion.
  arXiv  Detail & Related papers  (2026-06-03T04:25:11Z)
• 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)
• Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length [57.458450695137664]
  We present Live Avatar, an algorithm-system co-designed framework for efficient, high-fidelity, and infinite-length avatar generation.<n>Live Avatar is first to achieve practical, real-time, high-fidelity avatar generation at this scale.
  arXiv  Detail & Related papers  (2025-12-04T11:11:24Z)
• Uniform Discrete Diffusion with Metric Path for Video Generation [103.86033350602908]
  Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-duration inconsistency.<n>We present Uniform generative modeling and present Uniform pAth (URSA), a powerful framework that bridges the gap with continuous approaches for scalable video generation.<n>URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods.
  arXiv  Detail & Related papers  (2025-10-28T17:59:57Z)
• Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation [50.04968365065964]
  Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference.<n>We introduce Lightning-fast Caching-based Parallel denoising prediction (LightningCP)<n>We also propose Decoupled Foreground Attention (DFA) to further accelerate attention computations.
  arXiv  Detail & Related papers  (2025-08-25T02:58:39Z)
• 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)
• Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion [0.881371061335494]
  We introduce Accelerated Rolling Diffusion, a novel framework for streaming gesture generation.<n>RDLA restructures the noise schedule into a stepwise ladder, allowing multiple frames to be denoised simultaneously.<n>This significantly improves sampling efficiency while maintaining motion consistency, achieving up to a 2x speedup.
  arXiv  Detail & Related papers  (2025-03-13T15:54:45Z)
• 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)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)

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.