Research
TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation
arXiv:2610.02779v1 Announce Type: new Abstract: In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video gener
arXiv:2610.02779v1 Announce Type: new Abstract: In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video generation. Existing acceleration methods mainly target single-trajectory generation with bidirectional attention. AR video generation, by contrast, sequentially couples chunk-level denoising trajectories. Consequently, approximation errors accumulate and propagate through the generation process. TRAC addresses this challenge with three components, including robust cumulative scheduling (RCS), autoregressive trajectory-aware guidance scheduling (ATGS), and spectral structure correction (SSC). RCS selects cache reuse schedules by cumulative rollout error and cross-chunk/prompt variation. ATGS coordinates CFG refreshes along the global AR trajectory. SSC restores low-frequency structure of the first chunk to correct long-term structural loss. Experiments on SkyReels-V2 and FramePack-F1 show that, compared with existing methods, TRAC achieves both the highest inference efficiency and the best generation quality for AR video generation.
Related
- Motion-Aware Caching for Efficient Autoregressive Video Generation
- Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation
- PARE: Pruning and Adaptive Routing for Efficient Video Generation
- Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
- LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
Source: arXiv cs.CV | 2026-10-05