FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis

• URL: http://arxiv.org/abs/2603.07192v1
• Date: Sat, 07 Mar 2026 13:05:33 GMT
• Title: FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis
• Abstract summary: FastSTAR is a training-free acceleration framework designed for high-quality video generation.<n> Experimental results on InfinityStar demonstrate that FastSTAR achieves up to a 2.01x speedup with a PSNR of 28.29 and less than 1% performance degradation.
• Score: 1.8320252176005443
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual Autoregressive modeling (VAR) has emerged as a highly efficient alternative to diffusion-based frameworks, achieving comparable synthesis quality. However, as this paradigm extends to Spacetime Autoregressive modeling (STAR) for video generation, scaling resolution and frame counts leads to a "token explosion" that creates a massive computational bottleneck in the final refinement stages. To address this, we propose FastSTAR, a training-free acceleration framework designed for high-quality video generation. Our core method, Spatiotemporal Token Pruning, identifies essential tokens by integrating two specialized terms: (1) Spatial similarity, which evaluates structural convergence across hierarchical scales to skip computations in regions where further refinement becomes redundant, and (2) Temporal similarity, which identifies active motion trajectories by assessing feature-level variations relative to the preceding clip. Combined with a Partial Update mechanism, FastSTAR ensures that only non-converged regions are refined, maintaining fluid motion while bypassing redundant computations. Experimental results on InfinityStar demonstrate that FastSTAR achieves up to a 2.01x speedup with a PSNR of 28.29 and less than 1% performance degradation, proving a superior efficiency-quality trade-off for STAR-based video synthesis.

Related papers

• COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models [15.39037309359101]
  Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile.<n>We propose COMET, a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation.<n>For optimization, COMET combines temporal prior distillation with a forward-reverse TC-GRPO stage that turns temporal order into a direct learning signal.
  arXiv  Detail & Related papers  (2026-08-21T12:28:36Z)
• WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA [27.102605117827398]
  Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving.<n>They are constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.<n>We introduce WAM-Diff2, a multi-task discrete diffusion VLA framework powered by a three-stage hierarchical strategy.
  arXiv  Detail & Related papers  (2026-08-02T06:45:16Z)
• FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity [23.184639887235218]
  Video Diffusion Transformers (DiTs) can be substantially reduced through model, but per-step inference latency remains a critical bottleneck.<n>We propose Frame Inter Sparsity DiT (FIS-DiT), a training-free and operator-agnostic framework that shifts the optimization focus from the temporal trajectory to the latent frame position.<n>FIS-DiT consistently achieves 2.11--2.41$times$ speedup with negligible degradation across VBench-Q and CLIP metrics.
  arXiv  Detail & Related papers  (2026-05-12T09:49:36Z)
• Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness [7.596181361033662]
  Diffusion Transformers (DiTs) require intensive full-attention computation.<n>We present Jano, a training-free framework that leverages this insight for efficient region-aware generation.<n>Jano achieves substantial acceleration (average 2.0 times speedup, up to 2.4 times) while preserving generation quality.
  arXiv  Detail & Related papers  (2026-02-28T07:35:01Z)
• FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization [61.10456021136654]
  We introduce FASTer, a unified framework for efficient and general robot learning.<n>FASTerVQ encodes action chunks as single-channel images, capturing global-temporal dependencies while maintaining a high compression ratio.<n>FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance.
  arXiv  Detail & Related papers  (2025-12-04T16:21:38Z)
• 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)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• POSE: Phased One-Step Adversarial Equilibrium for Video Diffusion Models [18.761042377485367]
  POSE (Phased One-Step Equilibrium) is a distillation framework that reduces the sampling steps of large-scale video diffusion models.<n>We show that POSE outperforms other acceleration methods on VBench-I2V by average 7.15% in semantic alignment, temporal conference and frame quality.
  arXiv  Detail & Related papers  (2025-08-28T17:20:01Z)
• Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers [29.130090574300635]
  Video diffusion transformers (vDiTs) have made tremendous progress in text-to-video generation, but their compute demands pose a major challenge for practical deployment.<n>We introduce Astraea, a framework that searches for near-optimal configurations for vDiT-based video generation under a performance target.
  arXiv  Detail & Related papers  (2025-06-05T14:41:38Z)
• FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge [60.000984252907195]
  Auto-regressive (AR) models have recently shown promise in visual generation tasks due to their superior sampling efficiency.<n>Video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase.<n>We propose the textbfFastCar framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy.
  arXiv  Detail & Related papers  (2025-05-17T05:00:39Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)
• Dynamic Frame Interpolation in Wavelet Domain [57.25341639095404]
  Video frame is an important low-level computation vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts.
  arXiv  Detail & Related papers  (2023-09-07T06:41:15Z)

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.