FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers

• URL: http://arxiv.org/abs/2511.20390v1
• Date: Tue, 25 Nov 2025 15:12:10 GMT
• Title: FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers
• Authors: Xinwan Wen, Bowen Li, Jiajun Luo, Ye Li, Zhi Wang,
• Abstract summary: FREE is a novel framework that employs a lightweight drafter to perform feature-level autoregression with parallel verification.<n>Experiments on ImageNet-$5122$ show that FREE achieves up to $1.86 times$ acceleration, and FREE (relax) further reaches $2.25 times$ speedup.
• Score: 12.17745708847535
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in U-Net-based diffusion models via a drafter-verifier scheme, but their acceleration is limited on DiTs due to insufficient draft accuracy during verification. To address this limitation, we analyze the DiTs' feature dynamics and find the features of the final transformer layer (top-block) exhibit strong temporal consistency and rich semantic abstraction. Based on this insight, we propose FREE, a novel framework that employs a lightweight drafter to perform feature-level autoregression with parallel verification, guaranteeing lossless acceleration with theoretical and empirical support. Meanwhile, prediction variance (uncertainty) of DiTs naturally increases in later denoising steps, reducing acceptance rates under speculative sampling. To mitigate this effect, we further introduce an uncertainty-guided relaxation strategy, forming FREE (relax), which dynamically adjusts the acceptance probability in response to uncertainty levels. Experiments on ImageNet-$512^2$ show that FREE achieves up to $1.86 \times$ acceleration, and FREE (relax) further reaches $2.25 \times$ speedup while maintaining high perceptual and quantitative fidelity in generation quality.

Related papers

• Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers [10.751183015853863]
  Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation.<n>We propose textbfPrediT, a training-free acceleration framework that formulates feature prediction as a linear multistep problem.<n>Our method achieves up to $5.54times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation.
  arXiv  Detail & Related papers  (2026-02-20T09:33:59Z)
• Elastic Diffusion Transformer [32.62353162897611]
  Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive.<n>We propose textbfElastic Diffusion Transformer (E-DiT), an adaptive acceleration framework for DiT.
  arXiv  Detail & Related papers  (2026-02-15T05:19:17Z)
• Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives [22.29000001610794]
  Standard negative log-likelihood for Supervised Fine-Tuning (SFT) applies uniform token-level weighting.<n>This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy supervision and disrupt robust priors, and (ii) uniform weighting provides weak sharpening when the model is already confident.<n>Existing methods fail to resolve the resulting plasticity--stability dilemma, often suppressing necessary learning signals alongside harmful ones.<n>We introduce Dynamic Entropy Fine-Tuning (DEFT), a parameter-free objective that modulates the
  arXiv  Detail & Related papers  (2026-02-11T22:56:43Z)
• D$^2$-VR: Degradation-Robust and Distilled Video Restoration with Synergistic Optimization Strategy [7.553742541566094]
  integration of diffusion priors with temporal alignment has emerged as a transformative paradigm for video restoration, delivering fantastic perceptual quality.<n>We propose textbfD$2$-VR, a single-image diffusion-based video-restoration framework with low-step inference.
  arXiv  Detail & Related papers  (2026-02-09T08:52:51Z)
• Beyond Parameter Finetuning: Test-Time Representation Refinement for Node Classification [59.11332582888994]
  Graph Neural Networks frequently exhibit significant performance degradation in the out-of-distribution test scenario.<n>We propose TTReFT, a novel Test-Time Representation FineTuning framework that transitions the adaptation target from model parameters to latent representations.<n>Specifically, TTReFT achieves this through three key innovations: (1) uncertainty-guided node selection for specific interventions, (2) low-rank representation interventions that preserve pre-trained knowledge, and (3) an intervention-aware masked autoencoder.
  arXiv  Detail & Related papers  (2026-01-29T12:17:34Z)
• Low-Dimensional Adaptation of Rectified Flow: A New Perspective through the Lens of Diffusion and Stochastic Localization [59.04314685837778]
  Rectified flow (RF) has gained considerable popularity due to its generation efficiency and state-of-the-art performance.<n>In this paper, we investigate the degree to which RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution to accelerate sampling.<n>We show that, using a carefully designed choice of the time-discretization scheme and with sufficiently accurate drift estimates, the RF sampler enjoys an complexity of order $O(k/varepsilon)$.
  arXiv  Detail & Related papers  (2026-01-21T22:09:27Z)
• Test time training enhances in-context learning of nonlinear functions [51.56484100374058]
  Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction.<n>We investigate the combination of TTT with in-context learning (ICL), where the model is given a few examples from the target distribution at inference time.
  arXiv  Detail & Related papers  (2025-09-30T03:56:44Z)
• QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification [67.15451442018258]
  Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment.<n>Model quantization and attention sparsification are two promising directions for compression, but each alone suffers severe performance degradation under aggressive compression.<n>We propose textbfQuantSparse, a unified framework that integrates model quantization with attention sparsification.
  arXiv  Detail & Related papers  (2025-09-28T06:49:44Z)
• RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer [86.57077884971478]
  Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling.<n>We introduce RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformers.<n>It delivers image-wise acceleration with zero updates to the base generator.<n>It achieves nearly 3x faster sampling with competitive generation quality.
  arXiv  Detail & Related papers  (2025-09-26T13:20:52Z)
• EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving [64.15371139980802]
  Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP)<n>We show that different test-time scaling strategies for ATP models introduce significant computational overhead for inference.<n>We propose two complementary methods that can be integrated into a unified EconRL pipeline for amplified benefits.
  arXiv  Detail & Related papers  (2025-09-16T03:00:13Z)
• Sortblock: Similarity-Aware Feature Reuse for Diffusion Model [9.749736545966694]
  Diffusion Transformers (DiTs) have demonstrated remarkable generative capabilities.<n>DiTs' sequential denoising process results in high inference latency.<n>We propose Sortblock, a training-free inference acceleration framework.
  arXiv  Detail & Related papers  (2025-08-01T08:10:54Z)
• Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneity [30.53961003855146]
  Federated learning (FL) has emerged as a popular approach for collaborative machine learning in sixth-generation (6G) networks.<n>The deployment of FL algorithms is expected to empower a wide range of Internet-of-Things (IoT) applications, e.g., autonomous driving, augmented reality, and healthcare.<n>We propose a novel C$2$-aware framework for optimal batch-size control that minimizes end-to-end (E2E) learning latency while ensuring convergence.
  arXiv  Detail & Related papers  (2025-07-21T13:24:38Z)
• Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints [51.83081671798784]
  Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability.<n>DiT's practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference.<n>We propose Skip-DiT, an image and video generative DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets.
  arXiv  Detail & Related papers  (2024-11-26T17:28:10Z)
• Provable Acceleration for Diffusion Models under Minimal Assumptions [8.15094483029656]
  We propose a novel training-free acceleration scheme for score-based samplers.<n>Under minimal assumptions, our scheme achieves iterations in total variation within $widetildeO(d5/4/sqrtvarepsilon)$.
  arXiv  Detail & Related papers  (2024-10-30T17:59:06Z)
• Hessian-Free High-Resolution Nesterov Acceleration for Sampling [55.498092486970364]
  Nesterov's Accelerated Gradient (NAG) for optimization has better performance than its continuous time limit (noiseless kinetic Langevin) when a finite step-size is employed. This work explores the sampling counterpart of this phenonemon and proposes a diffusion process, whose discretizations can yield accelerated gradient-based MCMC methods.
  arXiv  Detail & Related papers  (2020-06-16T15:07:37Z)

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.