DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Summary
Proposes DiFA, a training-free framework that reframes inference-time data prediction refinement as sequential state estimation using Kalman filtering, significantly improving generative fidelity on CIFAR-10 and ImageNet.
View Cached Full Text
Cached at: 07/21/26, 06:35 AM
Paper page - DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Source: https://huggingface.co/papers/2607.17972
Abstract
Theprevailinginferenceframeworkfordiffusionmodelsformulatesgenerationfundamentallyasaproblemofnumericalintegration.Thisperspectivecaststhemodelasanexactestimator,neglectingtheinherentstatisticaluncertaintyofthedenoisingprocess.Inthiswork,weproposeForward-ProcessAlignedDiffusionprediction(DiFA),atraining-freeframeworkthatreframesinference-timedatapredictionrefinementasasequentialstateestimationproblem.Ratherthanreusingpastoutputssolelyfornumericalintegration,DiFAtreatsiterativedatapredictionsalongthereversetrajectoryascorrelatedobservationstobuildaforward-alignedtemporalconsensus.InspiredbyKalmanfiltering,thisconsensusaggregateshistoricalpredictionsaccordingtostructuralconsistencyandnoise-levelcompatibility.Tocounteracttheover-smoothingtendencyoftemporalconsensus,weintroduceadeviationguidancemechanismtoadaptivelypreserveresidualdetails.Empirically,DiFAyieldssignificantimprovementsonCIFAR-10andImageNetacrosstheevaluatedmetrics,includingFID,IS,andFD-DINOv2,demonstratingthataligninginferencewiththeforwardstatisticalstructuresubstantiallyimprovesgenerativefidelity.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2607\.17972
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.17972 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.17972 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.17972 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Introduces Flex-Forcing, a unified training and inference framework that allows video diffusion models to operate under both bidirectional and autoregressive regimes via a flexible chunking mechanism over temporal and denoising steps, achieving better video quality, long-video stability, and faster inference.
DiFA: Dual Evidence Fusion and Aggregation for Token-Level Text Anomaly Detection
DiFA introduces a dual-evidence fusion and aggregation framework for token-level text anomaly detection, improving performance by combining form-structural and semantic views across various benchmarks.
ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series
This paper presents ReDiTT, a retrieval augmented conditional diffusion transformer for asynchronous time series prediction. The model retrieves structurally similar latent sequences as reference conditions to improve long-horizon forecasting and sample diversity, achieving state-of-the-art performance on seven real-world datasets.
Temporal Difference Learning for Diffusion Models
This paper introduces a temporal difference (TD) learning objective for diffusion models that enforces cross-time consistency along the denoising trajectory. It reformulates denoising as a reinforcement learning policy evaluation problem, showing significant improvements in sample quality (FID), especially for few-step samplers.
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models
This paper proposes TIE, a knowledge fusion framework for masked diffusion language models that tracks confidence dynamics to identify reliable decoding trajectories and iteratively transfers partially denoised sequences between models, improving generation quality on reasoning tasks.