# SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation

Source: [SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation](<https://www.sota2.com/research/paper/68fa7c291e209131cea8cc24>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:58:13.123Z

Authors: Jihyun Yu, Yoojin Oh, Wonho Bae, Mingyu Kim, Junhyug Noh

Published: 2025-10-16T12:46:53.000Z

## Abstract

Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffusion-based TTA methods improve robustness for classification to corruptions but rely on gradient guidance, limiting exploration and generalization across distortion types. We propose SteeringTTA, an inference-only framework that adapts Feynman-Kac steering to guide diffusion-based input adaptation for classification with rewards driven by pseudo-label. SteeringTTA maintains multiple particle trajectories, steered by a combination of cumulative top-K probabilities and an entropy schedule, to balance exploration and confidence. On ImageNet-C, SteeringTTA consistently outperforms the baseline without any model updates or source data.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.14634>)

[PDF](<https://arxiv.org/pdf/2510.14634.pdf>)