arXiv Computer Vision September 11, 2026 By Kartik Jhawar, Lipo Wang

When is Test-Time Adaptation Identifiable From Unlabeled Evidence?

Read the original on arXiv Computer Vision →

arXiv:2609. 11235v1 Announce Type: new Abstract: Test-time adaptation (TTA) offers many ways to update a deployed model without labels, but choosing the wrong update can make a strong source model worse.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

benchmarks

arXiv AI

4d ago

WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation

arXiv:2609.37687v1 Announce Type: new Abstract: Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively queryin...

By Muhammad Huzaifa, Lea Sch\"onherr, Thorsten Eisenhofer

arXiv Computer Vision

4d ago

Not Every Correction Helps: Gain-Guided Continual Test-Time Adaptation

arXiv:2609.36655v1 Announce Type: new Abstract: Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods o...

By Youjia Zhang, Huiling Liu, Soyun Choi, Jaehong Yoon, Sungeun Hong

benchmarks

arXiv AI

Jun 10

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective

arXiv:2605. 28057v2 Announce Type: replace-cross Abstract: Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data.

By Zhi Zhou, Ming Yang, Shi-Yu Tian, Kun-Yang Yu, Lan-Zhe Guo, Yu-Feng Li

arXiv Machine Learning

Jun 2

Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation

arXiv:2602. 06136v2 Announce Type: replace Abstract: Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled samples.

By Sudarshan Sreeram, Young D. Kwon, Cecilia Mascolo

arXiv AI

Jul 21

Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration

arXiv:2607. 17531v1 Announce Type: cross Abstract: Test-time collaboration, including self-consistency, best-of-N selection, critic models, and verifier pipelines, is often credited with broadly improving LLM reasoning, yet its gains are uneven and sometimes negative.

By Jie Hu

llms agents

arXiv Machine Learning

Sep 1

Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting

arXiv:2608.29920v1 Announce Type: cross Abstract: Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA...

By Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui, Tor Kristian Stevik, Fadi Al Machot, Kristian Hovde Liland, Habib Ullah

One email a morning, machine-written

Related stories

WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation

Not Every Correction Helps: Gain-Guided Continual Test-Time Adaptation

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective

Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation

Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration

Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting