Papers

A curated list of papers on Test-Time Training / Adaptation, inspired by the Awesome list format. This page gathers foundational and recent research focused on enabling models to adapt at test time to improve robustness under distribution shifts.

Figure 1: This plot shows the trend of citations per year for Test-Time Training and Test-Time Adaptation papers listed below. The dashed red line represents the projected citation count for the current year based on the citation trajectory so far. Overall, the visualization illustrates the increasing academic attention and influence of these methods over time.

Sort by: Citations (high to low) Year (newest first) Conference (A-Z) Title (A-Z)

TENT: Fully Test-time Adaptation by Entropy Minimization

Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, Trevor Darrell

ICLR (2021)

paper | code

Citations: 1327

Test-Time Training with Self-Supervision for Generalization under Distribution Shifts

Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt

ICML (2020)

paper | code

Citations: 984

Efficient Test-Time Model Adaptation without Forgetting

Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, Mingkui Tan

ICLR (2023)

paper | code

Citations: 377

MEMO: Test Time Robustness via Adaptation and Augmentation

Marvin Zhang, Sergey Levine, Chelsea Finn

NeurIPS (2022)

paper | code

Citations: 359

TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?

Yuejiang Liu, Parth Kothari, Bastien van Delft, Baptiste Bellot-Gurlet, Taylor Mordan, Alexandre Alahi

NeurIPS (2021)

paper | code

Citations: 330

Test-Time Training with Masked Autoencoders

Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros

NeurIPS (2022)

paper | code

Citations: 191

Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Yu Sun, Xinhao Li, Karan Dalal, Jiarui Xu, Arjun Vikram, Genghan Zhang, Yann Dubois, Xinlei Chen, Xiaolong Wang, Sanmi Koyejo, Tatsunori Hashimoto, Carlos Guestrin

ICLR (2025)

paper | code

Citations: 89

Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors

Jonghyun Lee, Dahuin Jung, Saehyung Lee, Junsung Park, Juhyeon Shin, Uiwon Hwang, Sungroh Yoon

ICLR (2024)

paper | code

Citations: 35

ActMAD: Activation Matching to Align Distributions for Test-Time-Training

Muhammad Jehanzeb Mirza, Pol Jané Soneira, Wei Lin, Mateusz Kozinski, Horst Possegger, Horst Bischof

CVPR (2023)

paper | code

Citations: 29

Test-Time Training on Nearest Neighbors for Large Language Models

Moritz Hardt, Yu Sun

ICLR (2024)

paper | code

Citations: 21

Test-Time Training on Video Streams

Renhao Wang, Yu Sun, Arnuv Tandon, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang

JMLR (2023)

paper | code

Citations: 15