Test-Time Training

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 46

All topics

Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning
Oct 1, 2026Jude Waide, Robert LieckTest-Time Training Long-Term Memory
Department of Computer Science, University of Durham, Durham, United Kingdom.
JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
Sep 30, 2026Zheyuan Zhang, Suyu Ye, Nakul Agarwal +5Latent World Models Test-Time Training
Honda Research Institute USA · Johns Hopkins University
Transferable Mass Spectrum Prediction via Reference-Guided Test-time Specialization
Sep 28, 2026Yunhua Zhong, Runting Li, Yifan Li +5Tandem Mass Spectra Metabolic
The Hong Kong University of Science and Technology (Guangzhou) · The University of Hong Kong · South China University of Technology +3
GradLev: Token-Parallel Test-Time Training Via Costate Prediction
Sep 28, 2026Bo Liu, Qiang LiuTest-Time Training Inference-Time
The University of Texas at Austin
Position Aware Layer Queries for Test Time Training in Vision Language Models
Sep 27, 2026Rajat Modi, Priyank Pathak, Xin Liang +1Frozen Contrastive Language-Image Pre-Training Visual Encoder Test-Time Training
Institute of Artificial Intelligence University of Central Florida Orlando, FL 32816, USA
LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation
Sep 8, 2026Yi Luo, Yike Guo, Wenxuan Li +3Radiotherapy Test-Time Training
Department of Biomedical Engineering, Johns Hopkins University · Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University · Department of Computer Science, Johns Hopkins University +1
A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
Sep 1, 2026Shuaicheng Niu, Guohao Chen, Yaofo Chen +14Test-Time Adaptation Test-Time Training
South China University of Technology · Nanyang Technological University · Tulane University +3
VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction
Aug 10, 2026Hongjin Ji, Guoyang Xia, Luoyang Sun +2Test-Time Training
The Chinese University of Hong Kong, Shenzhen · Li Auto Inc. · Beijing University of Posts and Telecommunications +2
Modular TTT: Rethinking Test-Time Training as Composable Modules
Aug 7, 2026Bohao Tang, Zhen Qin, Yuqi Pan +3Test-Time Training Sequence Modeling
Shanghai Jiao Tong University · Shanghai Innovation Institute · ByteDance Seed
Learning What to Remember: Test-Time Training via Context Distillation
Aug 3, 2026Zixuan Wang, Xingyu Dang, Rui-Jie Zhu +4Efficient Long-Context Inference Test-Time Training
Princeton University · UC Santa Cruz · Carnegie Mellon University +1
Test-Time Training for Modality Order Consistency in Vision-Language Models
Jul 22, 2026Aditi Gupta, Yossi GandelsmanModalities Test-Time Training
University of Chicago · Reve
Self-Guided Test-Time Training for Long-Context LLMs
Jul 10, 2026Xinyu Zhu, Zhe Xu, Xiaohan Wei +10Efficient Long-Context Inference Test-Time Training
Meta AI · University of Virginia
No Time Like the Present: Agentic Test-Time Training for LLM Agents
Jul 3, 2026Yanbo Wang, Jinhua Hao, Yuze Shi +2Test-Time Training Large Language Model Training
Kuaishou Technology
Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training
Jul 1, 2026Xiangchen Song, Zhenhao Chen, Lingjing Kong +4Large Language Model Memory Large Language Model Evaluation
Carnegie Mellon University · MBZUAI
T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation
Jun 29, 2026Huy Truong, Alexander Lazovik, Victoria DegelerStable Test-Time Adaptation Graph Neural Networks
Bernoulli Institute, University of Groningen, Groningen, The Netherlands · Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
Forget, Anticipate and Adapt: Test Time Training for Long Videos
Jun 25, 2026Rajat Modi, Sebastian Noel, Xin Liang +1Test-Time Training Video Temporal Grounding
Institute of Artificial Intelligence, University of Central Florida
Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs
Jun 24, 2026Wenjie Zhu, Yabin Zhang, Liang Xu +3Out-Of-Distribution Detection Vision-Language Model Adaptation
The Hong Kong Polytechnic University · Harbin Institute of Technology (Shenzhen) · Shanghai Jiao Tong University +1
Test-Time Training with Next-Token Prediction
Jun 19, 2026Xuan Ouyang, Zefan Cai, Junjie HuTest-Time Training Next-Token Prediction
University of Wisconsin–Madison
MedTS-TTT: Test-Time Training for Medical Time Series Classification
Jun 19, 2026Mingzhi Chen, Yiyu Gui, Guibo LuoTime-Series Classification Test-Time Training
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University, Shenzhen, China
Test-Time Training for Robust Text-Guided Open-Vocabulary Object Counting
Jun 16, 2026Hao-Yuan Ma, Yuda Zou, Li Zhang +1Open-Vocabulary Object Detection Scene Text Recognition
School of Computer Science and Technology, Soochow University Suzhou, China · Wuhan University Wuhan, China
A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt
Jun 14, 2026Tomoya WakayamaStable Test-Time Adaptation Test-Time Training
RIKEN Center for Advanced Intelligence Project (AIP), Tokyo, Japan.
The Power of Test-Time Training for Approximate Sampling
Jun 9, 2026Noah Golowich, Ankur Moitra, Dhruv RohatgiOptimal Sample Complexity Test-Time Training
Microsoft Research NYC · MIT
U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training
Jun 9, 2026Zhiwen Yang, Jiayin Li, Hao Lu +3Positron Emission Tomography U-Net
School of Biological Science and Medical Engineering, Beihang University, Beijing 100191, China · Department of Biomedical Engineering, Tsinghua University, Beijing 100084, China · School of Aerospace Engineering, Tsinghua University, Beijing 100084, China
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
Jun 7, 2026Yishuo Cai, Xingyu Guo, Xuancheng Huang +8Large Language Model Agents Test-Time Training
Peking University, Beijing, China · Central South University, Changsha, China · Zhipu AI, Beijing, China +3
EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering
Jun 5, 2026Xiaopeng Yuan, Zebin Wang, Suwen Wang +3Efficient Long-Context Inference Question-Answering Benchmarks
University of Illinois Urbana-Champaign · 2Harvard University · 3Brion, ASML US LP +1
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
Jun 3, 2026Peilong Zhou, Zhirong Chen, Cangyuan Li +4Hierarchical Register Transfer Level Generation Register Transfer Level
1SKLP, Institute of Computing Technology, Chinese Academy of Sciences · University of the Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences
TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models
Jun 2, 2026Wenbo Zhang, Jianxiong Li, Shuai Yang +4Test-Time Training Steering
ByteDance Seed · The University of Adelaide · Tsinghua University +3
Test-Time Training for Zero-Resource Dense Retrieval Reranking
May 31, 2026Shiyan Liu, Yichen LiRetrieval Layer Cross-Encoder Reranking
Huazhong University of Science and Technology · ByteDance
Test Time Training for Supervised Causal Learning
May 28, 2026Zizhen Deng, Jiaru Zhang, Rui Ding +5Causal Discovery Methods Test-Time Training
Peking University · The work was done during his internship at Microsoft. · Shanghai Jiao Tong University +2
RW-TTT: Batched Serving for Request-Owned Test-Time Training State
May 27, 2026Jian Yang, Zhizhuo Kou, Yao Tian +4Large Language Model Serving Time-To-First-Token
1The Hong Kong University of Science and Technology · 2The Chinese University of Hong Kong · 3National University of Singapore
Test-Time Training Undermines Safety Guardrails
May 21, 2026Simone Antonelli, Sadegh Akhondzadeh, Aleksandar BojchevskiInference-Time Defense Test-Time Training
CISPA Helmholtz Center for Information Security · University of Cologne
Test-Time Learning with an Evolving Library
May 14, 2026Weijia Xu, Alessandro Sordoni, Chandan Singh +4Test-Time Training Replay-Based Continual Learning
Microsoft Research
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
May 13, 2026Tsz Ting Chung, Lemao Liu, Mo Yu +1In-Context Learning In-Context
Hong Kong University of Science and Technology · Fudan University · Wechat AI, Tencent.
Query-Conditioned Test-Time Self-Training for Large Language Models
May 13, 2026Chaehee Song, Minseok Seo, Yeeun Seong +2Test-Time Training Test-Time Scaling
School of Electrical Engineering, KAIST · 2Graduate School of Green Growth and Sustainability, KAIST
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
May 7, 2026Minghao Yan, Bo Peng, Benjamin Coleman +11Evolutionary Search Test-Time Training
1Google · University of Wisconsin–Madison · 3Google DeepMind
Test-Time Training for Visual Foresight Vision-Language-Action Models
May 6, 2026Sangwu Park, Wonjoong Kim, Yeonjun In +3Diffusion-Based Vision-Language-Actions Photometric Supervision
KAIST, Seoul, South Korea.
Linearizing Vision Transformer with Test-Time Training
May 4, 2026Yining Li, Dongchen Han, Zeyu Liu +3Self-Supervised Vision Transformers Vision Transformer
Tsinghua University, Beijing, China
Multi-Perspective Transformers in ARC-AGI-2 Challenge
May 1, 2026Caleb Talley, Vedant Tibrewal, Seun Adekunle +3Puzzle Model Fine-Tuning
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Apr 22, 2026Zhixin Zhang, Shabo Zhang, Chengcan Wu +2Efficient Long-Context Inference LLM Inference Optimization
1Peking University.
TEMPO: Scaling Test-time Training for Large Reasoning Models
Apr 21, 2026Qingyang Zhang, Xinke Kong, Haitao Wu +7Test-Time Training Inference-Time
Tianjin University · Tongyi Lab, Alibaba Group · The Chinese University of Hong Kong +1
Meta-TTL: Meta-Learning Self-Improvement Policies for Language Agents
Apr 1, 2026Zhanzhi Lou, Hui Chen, Yibo Li +2Stable Test-Time Adaptation Test-Time Training
National University of Singapore
TTSR: Test-Time Self-Evolving via Reflection
Feb 6, 2026Haoyang He, Zihua Rong, Yunjia Zhao +3Test-Time Training Test Time
Beijing University of Posts and Telecommunications · Southwestern University of Finance and Economics · China Unicom Online Information Technology Co., Ltd.
Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
Jan 28, 2026Zhengbo Jiao, Hongyu Xian, Qinglong Wang +5LLM Reasoning Strategies Large Language Model Policy Optimization
Zhejiang University · South China Normal University · Shanghai University of Finance and Economics +2
SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
Dec 5, 2025Yang Zheng, Hao Tan, Kai Zhang +43D Gaussian 3D Editing
Stanford University · Adobe
Test time training enhances in-context learning of nonlinear functions
Sep 30, 2025Kento Kuwataka, Taiji SuzukiIn-Context Learning Test-Time Training
Department of Mathematical Engineering and Information Physics The University of Tokyo Hongo 7-3-1, Bunkyo-ku, Tokyo
PERK: Long-Context Reasoning as Test-Time Learning
Jul 8, 2025Zeming Chen, Angelika Romanou, Gail Weiss +1Efficient Long-Context Inference Long-Context Reasoning
EPFL

Oct 1, 2026, cs.AIJ/K move · Enter open · S save

Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning

Jude Waide, Robert Lieck

Department of Computer Science, University of Durham, Durham, United Kingdom.

Test-Time Training Long-Term Memory Transformer Architectures

Open paper AskPDF arXiv

Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: RNNs suffer from vanishing gradients and the limited expressivity of vector-based hidden states, whilst Transformer-based models are limited by the quadratic scaling of attention. Recent work has proposed tackling this problem with the Test-Time Training (TTT) framework, which stores episodic memories in the parameters of a neural network through gradient descent at both train and test-time. This approach has seen success in the domain of Natural Language Processing, however, to the best of our knowledge it has not yet been applied to the domain of Reinforcement Learning (RL), nor has there been a study analysing how this memory practically functions. In this paper, we study the potential of the TTT framework for offline RL by augmenting a Decision Transformer with TTT layers, dubbed the Decision Titan. We analyse performance and properties of the model in the X-Maze environment, an extension of T-Maze designed to test sequential memory, and investigate how the memory mechanism learns by visualising gate values over time. Our key findings are that Decision Titan can learn long-term dependencies with ranges 20x longer than the context window, generalises to lengths 1.7x the training data, but crucially temporal generalisation depends on the time embeddings used, and the ability to learn long-term dependencies depends on how the relevant information is encoded.

Momentum

Related topics

Latest papers 46