English
Related papers

Related papers: Test-Time Training Done Right

200 papers

Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the…

Artificial Intelligence · Computer Science 2025-03-26 Ekin Akyürek , Mehul Damani , Adam Zweiger , Linlu Qiu , Han Guo , Jyothish Pari , Yoon Kim , Jacob Andreas

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Quan Kong , Yanru Xiao , Yuhao Shen , Cong Wang

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Machine Learning · Computer Science 2026-02-24 Halil Alperen Gozeten , M. Emrullah Ildiz , Xuechen Zhang , Mahdi Soltanolkotabi , Marco Mondelli , Samet Oymak

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak…

Machine Learning · Computer Science 2025-11-11 Zeman Li , Ali Behrouz , Yuan Deng , Peilin Zhong , Praneeth Kacham , Mahdi Karami , Meisam Razaviyayn , Vahab Mirrokni

The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT)…

Machine Learning · Computer Science 2026-04-08 Guhao Feng , Shengjie Luo , Kai Hua , Ge Zhang , Di He , Wenhao Huang , Tianle Cai

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings…

Machine Learning · Statistics 2026-02-03 Kento Kuwataka , Taiji Suzuki

Medical image segmentation plays a crucial role in clinical diagnosis and treatment planning. Although models based on convolutional neural networks (CNNs) and Transformers have achieved remarkable success in medical image segmentation…

Image and Video Processing · Electrical Eng. & Systems 2024-10-04 Jiashu Xu

Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulnerable to catastrophic forgetting and overfitting. As a result, LaCT is typically…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Ziqiao Ma , Xueyang Yu , Haoyu Zhen , Yuncong Yang , Joyce Chai , Chuang Gan

Recent advances in video generation can produce realistic, minute-long single-shot videos with scalable diffusion transformers. However, real-world narrative videos require multi-shot scenes with visual and dynamic consistency across shots.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Yuwei Guo , Ceyuan Yang , Ziyan Yang , Zhibei Ma , Zhijie Lin , Zhenheng Yang , Dahua Lin , Lu Jiang

The rapid advancements in vision-language models (VLMs), such as CLIP, have intensified the need to address distribution shifts between training and testing datasets. Although prior Test-Time Training (TTT) techniques for VLMs have…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Yuto Kojima , Jiarui Xu , Xueyan Zou , Xiaolong Wang

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Computation and Language · Computer Science 2025-11-20 Xiuying Wei , Anunay Yadav , Razvan Pascanu , Caglar Gulcehre

Test-Time Training (TTT) language models achieve theoretically infinite context windows with an O(1) memory footprint by replacing the standard exact-attention KV-cache with hidden state ``fast weights'' W_fast updated via self-supervised…

Machine Learning · Computer Science 2026-03-10 Swamynathan V P

Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights:…

Machine Learning · Computer Science 2026-05-28 Jian Yang , Zhizhuo Kou , Yao Tian , Hao Zhang , Han Chen , Sirui Han , Yike Guo

Time-series forecasting has seen significant advancements with the introduction of token prediction mechanisms such as multi-head attention. However, these methods often struggle to achieve the same performance as in language modeling,…

Machine Learning · Computer Science 2024-12-03 Panayiotis Christou , Shichu Chen , Xupeng Chen , Parijat Dube

Prior work has established Test-Time Training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is first trained on the same instance using a…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Renhao Wang , Yu Sun , Arnuv Tandon , Yossi Gandelsman , Xinlei Chen , Alexei A. Efros , Xiaolong Wang

Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly when applied beyond the training context length, revealing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Xingyu Chen , Yue Chen , Yuliang Xiu , Andreas Geiger , Anpei Chen

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Computation and Language · Computer Science 2022-10-07 Mario Michael Krell , Matej Kosec , Sergio P. Perez , Andrew Fitzgibbon

With the development of large language models (LLMs), there has been an increasing need for significant advancements in handling long contexts. To enhance long-context capabilities, constructing high-quality training data with long-range…

Computation and Language · Computer Science 2025-02-28 Longyun Wu , Dawei Zhu , Guangxiang Zhao , Zhuocheng Yu , Junfeng Ran , Xiangyu Wong , Lin Sun , Sujian Li

We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Chen Wang , Hao Tan , Wang Yifan , Zhiqin Chen , Yuheng Liu , Kalyan Sunkavalli , Sai Bi , Lingjie Liu , Yiwei Hu

Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an online learning problem, constructing a compact inner model from key-value pairs at test…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Dongchen Han , Yining Li , Tianyu Li , Zixuan Cao , Ziming Wang , Jun Song , Yu Cheng , Bo Zheng , Gao Huang
‹ Prev 1 2 3 10 Next ›