English
Related papers

Related papers: Test-Time Training Done Right

200 papers

Long-context video modeling is essential for enabling generative models to function as world simulators, as they must maintain temporal coherence over extended time spans. However, most existing models are trained on short clips, limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Yuchao Gu , Weijia Mao , Mike Zheng Shou

Fast weight architectures offer a promising alternative to attention-based transformers for long-context modeling by maintaining constant memory overhead regardless of context length. However, their potential is limited by the next-token…

Computation and Language · Computer Science 2026-02-19 Hee Seung Hwang , Xindi Wu , Sanghyuk Chun , Olga Russakovsky

Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping at test time. However, our analysis reveals multiple phenomena that contradict…

Machine Learning · Computer Science 2026-05-14 Junchen Liu , Sven Elflein , Or Litany , Zan Gojcic , Ruilong Li

Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory…

Image and Video Processing · Electrical Eng. & Systems 2020-03-12 Kushal Datta , Imtiaz Hossain , Sun Choi , Vikram Saletore , Kyle Ambert , William J. Godinez , Xian Zhang

Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of various lengths and then chunking them into sequences of a…

Computation and Language · Computer Science 2025-01-08 Hadi Pouransari , Chun-Liang Li , Jen-Hao Rick Chang , Pavan Kumar Anasosalu Vasu , Cem Koc , Vaishaal Shankar , Oncel Tuzel

Recently, test-time adaptation has garnered attention as a method for tuning models without labeled data. The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time primarily focuses on tuning…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Raza Imam , Asif Hanif , Jian Zhang , Khaled Waleed Dawoud , Yova Kementchedjhieva , Mohammad Yaqub

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-14 Xiulong Yuan , Hongtao Xu , Wenting Shen , Ang Wang , Xiafei Qiu , Jie Zhang , Yuqiong Liu , Bowen Yu , Junyang Lin , Mingzhen Li , Weile Jia , Yong Li , Wei Lin

Large Language Models (LLMs) exhibit substantial parameter redundancy, particularly in Feed-Forward Networks (FFNs). Existing pruning methods suffer from two primary limitations. First, reliance on dataset-specific calibration introduces…

Computation and Language · Computer Science 2026-02-02 Abhishek Tyagi , Yunuo Cen , Shrey Dhorajiya , Bharadwaj Veeravalli , Xuanyao Fong

Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines, making them costly to train and difficult to adapt to new…

This paper addresses the challenge of capturing global temporaldependencies in long video sequences for Video Object Segmentation (VOS). Existing architectures often fail to effectively model these dependencies acrossextended temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Fenglei Hao , Yuliang Yang , Ruiyuan Su , Zhengran Zhao , Yukun Qiao , Mengyu Zhu

Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by…

Computation and Language · Computer Science 2024-12-06 Suyu Ge , Xihui Lin , Yunan Zhang , Jiawei Han , Hao Peng

Despite recent progress in video large language models (VideoLLMs), a key open challenge remains: how to equip models with chain-of-thought (CoT) reasoning abilities grounded in fine-grained object-level video understanding. Existing…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Yanan Wang , Julio Vizcarra , Zhi Li , Hao Niu , Mori Kurokawa

Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model…

Computation and Language · Computer Science 2025-11-10 Wei Shao , Lingchao Zheng , Pengyu Wang , Peizhen Zheng , Jun Li , Yuwei Fan

Transformer-based Language Models' computation and memory overhead increase quadratically as a function of sequence length. The quadratic cost poses challenges when employing LLMs for processing long sequences. In this work, we introduce…

Computation and Language · Computer Science 2025-10-23 Kiarash Zahirnia , Zahra Golpayegani , Walid Ahmed , Yang Liu

Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate…

Computation and Language · Computer Science 2026-04-21 Iqra Ali , Talia Tseriotou , Mahmud Elahi Akhter , Yuxiang Zhou , Maria Liakata

Recent work has shown how to train Convolutional Neural Networks (CNNs) rapidly on large image datasets, then transfer the knowledge gained from these models to a variety of tasks. Following [Radford 2017], in this work, we demonstrate…

Machine Learning · Computer Science 2018-08-14 Raul Puri , Robert Kirby , Nikolai Yakovenko , Bryan Catanzaro

Learning to adapt pretrained language models to unlabeled, out-of-distribution data is a critical challenge, as models often falter on structurally novel reasoning tasks even while excelling within their training distribution. We introduce…

Computation and Language · Computer Science 2025-05-29 Mohammad Mahdi Moradi , Hossam Amer , Sudhir Mudur , Weiwei Zhang , Yang Liu , Walid Ahmed

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

Generalizing neural networks to unseen target domains is a significant challenge in real-world deployments. Test-time training (TTT) addresses this by using an auxiliary self-supervised task to reduce the domain gap caused by distribution…

Machine Learning · Computer Science 2025-07-22 Wooseong Jeong , Jegyeong Cho , Youngho Yoon , Kuk-Jin Yoon

Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 David Osowiechi , Gustavo A. Vargas Hakim , Mehrdad Noori , Milad Cheraghalikhani , Ali Bahri , Moslem Yazdanpanah , Ismail Ben Ayed , Christian Desrosiers