English
Related papers

Related papers: Test-Time Distillation for Continual Model Adaptat…

200 papers

In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions. In test-time adaptation…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Jiayi Han , Longbin Zeng , Liang Du , Weiyang Ding , Jianfeng Feng

Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data…

Machine Learning · Computer Science 2025-11-14 Ruxi Deng , Wenxuan Bao , Tianxin Wei , Jingrui He

Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller…

Computation and Language · Computer Science 2023-11-08 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Hongbo Zhang , Sung Ju Hwang , Alexander Min

Dataset distillation (DD) generates small synthetic datasets that can efficiently train deep networks with a limited amount of memory and compute. Despite the success of DD methods for supervised learning, DD for self-supervised…

Machine Learning · Computer Science 2025-04-02 Siddharth Joshi , Jiayi Ni , Baharan Mirzasoleiman

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Geon Yeong Park , Sang Wan Lee , Jong Chul Ye

Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and substantial computational resources. Dataset distillation offers a promising alternative by synthesizing…

Machine Learning · Computer Science 2025-11-24 Yuqi Li , Kuiye Ding , Chuanguang Yang , Hao Wang , Haoxuan Wang , Huiran Duan , Junming Liu , Yingli Tian

Reasoning is increasingly crucial for various tasks. While chain-of-thought prompting enables large language models to leverage reasoning effectively, harnessing the reasoning capabilities of Vision-Language Models (VLMs) remains…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Guande Wu , Huan Song , Yawei Wang , Qiaojing Yan , Yijun Tian , Lin Lee Cheong , Panpan Xu

Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two representative paradigms. While consistency methods enforce…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Tao Liu , Hao Yan , Mengting Chen , Taihang Hu , Zhengrong Yue , Zihao Pan , Jinsong Lan , Xiaoyong Zhu , Ming-Ming Cheng , Bo Zheng , Yaxing Wang

Test-Time Adaptation (TTA) has emerged as an effective solution for adapting Vision Transformers (ViT) to distribution shifts without additional training data. However, existing TTA methods often incur substantial computational overhead,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Yizhe Xiong , Zihan Zhou , Yiwen Liang , Hui Chen , Zijia Lin , Tianxiang Hao , Fan Zhang , Jungong Han , Guiguang Ding

Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes. However, this enhanced reasoning capability results in an increased number of output tokens during inference, leading to…

Computation and Language · Computer Science 2025-11-05 Jingxian Xu , Mengyu Zhou , Weichang Liu , Hanbing Liu , Shi Han , Dongmei Zhang

Machine learning models must continuously self-adjust themselves for novel data distribution in the open world. As the predominant principle, entropy minimization (EM) has been proven to be a simple yet effective cornerstone in existing…

Machine Learning · Statistics 2024-10-16 Qingyang Zhang , Yatao Bian , Xinke Kong , Peilin Zhao , Changqing Zhang

Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training…

Machine Learning · Computer Science 2025-06-05 Gianluigi Silvestri , Luca Ambrogioni , Chieh-Hsin Lai , Yuhta Takida , Yuki Mitsufuji

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. However, existing knowledge distillation has side effects, such as propagating…

Computation and Language · Computer Science 2023-08-07 Min Liu , Yu Bao , Chengqi Zhao , Shujian Huang

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classification problems. The pronounced success of classification…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Chang'an Yi , Haotian Chen , Yifan Zhang , Yonghui Xu , Yan Zhou , Lizhen Cui

Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data selection methods suffer from severe domain specificity:…

Computation and Language · Computer Science 2026-02-02 Junyou Su , He Zhu , Xiao Luo , Liyu Zhang , Hong-Yu Zhou , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Machine learning models for text classification often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OOD robustness are not applicable to settings where the model…

Machine Learning · Computer Science 2024-08-06 Kyle O'Brien , Nathan Ng , Isha Puri , Jorge Mendez , Hamid Palangi , Yoon Kim , Marzyeh Ghassemi , Thomas Hartvigsen

Deep neural networks often exhibit poor performance on data that is unlikely under the train-time data distribution, for instance data affected by corruptions. Previous works demonstrate that test-time adaptation to data shift, for instance…

In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-20 Oscar Chang , Dongseong Hwang , Olivier Siohan

Leveraging shared learning through Massively Multilingual Models, state-of-the-art machine translation models are often able to adapt to the paucity of data for low-resource languages. However, this performance comes at the cost of…

Computation and Language · Computer Science 2022-11-10 Harshita Diddee , Sandipan Dandapat , Monojit Choudhury , Tanuja Ganu , Kalika Bali

Large language models (LLMs) demonstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-time adaptation (TTA) methods rely on gradient-based updates that require white-box access…

Computation and Language · Computer Science 2026-04-16 Kaiwen Zheng , Kai Zhou , Jinwu Hu , Te Gu , Mingkai Peng , Fei Liu