English
Related papers

Related papers: Drop Clause: Enhancing Performance, Interpretabili…

200 papers

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power…

Computation and Language · Computer Science 2022-10-31 Zhiyi Wang , Shaoguang Mao , Wenshan Wu , Yan Xia

The industry increasingly relies on deep learning (DL) technology for manufacturing inspections, which are challenging to automate with rule-based machine vision algorithms. DL-powered inspection systems derive defect patterns from labeled…

Machine Learning · Computer Science 2024-09-17 Altaf Allah Abbassi , Houssem Ben Braiek , Foutse Khomh , Thomas Reid

Recent advancements in Transformer-based large language models (LLMs) have set new standards in natural language processing. However, the classical softmax attention incurs significant computational costs, leading to a $O(T)$ complexity for…

Computation and Language · Computer Science 2025-05-20 Zhihao He , Hang Yu , Zi Gong , Shizhan Liu , Jianguo Li , Weiyao Lin

The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic uncertainty techniques are robust when trained with noisy…

Machine Learning · Computer Science 2021-03-23 Purvi Goel , Li Chen

Previous studies on continual knowledge learning (CKL) in large language models (LLMs) have predominantly focused on approaches such as regularization, architectural modifications, and rehearsal techniques to mitigate catastrophic…

Computation and Language · Computer Science 2025-02-06 Yeongbin Seo , Dongha Lee , Jinyoung Yeo

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This…

Machine Learning · Computer Science 2024-11-06 Hanrui Yan , Dan Shao

Contrastive learning has shown to be effective to learn representations from time series in a self-supervised way. However, contrasting similar time series instances or values from adjacent timestamps within a time series leads to ignore…

Machine Learning · Computer Science 2026-01-15 Seunghan Lee , Taeyoung Park , Kibok Lee

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Machine Learning · Computer Science 2025-04-04 Artyom Gadetsky , Andrei Atanov , Yulun Jiang , Zhitong Gao , Ghazal Hosseini Mighan , Amir Zamir , Maria Brbic

Vocabulary selection, or lexical shortlisting, is a well-known technique to improve latency of Neural Machine Translation models by constraining the set of allowed output words during inference. The chosen set is typically determined by…

Computation and Language · Computer Science 2022-05-16 Tobias Domhan , Eva Hasler , Ke Tran , Sony Trenous , Bill Byrne , Felix Hieber

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

Machine Learning · Computer Science 2025-12-04 Runze Zhao , Yue Yu , Ruhan Wang , Chunfeng Huang , Dongruo Zhou

Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…

Machine Learning · Computer Science 2026-04-15 Amar Gahir , Varshil Patel , Shreyank N Gowda

This paper explores how to enhance existing masked time-series modeling by randomly dropping sub-sequence level patches of time series. On this basis, a simple yet effective method named DropPatch is proposed, which has two remarkable…

Machine Learning · Statistics 2024-12-23 Tianyu Qiu , Yi Xie , Yun Xiong , Hao Niu , Xiaofeng Gao

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Zixin Wang , Dong Gong , Sen Wang , Zi Huang , Yadan Luo

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Computation and Language · Computer Science 2026-04-21 Dang Huu-Tien , Hoang Thanh-Tung , Anh Bui , Minh-Phuong Nguyen , Le-Minh Nguyen , Naoya Inoue

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…

Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing…

Computation and Language · Computer Science 2023-04-13 Zixuan Ke , Yijia Shao , Haowei Lin , Tatsuya Konishi , Gyuhak Kim , Bing Liu

The reliable application of deep learning models to software engineering tasks hinges on high-quality training data. Yet, large-scale repositories inevitably introduce noisy or mislabeled examples that degrade both accuracy and robustness.…

Software Engineering · Computer Science 2025-12-05 Zixiao Zhao , Fatemeh H. Fard , Jie JW Wu

The PC algorithm is a widely used method in causal inference for learning the structure of Bayesian networks. Despite its popularity, the PC algorithm suffers from significant time complexity, particularly as the size of the dataset…

Machine Learning · Computer Science 2025-11-25 Kunal Dumbre , Lei Jiao , Ole-Christoffer Granmo

Time Series Foundation Models (TSFMs) have shown promising zero-shot generalization across diverse forecasting tasks. However, their robustness to continual adaptation remains underexplored. In this work, we investigate the extent to which…

Machine Learning · Computer Science 2025-10-03 Nouha Karaouli , Denis Coquenet , Elisa Fromont , Martial Mermillod , Marina Reyboz

We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual…

Artificial Intelligence · Computer Science 2022-03-25 Jinghui Lu , Linyi Yang , Brian Mac Namee , Yue Zhang