English
Related papers

Related papers: Initialization of Large Language Models via Repara…

200 papers

Training large language models (LLMs) typically relies on adaptive optimizers like Adam (Kingma & Ba, 2015) which store additional state information to accelerate convergence but incur significant memory overhead. Recent efforts, such as…

Machine Learning · Computer Science 2025-02-11 Meyer Scetbon , Chao Ma , Wenbo Gong , Edward Meeds

Large language models of high parameter counts are computationally expensive, yet can be made much more efficient by compressing their weights to very low numerical precision. This can be achieved either through post-training quantization…

Machine Learning · Computer Science 2025-04-21 Zifei Xu , Sayeh Sharify , Wanzin Yazar , Tristan Webb , Xin Wang

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

Multimedia · Computer Science 2022-12-07 Shinta Otake , Rei Kawakami , Nakamasa Inoue

We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and…

Neural and Evolutionary Computing · Computer Science 2016-11-23 Anders Søgaard

Large Language Models (LLMs), built on Transformer architectures, exhibit remarkable generalization across a wide range of tasks. However, fine-tuning these models for specific tasks remains resource-intensive due to their extensive…

Machine Learning · Computer Science 2025-05-15 Xinhao Yao , Hongjin Qian , Xiaolin Hu , Gengze Xu , Wei Liu , Jian Luan , Bin Wang , Yong Liu

The automated classification of stuttered speech has significant implications for timely assessments providing assistance to speech language pathologists. Despite notable advancements in the field, the cases in which multiple disfluencies…

Sound · Computer Science 2025-02-27 Huma Ameer , Seemab Latif , Mehwish Fatima

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

Overparameterization refers to the important phenomenon where the width of a neural network is chosen such that learning algorithms can provably attain zero loss in nonconvex training. The existing theory establishes such global convergence…

Machine Learning · Computer Science 2021-11-04 Chaehwan Song , Ali Ramezani-Kebrya , Thomas Pethick , Armin Eftekhari , Volkan Cevher

Recent studies have shown that as training progresses, neural networks gradually lose their capacity to learn new information, a phenomenon known as plasticity loss. An unbounded weight growth is one of the main causes of plasticity loss.…

Machine Learning · Computer Science 2025-07-08 Seungwon Oh , Sangyeon Park , Isaac Han , Kyung-Joong Kim

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation. Yet these neural networks are very sensitive to architecture and hyperparameter settings. Optimizing these settings by grid…

Computation and Language · Computer Science 2019-10-16 Kenton Murray , Jeffery Kinnison , Toan Q. Nguyen , Walter Scheirer , David Chiang

Transformers deliver outstanding performance across a wide range of tasks and are now a dominant backbone architecture for large language models (LLMs). Their task-solving performance is improved by increasing parameter size, as shown in…

Computation and Language · Computer Science 2025-06-10 Hidetaka Kamigaito , Ying Zhang , Jingun Kwon , Katsuhiko Hayashi , Manabu Okumura , Taro Watanabe

Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while…

Machine Learning · Computer Science 2024-12-10 Jörg K. H. Franke , Michael Hefenbrock , Gregor Koehler , Frank Hutter

As large language models achieve impressive scores on traditional benchmarks, an increasing number of researchers are becoming concerned about benchmark data leakage during pre-training, commonly known as the data contamination problem. To…

Computation and Language · Computer Science 2024-06-27 Kun Qian , Shunji Wan , Claudia Tang , Youzhi Wang , Xuanming Zhang , Maximillian Chen , Zhou Yu

This paper presents the first study to explore the potential of parameter quantization for multimodal large language models to alleviate the significant resource constraint encountered during vision-language instruction tuning. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2024-08-08 Jingjing Xie , Yuxin Zhang , Mingbao Lin , Liujuan Cao , Rongrong Ji

In this paper, we introduce the Curse of Depth, a concept that highlights, explains, and addresses the recent observation in modern Large Language Models (LLMs) where nearly half of the layers are less effective than expected. We first…

Machine Learning · Computer Science 2026-02-24 Wenfang Sun , Xinyuan Song , Pengxiang Li , Lu Yin , Yefeng Zheng , Shiwei Liu

Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks. While existing compression techniques are effective in…

Machine Learning · Computer Science 2025-06-03 Sameera Ramasinghe , Thalaiyasingam Ajanthan , Gil Avraham , Yan Zuo , Alexander Long

Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Mengjie Qian , Siyuan Tang , Rao Ma , Kate M. Knill , Mark J. F. Gales

Training extremely large language models (LLMs) with billions of parameters is a computationally intensive task that pushes the limits of current data parallel training systems. While techniques like ZeRO++ have enabled efficient…

Machine Learning · Computer Science 2024-10-08 Yun Dai , Tejas Dharamsi , Byron Hsu , Tao Song , Hamed Firooz

We present WaferSAGE, a framework for wafer defect visual question answering using small vision-language models. To address data scarcity in semiconductor manufacturing, we propose a three-stage synthesis pipeline incorporating structured…

Artificial Intelligence · Computer Science 2026-05-12 Ke Xu , Zhongyuan Lian
‹ Prev 1 8 9 10 Next ›