English
Related papers

Related papers: Optimizing Deeper Transformers on Small Datasets

200 papers

In this paper, we propose a simple yet effective method to stabilize extremely deep Transformers. Specifically, we introduce a new normalization function (DeepNorm) to modify the residual connection in Transformer, accompanying with…

Computation and Language · Computer Science 2022-03-02 Hongyu Wang , Shuming Ma , Li Dong , Shaohan Huang , Dongdong Zhang , Furu Wei

This micro-paper describes a trick to speed up inference of transformers with RoPE (such as LLaMA, Mistral, PaLM, and Gemma). For these models, a large portion of the first transformer layer can be precomputed, which results in slightly…

Machine Learning · Computer Science 2024-03-13 Nils Graef

Modern large language foundation models (LLM) have now entered the daily lives of millions of users. We ask a natural question whether it is possible to customize LLM for every user or every task. From system and industrial economy…

Machine Learning · Computer Science 2025-04-11 Jianqiao Wangni

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

Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learned on the source task. But an initialization contains…

Machine Learning · Computer Science 2022-05-23 Ravid Shwartz-Ziv , Micah Goldblum , Hossein Souri , Sanyam Kapoor , Chen Zhu , Yann LeCun , Andrew Gordon Wilson

In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources and most of the models are trained from…

Computation and Language · Computer Science 2021-10-15 Cheng Chen , Yichun Yin , Lifeng Shang , Xin Jiang , Yujia Qin , Fengyu Wang , Zhi Wang , Xiao Chen , Zhiyuan Liu , Qun Liu

Normalization layers are a staple in state-of-the-art deep neural network architectures. They are widely believed to stabilize training, enable higher learning rate, accelerate convergence and improve generalization, though the reason for…

Machine Learning · Computer Science 2019-03-13 Hongyi Zhang , Yann N. Dauphin , Tengyu Ma

Deep learning (DL) techniques are gaining more and more attention in the software engineering community. They have been used to support several code-related tasks, such as automatic bug fixing and code comments generation. Recent studies in…

Precise load forecasting in buildings could increase the bill savings potential and facilitate optimized strategies for power generation planning. With the rapid evolution of computer science, data-driven techniques, in particular the Deep…

Machine Learning · Computer Science 2023-01-30 Menna Nawar , Moustafa Shomer , Samy Faddel , Huangjie Gong

A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new task. This paper shows that in such settings, selectively…

Machine Learning · Computer Science 2023-06-07 Yoonho Lee , Annie S. Chen , Fahim Tajwar , Ananya Kumar , Huaxiu Yao , Percy Liang , Chelsea Finn

Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-09-21 Shang-Xuan Zou , Chun-Yen Chen , Jui-Lin Wu , Chun-Nan Chou , Chia-Chin Tsao , Kuan-Chieh Tung , Ting-Wei Lin , Cheng-Lung Sung , Edward Y. Chang

The growing capabilities of transformer models pave the way for solving increasingly complex NLP tasks. A key to supporting application-specific requirements is the ability to fine-tune. However, compiling a fine-tuning dataset tailored to…

Computation and Language · Computer Science 2024-02-13 Solveig Helland , Elena Gavagnin , Alexandre de Spindler

As the landscape of large language models expands, efficiently finetuning for specific tasks becomes increasingly crucial. At the same time, the landscape of parameter-efficient finetuning methods rapidly expands. Consequently,…

Computation and Language · Computer Science 2024-11-05 Tobias Strangmann , Lennart Purucker , Jörg K. H. Franke , Ivo Rapant , Fabio Ferreira , Frank Hutter

Many organizations rely on data from government and third-party sources, and those sources rarely follow the same data formatting. This introduces challenges in integrating data from multiple sources or aligning external sources with…

Databases · Computer Science 2023-12-27 Arash Dargahi Nobari , Davood Rafiei

Transformer is a deep neural network that employs a self-attention mechanism to comprehend the contextual relationships within sequential data. Unlike conventional neural networks or updated versions of Recurrent Neural Networks (RNNs) such…

Machine Learning · Computer Science 2023-06-14 Saidul Islam , Hanae Elmekki , Ahmed Elsebai , Jamal Bentahar , Najat Drawel , Gaith Rjoub , Witold Pedrycz

Pretraining is a common technique in deep learning for increasing performance and reducing training time, with promising experimental results in deep reinforcement learning (RL). However, pretraining requires a relevant dataset for…

Machine Learning · Computer Science 2021-10-07 Saurav Kadavath , Samuel Paradis , Brian Yao

Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit…

Machine Learning · Computer Science 2026-05-19 Zhaiming Shen , Alex Havrilla , Rongjie Lai , Alexander Cloninger , Wenjing Liao

Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in general, freezing the trained feature extractor (the lower…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-10 Shucong Zhang , Cong-Thanh Do , Rama Doddipatla , Erfan Loweimi , Peter Bell , Steve Renals

That neural networks may be pruned to high sparsities and retain high accuracy is well established. Recent research efforts focus on pruning immediately after initialization so as to allow the computational savings afforded by sparsity to…

Machine Learning · Computer Science 2022-01-28 Ilan Price , Jared Tanner

As scaling laws in generative AI push performance, they also simultaneously concentrate the development of these models among actors with large computational resources. With a focus on text-to-image (T2I) generative models, we aim to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Vikash Sehwag , Xianghao Kong , Jingtao Li , Michael Spranger , Lingjuan Lyu