English
Related papers

Related papers: Divide et Impera: Multi-Transformer Architectures …

200 papers

Training a Neural Network (NN) with lots of parameters or intricate architectures creates undesired phenomena that complicate the optimization process. To address this issue we propose a first modular approach to NN design, wherein the NN…

Machine Learning · Computer Science 2019-02-26 David Castillo-Bolado , Cayetano Guerra-Artal , Mario Hernandez-Tejera

Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the training data, recent works have explored how LLMs can be used to…

Computation and Language · Computer Science 2025-03-04 Vighnesh Subramaniam , Yilun Du , Joshua B. Tenenbaum , Antonio Torralba , Shuang Li , Igor Mordatch

Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these shortcomings, we…

Computation and Language · Computer Science 2021-01-27 Jonas Pfeiffer , Aishwarya Kamath , Andreas Rücklé , Kyunghyun Cho , Iryna Gurevych

Instruction tuning significantly enhances the performance of large language models (LLMs) across various tasks. However, the procedure to optimizing the mixing of instruction datasets for LLM fine-tuning is still poorly understood. This…

Computation and Language · Computer Science 2024-02-20 Renxi Wang , Haonan Li , Minghao Wu , Yuxia Wang , Xudong Han , Chiyu Zhang , Timothy Baldwin

Performance prediction, the task of estimating a system's performance without performing experiments, allows us to reduce the experimental burden caused by the combinatorial explosion of different datasets, languages, tasks, and models. In…

Computation and Language · Computer Science 2021-02-11 Zihuiwen Ye , Pengfei Liu , Jinlan Fu , Graham Neubig

The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes…

Computation and Language · Computer Science 2020-10-07 Jonas Pfeiffer , Andreas Rücklé , Clifton Poth , Aishwarya Kamath , Ivan Vulić , Sebastian Ruder , Kyunghyun Cho , Iryna Gurevych

Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this…

Computation and Language · Computer Science 2020-10-08 Tu Vu , Tong Wang , Tsendsuren Munkhdalai , Alessandro Sordoni , Adam Trischler , Andrew Mattarella-Micke , Subhransu Maji , Mohit Iyyer

Many recent pattern recognition applications rely on complex distributed architectures in which sensing and computational nodes interact together through a communication network. Deep neural networks (DNNs) play an important role in this…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-03-23 Luigi Capogrosso , Federico Cunico , Michele Lora , Marco Cristani , Franco Fummi , Davide Quaglia

Both encoder-only models (e.g., BERT, RoBERTa) and large language models (LLMs, e.g., Llama3) have been widely used for text classification tasks. However, there is a lack of systematic studies comparing the performance of encoder-based…

Computation and Language · Computer Science 2025-05-13 Hang Zhao , Qile P. Chen , Yijing Barry Zhang , Gang Yang

This position paper proposes a systematic approach towards developing a framework to help select the most effective embedding models for natural language processing (NLP) tasks, addressing the challenge posed by the proliferation of both…

Computation and Language · Computer Science 2024-09-02 Vivek Khetan

Large language models (LLMs), despite their breakthroughs on many challenging benchmark tasks, lean to generate verbose responses and lack the controllability of output complexity, which is usually preferred by human users in practice. In…

Computation and Language · Computer Science 2024-06-25 Dang Nguyen , Jiuhai Chen , Tianyi Zhou

Recent advancements in the NLP field showed that transfer learning helps with achieving state-of-the-art results for new tasks by tuning pre-trained models instead of starting from scratch. Transformers have made a significant improvement…

Computation and Language · Computer Science 2020-09-14 Aysu Ezen-Can

We implement a network-based approach to study expertise in a complex real-world task: operating particle accelerators. Most real-world tasks we learn and perform (e.g., driving cars, operating complex machines, solving mathematical…

Social and Information Networks · Computer Science 2024-12-25 Roussel Rahman , Jane Shtalenkova , Aashwin Ananda Mishra , Wan-Lin Hu

Data pruning, selecting small but impactful subsets, offers a promising way to efficiently scale NLP model training. However, existing methods often involve many different design choices, which have not been systematically studied. This…

Computation and Language · Computer Science 2025-07-08 Yupei Du , Yingjin Song , Hugh Mee Wong , Daniil Ignatev , Albert Gatt , Dong Nguyen

Pre-trained language models can be fine-tuned to solve diverse NLP tasks, including in few-shot settings. Thus fine-tuning allows the model to quickly pick up task-specific ``skills,'' but there has been limited study of where these…

Computation and Language · Computer Science 2023-07-04 Abhishek Panigrahi , Nikunj Saunshi , Haoyu Zhao , Sanjeev Arora

We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We…

Computer Vision and Pattern Recognition · Computer Science 2017-11-02 Miquel Martí , Atsuto Maki

Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and…

Computation and Language · Computer Science 2025-09-08 Faruk Alpay , Taylan Alpay

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Christian Bohn , Thomas Kurbiel , Klaus Friedrichs , Hasan Tercan , Tobias Meisen

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…

Patent analysis and mining are time-consuming and costly processes for companies, but nevertheless essential if they are willing to remain competitive. To face the overload induced by numerous patents, the idea is to automatically filter…

Computation and Language · Computer Science 2021-07-05 Théo Ding , Walter Vermeiren , Sylvie Ranwez , Binbin Xu