English
Related papers

Related papers: Partially Randomizing Transformer Weights for Dial…

200 papers

We introduce ElastiFormer, a post-training technique that adapts pretrained Transformer models into an elastic counterpart with variable inference time compute. ElastiFormer introduces small routing modules (as low as .00006% additional…

Machine Learning · Computer Science 2024-11-26 Junzhang Liu , Tingkai Liu , Yueyuan Sui , Stephen Xia

Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low-level features can become harder to recover as the residual stream is repeatedly…

Machine Learning · Computer Science 2026-05-07 Skye Gunasekaran , Téa Wright , Rui-Jie Zhu , Jason Eshraghian

With the increasing implementation of machine learning models on edge or Internet-of-Things (IoT) devices, deploying advanced models on resource-constrained IoT devices remains challenging. Transformer models, a currently dominant neural…

Sound · Computer Science 2024-11-15 Zixing Zhang , Zhongren Dong , Weixiang Xu , Jing Han

Transformer models have revolutionized natural language processing with their unparalleled ability to grasp complex contextual relationships. However, the vast number of parameters in these models has raised concerns regarding computational…

Machine Learning · Computer Science 2023-10-10 Sia Gholami , Marwan Omar

Neural models of dialog rely on generalized latent representations of language. This paper introduces a novel training procedure which explicitly learns multiple representations of language at several levels of granularity. The…

Computation and Language · Computer Science 2019-08-28 Shikib Mehri , Maxine Eskenazi

Open-domain retrieval-based dialogue systems require a considerable amount of training data to learn their parameters. However, in practice, the negative samples of training data are usually selected from an unannotated conversation data…

Computation and Language · Computer Science 2020-02-19 Kun Zhou , Wayne Xin Zhao , Yutao Zhu , Ji-Rong Wen , Jingsong Yu

The training of modern large-language models requires an increasingly amount of computation power and time. Even smaller variants, such as small-language models (SLMs), take several days to train in the best-case scenarios, often requiring…

Computation and Language · Computer Science 2025-08-11 Joonas Tapaninaho , Mourad Oussala

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…

Computation and Language · Computer Science 2021-12-17 Yadong Xi , Jiashu Pu , Xiaoxi Mao

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

We present an empirical investigation of pre-trained Transformer-based auto-regressive language models for the task of open-domain dialogue generation. Training paradigm of pre-training and fine-tuning is employed to conduct the parameter…

Computation and Language · Computer Science 2020-03-10 Piji Li

Pre-training large language models (LLMs) necessitates enormous diverse textual corpora, making effective data selection a key challenge for balancing computational resources and model performance. Current methodologies primarily emphasize…

Computation and Language · Computer Science 2025-04-22 Xiaoxuan Zhu , Zhouhong Gu , Baiqian Wu , Suhang Zheng , Tao Wang , Tianyu Li , Hongwei Feng , Yanghua Xiao

In dialogue transcription pipelines, Large Language Models (LLMs) are frequently employed in post-processing to improve grammar, punctuation, and readability. We explore a complementary post-processing step: enriching transcribed dialogues…

Computation and Language · Computer Science 2025-09-10 Thomas Thebaud , Yen-Ju Lu , Matthew Wiesner , Peter Viechnicki , Najim Dehak

For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various…

Computation and Language · Computer Science 2021-01-01 Baolin Peng , Chunyuan Li , Zhu Zhang , Chenguang Zhu , Jinchao Li , Jianfeng Gao

Beamformers often trade off white noise gain against the ability to suppress interferers. With distributed microphone arrays, this trade-off becomes crucial as different arrays capture vastly different magnitude and phase differences for…

Sound · Computer Science 2025-07-09 Manan Mittal , Ryan M. Corey , Andrew C. Singer

Fine-tuning pre-trained language models improves the quality of commercial reply suggestion systems, but at the cost of unsustainable training times. Popular training time reduction approaches are resource intensive, thus we explore…

Computation and Language · Computer Science 2021-11-30 Vaishnavi Shrivastava , Radhika Gaonkar , Shashank Gupta , Abhishek Jha

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Machine Learning · Computer Science 2025-09-24 Duke Nguyen , Du Yin , Aditya Joshi , Flora Salim

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

Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length…

Computation and Language · Computer Science 2023-10-19 Sara Papi , Marco Gaido , Matteo Negri , Marco Turchi

Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning,…

Computation and Language · Computer Science 2019-08-06 Paweł Budzianowski , Ivan Vulić

With the resurgent interest in building open-domain dialogue systems, the dialogue generation task has attracted increasing attention over the past few years. This task is usually formulated as a conditional generation problem, which aims…

Computation and Language · Computer Science 2024-10-29 Haoyu Song , Wei-Nan Zhang , Kaiyan Zhang , Ting Liu