English
Related papers

Related papers: Multinomial Loss on Held-out Data for the Sparse N…

200 papers

Transformer architectures, and their attention mechanisms in particular, form the foundation of modern large language models. While transformer models are widely believed to operate in high-dimensional hidden spaces, we show that attention…

Machine Learning · Computer Science 2026-02-12 Junxuan Wang , Xuyang Ge , Wentao Shu , Zhengfu He , Xipeng Qiu

Generalization remains a major problem in supervised learning of single-channel speech enhancement. In this work, we propose learnable loss mixup (LLM), a simple and effortless training diagram, to improve the generalization of deep…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-01 Oscar Chang , Dung N. Tran , Kazuhito Koishida

Deep neural state-space models (SSMs) provide a powerful tool for modeling dynamical systems solely using operational data. Typically, neural SSMs are trained using data collected from the actual system under consideration, despite the…

Machine Learning · Computer Science 2022-11-16 Ankush Chakrabarty , Gordon Wichern , Christopher R. Laughman

Language models often show little to no improvement (i.e., "saturation") when trained via vanilla supervised fine-tuning (SFT) on data similar to what they saw in their training set (e.g., MATH). We introduce a new fine-tuning strategy,…

Machine Learning · Computer Science 2025-10-14 Yinghui He , Abhishek Panigrahi , Yong Lin , Sanjeev Arora

Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing…

Machine Learning · Computer Science 2026-03-05 Paulius Rauba , Mihaela van der Schaar

The quality of instruction data directly affects the performance of fine-tuned Large Language Models (LLMs). Previously, \cite{li2023one} proposed \texttt{NUGGETS}, which identifies and selects high-quality quality data from a large dataset…

Computation and Language · Computer Science 2024-12-16 Shiwen Ni , Haihong Wu , Di Yang , Qiang Qu , Hamid Alinejad-Rokny , Min Yang

Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM), and Memory Networks which contain memory are popularly used to learn patterns in sequential data. Sequential data has long sequences that hold relationships. RNN can…

Computation and Language · Computer Science 2019-04-22 Anupiya Nugaliyadde , Kok Wai Wong , Ferdous Sohel , Hong Xie

Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…

Computation and Language · Computer Science 2007-05-23 Rens Bod

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired…

Computation and Language · Computer Science 2025-10-30 Chunyuan Deng , Ruidi Chang , Hanjie Chen

The hidden Markov model (HMM) is a fundamental tool for sequence modeling that cleanly separates the hidden state from the emission structure. However, this separation makes it difficult to fit HMMs to large datasets in modern NLP, and they…

Computation and Language · Computer Science 2020-11-10 Justin T. Chiu , Alexander M. Rush

Using a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data is available for one…

Computation and Language · Computer Science 2020-10-07 Alexandra Chronopoulou , Dario Stojanovski , Alexander Fraser

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Machine Learning · Computer Science 2025-09-22 Shiwan Zhao , Xuyang Zhao , Jiaming Zhou , Aobo Kong , Qicheng Li , Yong Qin

Large and sparse feed-forward layers (S-FFN) such as Mixture-of-Experts (MoE) have proven effective in scaling up Transformers model size for \textit{pretraining} large language models. By only activating part of the FFN parameters…

Computation and Language · Computer Science 2023-10-25 Zeyu Leo Liu , Tim Dettmers , Xi Victoria Lin , Veselin Stoyanov , Xian Li

Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…

Machine Learning · Computer Science 2024-11-13 Kristian Georgiev , Roy Rinberg , Sung Min Park , Shivam Garg , Andrew Ilyas , Aleksander Madry , Seth Neel

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

Computer Vision and Pattern Recognition · Computer Science 2020-08-31 Andrea Burns , Donghyun Kim , Derry Wijaya , Kate Saenko , Bryan A. Plummer

There is a growing interest in the learning-to-learn paradigm, also known as meta-learning, where models infer on new tasks using a few training examples. Recently, meta-learning based methods have been widely used in few-shot…

Machine Learning · Computer Science 2024-03-13 Anish Madan , Ranjitha Prasad

The sample selection approach is very popular in learning with noisy labels. As deep networks learn pattern first, prior methods built on sample selection share a similar training procedure: the small-loss examples can be regarded as clean…

Machine Learning · Computer Science 2023-09-06 Xiaobo Xia , Pengqian Lu , Chen Gong , Bo Han , Jun Yu , Jun Yu , Tongliang Liu

As large language models (LLMs) are widely applied across various fields, model compression has become increasingly crucial for reducing costs and improving inference efficiency. Post-training pruning is a promising method that does not…

Computation and Language · Computer Science 2025-07-01 Yixin Ji , Yang Xiang , Juntao Li , Qingrong Xia , Ping Li , Xinyu Duan , Zhefeng Wang , Min Zhang

Interpretable machine learning has demonstrated impressive performance while preserving explainability. In particular, neural additive models (NAM) offer the interpretability to the black-box deep learning and achieve state-of-the-art…

Machine Learning · Statistics 2022-02-28 Shiyun Xu , Zhiqi Bu , Pratik Chaudhari , Ian J. Barnett

State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expressivity, as measured…