English
Related papers

Related papers: Representation Collapse in Machine Translation Thr…

200 papers

Neural network models and deep models are one of the leading and state of the art models in machine learning. Most successful deep neural models are the ones with many layers which highly increases their number of parameters. Training such…

Machine Learning · Computer Science 2018-07-17 Soufiane Belharbi

The development of diffusion-based generative models over the past decade has largely proceeded independently of progress in representation learning. These diffusion models typically rely on regression-based objectives and generally lack…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Runqian Wang , Kaiming He

While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector…

Computation and Language · Computer Science 2018-01-25 Yonatan Belinkov , Lluís Màrquez , Hassan Sajjad , Nadir Durrani , Fahim Dalvi , James Glass

In our study, we propose a self-supervised neural topic model (NTM) that combines the power of NTMs and regularized self-supervised learning methods to improve performance. NTMs use neural networks to learn latent topics hidden behind the…

Machine Learning · Computer Science 2025-02-27 Weiran Xu , Kengo Hirami , Koji Eguchi

Despite their empirical success, pushing Transformer architectures to extreme depth often leads to a paradoxical failure: representations become increasingly redundant, lose rank, and ultimately collapse. Existing explanations largely…

Machine Learning · Computer Science 2026-01-16 Haoran Su , Chenyu You

Neural collapse ($\mathcal{NC}$) is a phenomenon observed in classification tasks where top-layer representations collapse into their class means, which become equinorm, equiangular and aligned with the classifiers. These behaviours --…

Machine Learning · Computer Science 2024-11-27 Robert Wu , Vardan Papyan

We analyze a new approach to Machine Learning coming from a modification of classical regularization networks by casting the process in the time dimension, leading to a sort of collapse of dimensionality in the problem of learning the model…

Machine Learning · Computer Science 2017-01-05 Marco Gori , Marco Maggini , Alessandro Rossi

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…

Machine Learning · Computer Science 2022-06-29 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…

Machine Learning · Computer Science 2016-02-09 William Whitney

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…

Computation and Language · Computer Science 2021-09-10 Chunting Zhou , Daniel Levy , Xian Li , Marjan Ghazvininejad , Graham Neubig

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Machine Learning · Computer Science 2026-05-20 Zhipeng Zhang

While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear. In this paper, we conduct a detailed diagnostic analysis…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Enguang Wang , Qiang Wang , Yuanchen Wu , Ke Yan , Xinbin Yuan , Shouhong Ding , Xialei Liu , Ming-Ming Cheng

Large models have demonstrated exceptional generalization capabilities in computer vision and natural language processing. Recent efforts have focused on enhancing these models with multimodal processing abilities. However, addressing the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Hao Sun , Yu Song

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…

Computation and Language · Computer Science 2021-09-06 Elena Voita , Rico Sennrich , Ivan Titov

Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with…

We investigate an extension of continuous online learning in recurrent neural network language models. The model keeps a separate vector representation of the current unit of text being processed and adaptively adjusts it after each…

Computation and Language · Computer Science 2017-03-07 Marek Rei

A widely cited result by Dong et al. (2021) showed that Transformers built from self-attention alone, without skip connections or feed-forward layers, suffer from rapid rank collapse: all token representations converge to a single…

Machine Learning · Computer Science 2026-04-28 Giansalvo Cirrincione

In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence.These vectors are generated by parameters…

Computation and Language · Computer Science 2017-08-08 Rongxiang Weng , Shujian Huang , Zaixiang Zheng , Xinyu Dai , Jiajun Chen

Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivariate regression, as employed in imitation learning and other…

Machine Learning · Computer Science 2025-09-30 George Andriopoulos , Zixuan Dong , Li Guo , Zifan Zhao , Keith Ross