English
Related papers

Related papers: Arbitrary-Length Generalization for Addition in a …

200 papers

Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized…

Machine Learning · Computer Science 2024-11-01 Arihan Yadav , Alan McMillan

Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially…

Computation and Language · Computer Science 2019-10-29 Jiatao Gu , Changhan Wang , Jake Zhao

Reversibility in artificial neural networks allows us to retrieve the input given an output. We present feature alignment, a method for approximating reversibility in arbitrary neural networks. We train a network by minimizing the distance…

Machine Learning · Computer Science 2023-01-31 Tiago de Souza Farias , Jonas Maziero

Mathematical reasoning is one of the most impressive achievements of human intellect but remains a formidable challenge for artificial intelligence systems. In this work we explore whether modern deep learning architectures can learn to…

Machine Learning · Computer Science 2022-07-07 Samuel Cognolato , Alberto Testolin

Autoregressive models, such as the GPT family, use a fixed order, usually left-to-right, to generate sequences. However, this is not a necessity. In this paper, we challenge this assumption and show that by simply adding a positional…

Machine Learning · Computer Science 2024-07-02 Arnaud Pannatier , Evann Courdier , François Fleuret

Despite the crucial importance of accelerating text generation in large language models (LLMs) for efficiently producing content, the sequential nature of this process often leads to high inference latency, posing challenges for real-time…

Computation and Language · Computer Science 2024-05-27 Mahsa Khoshnoodi , Vinija Jain , Mingye Gao , Malavika Srikanth , Aman Chadha

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color…

Computer Vision and Pattern Recognition · Computer Science 2019-09-24 Saypraseuth Mounsaveng , David Vazquez , Ismail Ben Ayed , Marco Pedersoli

Length generalization refers to the ability to extrapolate from short training sequences to long test sequences and is a challenge for current large language models. While prior work has proposed some architecture or data format changes to…

Machine Learning · Computer Science 2024-07-04 Kaiying Hou , David Brandfonbrener , Sham Kakade , Samy Jelassi , Eran Malach

Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Yang Ye , Junliang Guo , Haoyu Wu , Tianyu He , Tim Pearce , Tabish Rashid , Katja Hofmann , Jiang Bian

Self-attention has emerged as a vital component of state-of-the-art sequence-to-sequence models for natural language processing in recent years, brought to the forefront by pre-trained bi-directional Transformer models. Its effectiveness is…

Machine Learning · Computer Science 2020-06-23 Hyoungwook Nam , Seung Byum Seo , Vikram Sharma Mailthody , Noor Michael , Lan Li

This technical note is an ancillary material for our research paper (Itoh and Parente, 2019). We discuss an alternating direction method of multipliers with generalized augmented terms (ADMM-GAT) and introduce a generalized residual balance…

Optimization and Control · Mathematics 2019-09-19 Yuki Itoh , Mario Parente

Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. However, the initial quantization breaks the continuous…

Machine Learning · Computer Science 2025-12-09 Ziyad Sheebaelhamd , Michael Tschannen , Michael Muehlebach , Claire Vernade

Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the…

Computer Vision and Pattern Recognition · Computer Science 2019-10-24 Atsuhiro Noguchi , Tatsuya Harada

Large language models often struggle with length generalization and solving complex problem instances beyond their training distribution. We present a self-improvement approach where models iteratively generate and learn from their own…

Machine Learning · Computer Science 2025-02-14 Nayoung Lee , Ziyang Cai , Avi Schwarzschild , Kangwook Lee , Dimitris Papailiopoulos

Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency. To mitigate this inefficiency, we present Bi-directional Tuning for lossless…

Computation and Language · Computer Science 2025-07-02 Feng Lin , Hanling Yi , Hongbin Li , Yifan Yang , Xiaotian Yu , Guangming Lu , Rong Xiao

In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach first applies a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Qikai Yang , Cheng Ji , Huaiying Luo , Panfeng Li , Zhicheng Ding

We present Autoregressive Representation Alignment (ARRA), a new training framework that unlocks global-coherent text-to-image generation in autoregressive LLMs without architectural modifications. Different from prior works that require…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Xing Xie , Jiawei Liu , Ziyue Lin , Huijie Fan , Zhi Han , Yandong Tang , Liangqiong Qu

In many cases of machine learning, research suggests that the development of training data might have a higher relevance than the choice and modelling of classifiers themselves. Thus, data augmentation methods have been developed to improve…

Computation and Language · Computer Science 2022-07-25 Markus Bayer , Marc-André Kaufhold , Björn Buchhold , Marcel Keller , Jörg Dallmeyer , Christian Reuter

Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Traditional approaches focused on augmentation using rotation,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Fazle Rahat , M Shifat Hossain , Md Rubel Ahmed , Sumit Kumar Jha , Rickard Ewetz