English
Related papers

Related papers: Conditional Attribute Estimation with Autoregressi…

200 papers

In this paper we propose a general framework for learning distributed representations of attributes: characteristics of text whose representations can be jointly learned with word embeddings. Attributes can correspond to document indicators…

Machine Learning · Computer Science 2014-06-12 Ryan Kiros , Richard S. Zemel , Ruslan Salakhutdinov

Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently,…

Machine Learning · Computer Science 2020-01-10 Zhiqing Sun , Zhuohan Li , Haoqing Wang , Zi Lin , Di He , Zhi-Hong Deng

Causal decoder-only transformer models used for generative language modelling, such as Generative Pre-trained Transformers (GPT), are trained to predict the next token in a sequence based only on its previous tokens. Despite this simple…

Computation and Language · Computer Science 2024-10-25 Nicholas Walker

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive…

Computation and Language · Computer Science 2026-04-07 Oshri Naparstek

Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…

Computation and Language · Computer Science 2025-03-13 Falko Helm , Nico Daheim , Iryna Gurevych

To predict the next token, autoregressive models ordinarily examine the past. Could they also benefit from also examining hypothetical futures? We consider a novel Transformer-based autoregressive architecture that estimates the next-token…

Computation and Language · Computer Science 2023-05-23 Li Du , Hongyuan Mei , Jason Eisner

In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Deng Li , Aming Wu , Yang Li , Yaowei Wang , Yahong Han

Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability in learning symbolic…

Computation and Language · Computer Science 2021-10-01 Yichen Jiang , Mohit Bansal

We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed. Drawing on temporal-difference learning from reinforcement learning, we identify a…

Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…

Computation and Language · Computer Science 2021-03-23 Chen Liang , Haoming Jiang , Xiaodong Liu , Pengcheng He , Weizhu Chen , Jianfeng Gao , Tuo Zhao

Visual saliency patterns are the result of a variety of factors aside from the image being parsed, however existing approaches have ignored these. To address this limitation, we propose a novel saliency estimation model which leverages the…

Computer Vision and Pattern Recognition · Computer Science 2018-03-12 Tharindu Fernando , Simon Denman , Sridha Sridharan , Clinton Fookes

Despite significant progress of generative models in the natural sciences, their controllability remains challenging. One fundamentally missing aspect of molecular or protein generative models is an inductive bias that can reflect…

Machine Learning · Computer Science 2023-08-25 Jannis Born , Matteo Manica

Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework…

Machine Learning · Computer Science 2020-10-12 Sameera Ramasinghe , Kanchana Ranasinghe , Salman Khan , Nick Barnes , Stephen Gould

Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language…

Machine Learning · Computer Science 2026-05-25 Giang Nguyen

Next-token prediction is conventionally done using decoder-only Transformers with causal attention, as this approach allows for efficient reuse of keys and values. What if we were not compute-limited, should we still use decoder-only…

Machine Learning · Computer Science 2025-02-05 Ethan Ewer , Daewon Chae , Thomas Zeng , Jinkyu Kim , Kangwook Lee

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-26 Jing Shi , Xuankai Chang , Pengcheng Guo , Shinji Watanabe , Yusuke Fujita , Jiaming Xu , Bo Xu , Lei Xie

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

Computation and Language · Computer Science 2024-06-04 Wenhong Zhu , Hongkun Hao , Zhiwei He , Yiming Ai , Rui Wang

We propose a novel conditional diffusion model for contextual portfolio optimization that learns the cross-sectional distribution of next-day stock returns conditioned on high-dimensional asset-specific factors. Our model leverages a…

Portfolio Management · Quantitative Finance 2026-04-17 Xuefeng Gao , Mengying He , Xuedong He

In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation. Transformers have become the standard architecture…

Information Theory · Computer Science 2024-05-07 Alessio Devoto , Simone Petruzzi , Jary Pomponi , Paolo Di Lorenzo , Simone Scardapane

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Machine Learning · Computer Science 2021-08-19 Radostin Cholakov , Todor Kolev