English
Related papers

Related papers: Efficient Encoder-Decoder Transformer Decoding for…

200 papers

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…

Computation and Language · Computer Science 2025-01-31 Mohamed Elfeki , Rui Liu , Chad Voegele

Code pre-trained models (CodePTMs) have recently demonstrated a solid capacity to process various software intelligence tasks, e.g., code clone detection, code translation, and code summarization. The current mainstream method that deploys…

Software Engineering · Computer Science 2024-05-10 Qiushi Sun , Nuo Chen , Jianing Wang , Xiang Li , Ming Gao

The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach…

Computation and Language · Computer Science 2021-07-08 Belen Alastruey , Gerard I. Gállego , Marta R. Costa-jussà

Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent works proposed variations of positional encodings with…

Computation and Language · Computer Science 2021-11-04 Pu-Chin Chen , Henry Tsai , Srinadh Bhojanapalli , Hyung Won Chung , Yin-Wen Chang , Chun-Sung Ferng

With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting. To adapt PTMs with model parameters frozen, most current…

Computation and Language · Computer Science 2023-05-25 Ganqu Cui , Wentao Li , Ning Ding , Longtao Huang , Zhiyuan Liu , Maosong Sun

Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Naresh Kumar Gurulingan , Elahe Arani , Bahram Zonooz

Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity. However, the extra latency and memory costs introduced by this approach may make it…

Computation and Language · Computer Science 2022-06-07 Xiang Kong , Adithya Renduchintala , James Cross , Yuqing Tang , Jiatao Gu , Xian Li

Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs, early, middle, and late layers may serve distinct roles:…

Computation and Language · Computer Science 2025-10-15 Xuan Luo , Weizhi Wang , Xifeng Yan

Recent Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstream tasks without accessing their parameters and gradients,…

Computation and Language · Computer Science 2025-06-03 Zifeng Cheng , Zhaoling Chen , Zhiwei Jiang , Yafeng Yin , Cong Wang , Shiping Ge , Qing Gu

Autoregressive language models can often identify parallel subproblems, but standard decoding exposes only a single left-to-right output interface. External orchestration methods can launch multiple prompts concurrently, yet they provide no…

Artificial Intelligence · Computer Science 2026-03-10 Logan Robbins

Generative recommendation models employing Semantic IDs (SIDs) exhibit strong potential, yet their practical deployment is bottlenecked by the high inference latency of beam-expanded autoregressive decoding. In this work, we identify that…

Information Retrieval · Computer Science 2026-05-14 Zitian Guo , Yupeng Hou , Clark Mingxuan Ju , Neil Shah , Julian McAuley

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

We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Ronghang Hu , Amanpreet Singh

Surface crack segmentation poses a challenging computer vision task as background, shape, colour and size of cracks vary. In this work we propose optimized deep encoder-decoder methods consisting of a combination of techniques which yield…

Computer Vision and Pattern Recognition · Computer Science 2021-08-27 Jacob König , Mark Jenkins , Mike Mannion , Peter Barrie , Gordon Morison

Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…

Neural and Evolutionary Computing · Computer Science 2018-06-04 Shuai Tang , Hailin Jin , Chen Fang , Zhaowen Wang , Virginia R. de Sa

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Neural and Evolutionary Computing · Computer Science 2019-11-07 Noam Shazeer

While large language models are primarily used on natural language tasks, they have also shown great promise when adapted to new modalities, e.g., for scientific machine learning tasks. Most proposed approaches for such cross-modal…

Machine Learning · Computer Science 2026-03-09 Paloma García-de-Herreros , Philipp Slusallek , Dietrich Klakow , Vagrant Gautam

This paper presents "Predictive Pipelined Decoding (PPD)," an approach that speeds up greedy decoding in Large Language Models (LLMs) while maintaining the exact same output as the original decoding. Unlike conventional strategies, PPD…

Computation and Language · Computer Science 2024-07-30 Seongjun Yang , Gibbeum Lee , Jaewoong Cho , Dimitris Papailiopoulos , Kangwook Lee

This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facilitate faster recognition. We provide a comprehensive comparison of techniques to integrate…

Computation and Language · Computer Science 2026-04-30 Albert Zeyer , Tim Posielek , Ralf Schlüter , Hermann Ney

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Yangyang Xu , Yibo Yang , Lefei Zhang