English
Related papers

Related papers: Decoding Partial Differential Equations: Cross-Mod…

200 papers

Recently, the ever-increasing demand for bandwidth in multi-modal communication systems requires a paradigm shift. Powered by deep learning, semantic communications are applied to multi-modal scenarios to boost communication efficiency and…

Signal Processing · Electrical Eng. & Systems 2023-05-19 Yangshuo He , Guanding Yu , Yunlong Cai

Cross-model retrieval has emerged as one of the most important upgrades for text-only search engines (SE). Recently, with powerful representation for pairwise text-image inputs via early interaction, the accuracy of vision-language (VL)…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Lisai Zhang , Hongfa Wu , Qingcai Chen , Yimeng Deng , Zhonghua Li , Dejiang Kong , Zhao Cao , Joanna Siebert , Yunpeng Han

Recently, using large pretrained Transformer models for transfer learning tasks has evolved to the point where they have become one of the flagship trends in the Natural Language Processing (NLP) community, giving rise to various outlooks…

Computation and Language · Computer Science 2024-05-24 Alejo Lopez-Avila , Víctor Suárez-Paniagua

Generally, the decoder-only large language models (LLMs) are adapted to context-aware neural machine translation (NMT) in a concatenating way, where LLMs take the concatenation of the source sentence (i.e., intra-sentence context) and the…

Computation and Language · Computer Science 2024-09-24 Xinglin Lyu , Junhui Li , Yanqing Zhao , Min Zhang , Daimeng Wei , Shimin Tao , Hao Yang , Min Zhang

Metaphor requires a language model to resolve a token whose contextual meaning diverges from its basic literal sense. Understanding how transformer models organize this reinterpretation across depth remains an open problem in mechanistic…

Computation and Language · Computer Science 2026-05-21 Lawhori Chakrabarti , Jennifer Johnson-Leung , Bert Baumgaertner , Aleksandar Vakanski , Min Xian , Boyu Zhang

The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\textit{Franken-Adapter}$, a modular…

Computation and Language · Computer Science 2025-02-13 Fan Jiang , Honglin Yu , Grace Chung , Trevor Cohn

Multi-modal affect recognition models leverage complementary information in different modalities to outperform their uni-modal counterparts. However, due to the unavailability of modality-specific sensors or data, multi-modal models may not…

Image and Video Processing · Electrical Eng. & Systems 2021-08-03 Vandana Rajan , Alessio Brutti , Andrea Cavallaro

Error correction codes are a crucial part of the physical communication layer, ensuring the reliable transfer of data over noisy channels. The design of optimal linear block codes capable of being efficiently decoded is of major concern,…

Information Theory · Computer Science 2024-05-08 Yoni Choukroun , Lior Wolf

Recent multimodal large language models (MLLMs) increasingly integrate multiple vision encoders to improve performance on various benchmarks, assuming that diverse pretraining objectives yield complementary visual signals. However, we show…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Yizhou Wang , Song Mao , Yang Chen , Yufan Shen , Yinqiao Yan , Pinlong Cai , Ding Wang , Guohang Yan , Zhi Yu , Xuming Hu , Botian Shi

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

Domain-specific adaptation is critical to maximizing the performance of pre-trained language models (PLMs) on one or multiple targeted tasks, especially under resource-constrained use cases, such as edge devices. However, existing methods…

Computation and Language · Computer Science 2024-10-25 Peter Schafhalter , Shun Liao , Yanqi Zhou , Chih-Kuan Yeh , Arun Kandoor , James Laudon

Decoder-only transformers lead to a step-change in capability of large language models. However, opinions are mixed as to whether they are really planning or reasoning. A path to making progress in this direction is to study the model's…

Machine Learning · Computer Science 2025-02-14 Andrew Cohen , Andrey Gromov , Kaiyu Yang , Yuandong Tian

Data-efficient neural decoding is a central challenge for speech brain-computer interfaces. We present the first demonstration of transfer learning and cross-task decoding for MEG-based speech models spanning perception and production. We…

Machine Learning · Computer Science 2026-02-23 Xabier de Zuazo , Vincenzo Verbeni , Eva Navas , Ibon Saratxaga , Mathieu Bourguignon , Nicola Molinaro

We give a novel logical characterization of encoder-decoder transformers, the foundational architecture for LLMs that also sees use in various settings that benefit from cross-attention. We study such transformers over text in the practical…

Logic in Computer Science · Computer Science 2026-05-11 Veeti Ahvonen , Damian Heiman , Antti Kuusisto , Miguel Moreno , Matias Selin

Encoder-decoder models have achieved remarkable success in speech and text tasks, yet efficiently adapting these models to diverse uni/multi-modal scenarios remains an open challenge. In this paper, we propose Whisper-UT, a unified and…

We present an empirical study of scaling properties of encoder-decoder Transformer models used in neural machine translation (NMT). We show that cross-entropy loss as a function of model size follows a certain scaling law. Specifically (i)…

Machine Learning · Computer Science 2021-09-17 Behrooz Ghorbani , Orhan Firat , Markus Freitag , Ankur Bapna , Maxim Krikun , Xavier Garcia , Ciprian Chelba , Colin Cherry

Electroencephalography (EEG) decoding is a challenging task due to the limited availability of labelled data. While transfer learning is a promising technique to address this challenge, it assumes that transferable data domains and task are…

Signal Processing · Electrical Eng. & Systems 2023-08-07 Bruno Aristimunha , Raphael Y. de Camargo , Walter H. Lopez Pinaya , Sylvain Chevallier , Alexandre Gramfort , Cedric Rommel

Learning high-quality text representations is fundamental to a wide range of NLP tasks. While encoder pretraining has traditionally relied on Masked Language Modeling (MLM), recent evidence suggests that decoder models pretrained with…

When adapting an encoder to a new domain, the standard approach is to continue training with Masked Language Modeling (MLM). We show that temporarily switching to Causal Language Modeling (CLM) followed by a short MLM decay improves…

Computation and Language · Computer Science 2026-05-13 Rian Touchent , Eric de la Clergerie

Pre-trained encoders are widely employed in dense prediction tasks for their capability to effectively extract visual features from images. The decoder subsequently processes these features to generate pixel-level predictions. However, due…

Machine Learning · Computer Science 2025-03-18 Chao Ning , Wanshui Gan , Weihao Xuan , Naoto Yokoya