English
Related papers

Related papers: Generative Semantic HARQ: Latent-Space Text Retran…

200 papers

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even…

Machine Learning · Computer Science 2018-01-31 Łukasz Kaiser , Samy Bengio

Recently, semantic communication has been investigated to boost the performance of end-to-end image transmission systems. However, existing semantic approaches are generally based on deep learning and belong to lossy transmission.…

Signal Processing · Electrical Eng. & Systems 2023-08-23 Guangyi Zhang , Qiyu Hu , Yunlong Cai , Guanding Yu

Semantic communication (SemCom) significantly improves inter-vehicle interactions in intelligent connected vehicles (ICVs) within limited wireless spectrum. However, the open nature of wireless communications introduces eavesdropping risks.…

Cryptography and Security · Computer Science 2025-02-25 Bizhu Wang , Zhiqiang Bian , Yue Chen , Xiaodong Xu , Chen Sun , Wenqi Zhang , Ping Zhang

Hybrid Automatic Repeat Request (HARQ) schemes typically allocate all available resources to retransmit failed packets to ensure reliability. However, under stringent delay constraints, these schemes often exhibit low spectral efficiency…

Signal Processing · Electrical Eng. & Systems 2026-03-05 Hongling Huang , Jintao Wang , Zheng Shi , Xu Wang , Guanghua Yang , Shaodan Ma , Haichuan Ding

Reliable image transmission over wireless channels is particularly challenging at extremely low transmission rates, where conventional compression and channel coding schemes fail to preserve adequate visual quality. To address this issue,…

Information Theory · Computer Science 2025-10-27 Shengkang Chen , Tong Wu , Zhiyong Chen , Feng Yang , Meixia Tao , Wenjun Zhang

Mechanisms for data recovery and packet reliability are essential components of the upcoming 6th generation (6G) communication system. In this paper, we evaluate the interaction between a fast hybrid automatic repeat request (HARQ) scheme,…

Signal Processing · Electrical Eng. & Systems 2024-04-12 Uyoata E. Uyoata , Abolfazl Amiri , Enric Juan , Guillermo Pocovi , Pilar Andres-Maldonado , Klaus I. Pedersen , Troels Kolding

The rapid progress of artificial intelligence (AI) and computer vision (CV) has facilitated the development of computation-intensive applications like Visual Question Answering (VQA), which integrates visual perception and natural language…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Sige Liu , Nan Li , Yansha Deng , Tony Q. S. Quek

Despite the rise of token communication (TokCom) as a new paradigm beyond traditional bit communication, existing approaches have primarily adopted artificial intelligence (AI)-centric designs that rely on semantic recovery via large…

Signal Processing · Electrical Eng. & Systems 2026-05-01 Jihoon Lee , Seungeun Oh , Jihong Park , Seong-Lyun Kim , Seung-Woo Ko

6G wireless networks will integrate communication, computing, localization, and sensing capabilities while meeting the needs of high reliability and trustworthiness. In this paper, we develop similar techniques as those used by…

Signal Processing · Electrical Eng. & Systems 2024-04-17 Georgios Mylonopoulos , Behrooz Makki , Stefano Buzzi , Gábor Fodor

Automatic repeat request (ARQ) is widely used in modern communication systems to improve transmission reliability. In conventional ARQ protocols developed for systems with energy-unconstrained receivers, an…

Information Theory · Computer Science 2016-11-17 Yuyi Mao , Jun Zhang , Khaled B. Letaief

Symbols are shared, but perception is private. We study emergent communication between heterogeneous visual agents through decentralized learning, asking what visual information can become shareable when agents have different visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Mikako Ochiai , Masatoshi Nagano , Tadahiro Taniguchi

Semantic image synthesis enables control over unconditional image generation by allowing guidance on what is being generated. We conditionally synthesize the latent space from a vector quantized model (VQ-model) pre-trained to autoencode…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Stephan Alaniz , Thomas Hummel , Zeynep Akata

Directly sending audio signals from a transmitter to a receiver across a noisy channel may absorb consistent bandwidth and be prone to errors when trying to recover the transmitted bits. On the contrary, the recent semantic communication…

Sound · Computer Science 2023-09-15 Eleonora Grassucci , Christian Marinoni , Andrea Rodriguez , Danilo Comminiello

Recent advances in semantic communication (SC) have introduced neural network (NN)-based transceivers that convey semantic representation (SR) of signals such as images. However, these NNs are trained over diverse image distributions and…

Signal Processing · Electrical Eng. & Systems 2025-07-24 Hyelin Nam , Jihong Park , Jinho Choi , Seong-Lyun Kim

Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, decoding a random latent vector from the prior usually does not produce meaningful data, at least…

Machine Learning · Computer Science 2025-07-23 Alejandro Ascarate , Leo Lebrat , Rodrigo Santa Cruz , Clinton Fookes , Olivier Salvado

With the emergence of diverse and massive data in the upcoming sixth-generation (6G) networks, the task-agnostic semantic communication system is regarded to provide robust intelligent services. In this paper, we propose a task-agnostic…

Information Theory · Computer Science 2025-09-16 Shiyao Jiang , Jian Jiao , Xingjian Zhang , Ye Wang , Dusit Niyato , Qinyu Zhang

Underwater wireless communications face significant challenges due to propagation constraints, limiting the effectiveness of traditional radio and optical technologies. Long-range acoustic communications support distances up to a few…

Networking and Internet Architecture · Computer Science 2025-07-01 João Pedro Loureiro , Patrícia Delgado , Tomás Feliciano Ribeiro , Filipe B. Teixeira , Rui Campos

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Machine Learning · Computer Science 2020-07-08 Tianxiao Shen , Jonas Mueller , Regina Barzilay , Tommi Jaakkola

Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for applications such as telepresence, augmented reality, and remote sensing. Recent…

Machine Learning · Computer Science 2025-12-18 Matin Mortaheb , Erciyes Karakaya , Sennur Ulukus

Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue. In an effort to model this kind of generative process, we propose a neural…

Computation and Language · Computer Science 2016-06-15 Iulian Vlad Serban , Alessandro Sordoni , Ryan Lowe , Laurent Charlin , Joelle Pineau , Aaron Courville , Yoshua Bengio