As NNs permeate various scientific and industrial domains, understanding the universality and reusability of their representations becomes crucial. At their core, these networks create intermediate neural representations, indicated as latent spaces, of the input data and subsequently leverage them to perform specific downstream tasks. This dissertation focuses on the universality and reusability of neural representations. Do the latent representations crafted by a NN remain exclusive to a particular trained instance, or can they generalize across models, adapting to factors such as randomness during training, model architecture, or even data domain? This adaptive quality introduces the notion of Latent Communication -- a phenomenon that describes when representations can be unified or reused across neural spaces. A salient observation from our research is the emergence of similarities in latent representations, even when these originate from distinct or seemingly unrelated NNs. By exploiting a partial correspondence between the two data distributions that establishes a semantic link, we found that these representations can either be projected into a universal representation, coined as Relative Representation, or be directly translated from one space to another. Latent Communication allows for a bridge between independently trained NN, irrespective of their training regimen, architecture, or the data modality they were trained on -- as long as the data semantic content stays the same (e.g., images and their captions). This holds true for both generation, classification and retrieval downstream tasks; in supervised, weakly supervised, and unsupervised settings; and spans various data modalities including images, text, audio, and graphs -- showcasing the universality of the Latent Communication phenomenon. [...]
Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
University of Waterloo（多伦多大学）；Perimeter Institute for Theoretical Physics（理论物理研究所）；Homes Plus Magazine Inc.（Homes Plus 杂志公司）；University of Toronto（多伦多大学）
Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
Beijing University of Posts and Telecommunications（北京邮电大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Princeton University（普林斯顿大学）；The University of Edinburgh（爱丁堡大学）；Virginia Tech（弗吉尼亚理工大学）；Huawei France R & D（华为法国研发中心）
Enabling Agents to Communicate Entirely in Latent Space
State Key Lab of CAD&CG（CAD与CG国家重点实验室）；Future Living Lab of Alibaba（阿里巴巴未来生活实验室）；Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江医学影像人工智能重点实验室）；Shanghai Jiao Tong University（上海交通大学）
Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises
School of Electrical and Electronic Engineering, Huazhong University of Science and Technology（华中科技大学电气与电子工程学院）；Cornell University（康奈尔大学）；Lassonde School of Engineering, York University（约克大学拉桑德工程学院）
Bridging the Communication Gap: Artificial Agents Learning Sign Language through Imitation
University of Manchester（曼彻斯特大学）；Manchester Centre for Robotics and AI（曼彻斯特机器人与人工智能中心）；Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系）
Mind the Gap! Bridging Explainable Artificial Intelligence and Human Understanding with Luhmann's Functional Theory of Communication
School of Law, Birkbeck, University of London（伦敦大学伯贝克学院法学院）；Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系）；ARC Centre of Excellence for Automated Decision-Making and Society, RMIT University（皇家墨尔本理工大学自动化决策与社会ARC卓越研究中心）
Learnable Residual-Based Latent Denoising in Semantic Communication
Department of Electronic Engineering, Shanghai Jiao Tong University（电子工程系，上海交通大学）；School of Cyber and Engineering, Shanghai Jiao Tong University（网络与工程学院，上海交通大学）；Department of Electrical and Computer Engineering, University of Delaware（电气与计算机工程系，德雷塞尔大学）；State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（网络与交换技术国家重点实验室，北京邮电大学）
Integrated Sensing-Communication-Computation for Edge Artificial Intelligence
School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；School of Information and Communication Engineering, Beijing University of Posts and Telecommunications（北京邮电大学信息与通信工程学院）；Tsinghua University（清华大学）
Latent Space Alignment for AI-Native MIMO Semantic Communications
DIAG Department, Sapienza University of Rome（罗马萨皮恩扎大学DIAG系）；Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT)（国家跨大学电信合作组织（CNIT））；CEA Leti, University Grenoble Alpes（CEA Leti，格勒诺布尔阿尔卑斯大学）；DIET Department, Sapienza University of Rome（罗马萨皮恩扎大学DIET系）
针对 AI 原生 MIMO 语义通信中的潜空间不对齐问题，提出联合压缩与语义均衡的预编码器/解码器学习方法，并给出 ADMM 线性模型和受功率、复杂度约束的神经网络方案。
CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence
College of Computer Science and Technology（计算机科学与技术学院）；Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）；School of Aeronautics and Astronautics（航空宇航科学学院）；School of Computing（计算科学学院）
