相关论文: Task-Driven Semantic Quantization and Imitation Le…

State-of-the-art generative image and video models rely heavily on tokenizers that compress high-dimensional inputs into more efficient latent representations. While this paradigm has revolutionized RGB generation, Earth observation (EO)…

While semantic communications have shown the potential in the case of single-modal single-users, its applications to the multi-user scenario remain limited. In this paper, we investigate deep learning (DL) based multi-user semantic…

This paper addresses the problem of end-to-end (E2E) design of learning and communication in a task-oriented semantic communication system. In particular, we consider a multi-device cooperative edge inference system over a wireless…

We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression,…

Task-Oriented Semantic Communication (TOSC) has been considered as a new communication paradigm to serve various samrt devices that depend on Artificial Intelligence (AI) tasks in future wireless networks. The existing TOSC frameworks rely…

Despite recent successes in synthesizing faces and bedrooms, existing generative models struggle to capture more complex image types, potentially due to the oversimplification of their latent space constructions. To tackle this issue,…

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…

With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification and clustering apart from data recovery. Motivated by the success of deep learning,…

With the aim of accomplishing intelligence tasks, semantic communications transmit task-related information only, yielding significant performance gains over conventional communications. To guarantee user requirements for different types of…

With the ever-increasing amount of data, the central challenge in multimodal learning involves limitations of labelled samples. For the task of classification, techniques such as meta-learning, zero-shot learning, and few-shot learning…

Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…

Semantic communications represent a significant breakthrough with respect to the current communication paradigm, as they focus on recovering the meaning behind the transmitted sequence of symbols, rather than the symbols themselves. In…

Existing state-of-the-art image tokenization methods leverage diverse semantic features from pre-trained vision models for additional supervision, to expand the distribution of latent representations and thereby improve the quality of image…

Variational auto-encoder (VAE) is an effective neural network architecture to disentangle a speech utterance into speaker identity and linguistic content latent embeddings, then generate an utterance for a target speaker from that of a…

The integration of Semantic Communications (SemCom) and edge computing in space networks enables the optimal allocation of the scarce energy, computing, and communication resources for data-intensive applications. We use Earth Observation…

We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to…

In the era of 6G, with compelling visions of intelligent transportation systems and digital twins, remote surveillance is poised to become a ubiquitous practice. Substantial data volume and frequent updates present challenges in wireless…

Semantic communications, aiming at ensuring the successful delivery of the meaning of information, are expected to be one of the potential techniques for the next generation communications. However, the knowledge forming and synchronizing…

People can easily imagine the potential sound while seeing an event. This natural synchronization between audio and visual signals reveals their intrinsic correlations. To this end, we propose to learn the audio-visual correlations from the…

Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the…