As 6G advances, it is expected to go beyond traditional mobile Internet applications by supporting ubiquitous  intelligence services such as sustainable cities, connected autonomous systems, digital twins, and the metaverse. Driven by these emerging applications, the way of content generation has been inherently shifting from human-generated to AI-generated. Moreover, their unique requirements and goals further pose critical challenges to traditional Shannon’s bit oriented communication frameworks, which are nearing the Shannon capacity limit. To enhance communication efficiency and reliability, recent studies in semantic communications have focused on transmitting information with semantics by considering information relevance and importance. However, these transmitter-centered paradigms cannot effectively characterize the significance of data in specific tasks, as the significance of the same data varies across different tasks and overtime on the receiver side. To address this issue, task-oriented and generative communications have recently attracted considerable attention. Task-oriented communications consider the effective and efficient completion of specific tasks at the receiver side. Generative communication further enhances this efficiency by reducing communication costs to the smallest units, such as tokens, while enabling the receiver to generate the required data based on task specifications. However, the role of generative AI goes beyond simple data compression. It enables data modality conversion (e.g., transforming text into images or videos) and enables dynamic data modifications (e.g., generating images with different poses or object orientations), offering greater flexibility and adaptability to specific task needs. In general, task-oriented and generative communications have a synergy to meet the requirements of intelligence services, especially for time-varying and generic tasks without compromising communication efficiency.

However, there are still many fundamental problems in task-oriented and generative communications that remain under-explored. Observing the recent surge in related research and the emergence of exciting opportunities, we propose the timely and promising workshop “Task-Oriented and Generative Communications for 6G.” This workshop aims to bring together researchers from both academia and industry to present the latest advancements and discuss future research opportunities in this field. 

Topics of interest include, but are not limited to: 

•  Information theory for task-oriented and generative communications

•  Signal processing for task-oriented and generative communications

•  New protocols for task-oriented and generative communications

• Applications and use cases of task-oriented and generative communications

• Hardware designs tailored to task-oriented and generative communication systems

• Generative AI and large language models (LLMs) for task-oriented communications

• Multimodal learning and its integration into task-oriented communications

• Task-oriented and generative communication for edge AI

• Distributed fine-tuning of generative models over wireless systems

• Multimodal generative models for deep joint source and channel coding

• Task-oriented joint source and channel coding

• Generative model based channel emulation and estimation

• Case studies and practical implementations of task-oriented communication systems

Paper Submission Link

https://edas.info/newPaper.php?c=32909&track=127539

Important Dates

Workshop Paper Submission: 1 December 2024

Paper Acceptance Notification: 15 January 2025

Camera Ready: 1 February  2025 

Registration Due for Accepted Papers: TBD