Related papers: ToDMA: Large Model-Driven Token-Domain Multiple Ac…

Multiple access (MA) design is investigated for facilitating the coexistence of the emerging semantic transmission and the conventional bit-based transmission in future networks. The semantic rate is considered for measuring the performance…

Semantic communications have been utilized to execute numerous intelligent tasks by transmitting task-related semantic information instead of bits. In this article, we propose a semantic-aware speech-to-text transmission system for the…

Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel decoding, this process incurs substantial computational cost…

This paper investigates a novel generative artificial intelligence (GAI) empowered multi-user semantic communication system called semantic feature multiple access (SFMA) for video transmission, which comprises a base station (BS) and…

Large language models (LLMs) face persistent challenges when handling long-context tasks, most notably the lost in the middle issue, where information located in the middle of a long input tends to be underutilized. Some existing methods…

Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often…

Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and…

Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse…

While Large Language Models (LLMs) have shown exceptional generalization capabilities, their ability to process graph data, such as molecular structures, remains limited. To bridge this gap, this paper proposes Graph2Token, an efficient…

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored.…

Dialog act (DA) recognition is a task that has been widely explored over the years. Recently, most approaches to the task explored different DNN architectures to combine the representations of the words in a segment and generate a segment…

Vehicle-to-everything (V2X) communication supports numerous tasks, from driving safety to entertainment services. To achieve a holistic view, vehicles are typically equipped with multiple sensors to compensate for undetectable blind spots.…

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…

Recent research in dialogue systems and corpora has focused on two main categories: task-oriented (TOD) and open-domain (chit-chat) dialogues. TOD systems help users accomplish specific tasks, while open-domain systems aim to create…

In this work, we study the use of non-orthogonal multiple access (NOMA) and orthogonal time frequency space (OTFS) modulation in a multiple-input multiple-output (MIMO) communication network where mobile users (MUs) with different mobility…

The fifth generation wireless networks focus on the design of low latency, high data rate, high reliability, and massive connectivity communications. Non-orthogonal multiple access (NOMA) is an essential enabling technology to accommodate…

As three-dimensional acquisition technologies like LiDAR cameras advance, the need for efficient transmission of 3D point clouds is becoming increasingly important. In this paper, we present a novel semantic communication (SemCom) approach…

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual…

This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of…

Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the…