Related papers: Semantic Importance-Aware Communications with Sema…

Large Language Models (LLMs) have shown great potential for enhancing recommender systems through their extensive world knowledge and reasoning capabilities. However, effectively translating these semantic signals into traditional…

Deep learning algorithms lack human-interpretable accounts of how they transform raw visual input into a robust semantic understanding, which impedes comparisons between different architectures, training objectives, and the human brain. In…

Image-text retrieval is one of the major tasks of cross-modal retrieval. Several approaches for this task map images and texts into a common space to create correspondences between the two modalities. However, due to the content (semantics)…

We present the first loss agent, dubbed LossAgent, for low-level image processing tasks, e.g., image super-resolution and restoration, intending to achieve any customized optimization objectives of low-level image processing in different…

Against the backdrop of enthusiasm for large language models (LLMs), there is a growing need to scientifically assess their capabilities and shortcomings. This is nontrivial in part because it is difficult to find tasks which the models…

Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…

We introduce a new semantic communication mechanism - SemanticRL, whose key idea is to preserve the semantic information instead of strictly securing the bit-level precision. Unlike previous methods that mainly concentrate on the network or…

Large Language Models (LLMs) play a crucial role in capturing structured semantics to enhance language understanding, improve interpretability, and reduce bias. Nevertheless, an ongoing controversy exists over the extent to which LLMs can…

Machine Learning (ML) is continuously permeating a growing amount of application domains. Generative AI such as Large Language Models (LLMs) also sees broad adoption to process multi-modal data such as text, images, audio, and video. While…

Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years. In this paper, we propose a generative model based semantic communication to further improve the efficiency of image…

Meaning in human language is relational, context dependent, and emergent, arising from dynamic systems of signs rather than fixed word-concept mappings. In computational settings, this semiotic and interpretive complexity complicates the…

Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to…

In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between agents with different…

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Effective human-robot collaboration hinges on robust communication channels, with visual signaling playing a pivotal role due to its intuitive appeal. Yet, the creation of visually intuitive cues often demands extensive resources and…

We address the problem of semantic correspondence, that is, establishing a dense flow field between images depicting different instances of the same object or scene category. We propose to use images annotated with binary foreground masks…

Recently, learning-based semantic communication (SemCom) has emerged as a promising approach in the upcoming 6G network and researchers have made remarkable efforts in this field. However, existing works have yet to fully explore the…

As the global demand for data has continued to rise exponentially, some have begun turning to the idea of semantic communication as a means of efficiently meeting this demand. Pushing beyond the boundaries of conventional communication…

Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information which makes place recognition based on point clouds…

In multi-agent settings, such as debate, reflection, or tool-calling, large language models (LLMs) pass messages as plain tokens, discarding most latent semantics. This constrains information transfer and adds unnecessary computational…