Related papers: On Barbs and Labels in Reactive Systems

To enable Large Language Models (LLMs) to function as conscious agents with generalizable reasoning capabilities, it is crucial that they possess the reasoning ability to comprehend situational changes (transitions) in distribution…

Conversational Recommender Systems (CRSs) have garnered attention as a novel approach to delivering personalized recommendations through multi-turn dialogues. This review developed a taxonomy framework to systematically categorize relevant…

The topological interpretation of modal logics provides descriptive languages and proof systems for reasoning about points of topological spaces. Recent work has been devoted to model checking of spatial logics on discrete spatial…

Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferences while effectively leveraging both behavioral and semantic signals. Existing approaches…

This article addresses the challenge of optimizing handover (HO) in next-generation wireless networks by integrating Reconfigurable Intelligent Surfaces (RIS), predicting received signal power, and utilizing learning-based decision-making.…

Multi-agent systems (MAS) have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving; however, current MAS frameworks suffer from poor flexibility and scalability with…

In-context imitation learning (ICIL) enables robots to learn tasks from prompts consisting of just a handful of demonstrations. By eliminating the need for parameter updates at deployment time, this paradigm supports few-shot adaptation to…

The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sensitive to environmental design, reward structures, and…

Traditional evaluation metrics for textual and visual question answering, like ROUGE, METEOR, and Exact Match (EM), focus heavily on n-gram based lexical similarity, often missing the deeper semantic understanding needed for accurate…

Reconfigurable intelligent surfaces (RISs) are considered a promising technology for boosting the coverage and for enhancing the spectral efficiency of wireless systems, as well as for taming the wireless environment. The potential benefits…

Available works addressing multi-label classification in a data stream environment focus on proposing accurate models; however, these models often exhibit inefficiency and cannot balance effectiveness and efficiency. In this work, we…

Large Language Models (LLMs) have achieved rapid progress in Chinese language understanding, yet accurately evaluating their capabilities remains challenged by benchmark saturation and prohibitive computational costs. While static…

Reconfigurable multi-agent systems consist of a set of autonomous agents, with integrated interaction capabilities that feature opportunistic interaction. Agents seemingly reconfigure their interactions interfaces by forming collectives,…

Reconfigurable intelligent surfaces (RISs) have the potential of realizing the emerging concept of smart radio environments by leveraging the unique properties of meta-surfaces. In this article, we discuss the potential applications of RISs…

Motivated by the observation that a given signal $\boldsymbol{x}$ admits sparse representations in multiple dictionaries $\boldsymbol{\Psi}_d$ but with varying levels of sparsity across dictionaries, we propose two new algorithms for the…

Large language models (LLMs) excel at explicit reasoning, but their implicit computational strategies remain underexplored. Decades of psychophysics research show that humans intuitively process and integrate noisy signals using…

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

We introduce a dynamic benchmarking system for conversational agents that evaluates their performance through a single, simulated, and lengthy user$\leftrightarrow$agent interaction. The interaction is a conversation between the user and…

Given the exponential advancement in AI technologies and the potential escalation of harmful effects from recommendation systems, it is crucial to simulate and evaluate these effects early on. Doing so can help prevent possible damage to…