In wireless communications, electromagnetic theory and information theory constitute a pair of fundamental theories, bridged by antenna theory and wireless propagation channel modeling theory. Up to the fifth generation (5G) wireless communication networks, these four theories have been developing relatively independently. However, in sixth generation (6G) space-air-ground-sea wireless communication networks, seamless coverage is expected in the three-dimensional (3D) space, potentially necessitating the acquisition of channel state information (CSI) and channel capacity calculation at anywhere and any time. Additionally, the key 6G technologies such as ultra-massive multiple-input multiple-output (MIMO) and holographic MIMO achieves intricate interaction of the antennas and wireless propagation environments, which necessitates the joint modeling of antennas and wireless propagation channels. To address the challenges in 6G, the integration of the above four theories becomes inevitable, leading to the concept of the so-called electromagnetic information theory (EIT). In this article, a suite of 6G key technologies is highlighted. Then, the concepts and relationships of the four theories are unveiled. Finally, the necessity and benefits of integrating them into the EIT are revealed.
Effective progress monitoring is crucial for the successful delivery of the construction project within the stipulated time and budget. Construction projects are often monitored irregularly through time-consuming physical site visits by multiple project stakeholders. Remote monitoring using robotic cyber-physical systems (CPS) can make the process more efficient and safer. This article presents a conceptual framework for robotic CPS for automated reality capture and visualization for remote progress monitoring in construction. The CPS integrates quadruped robot, Building Information Modelling (BIM), and 360{\deg} reality capturing to autonomously capture, and visualize up-to-date site information. Additionally, the study explores the factors affecting acceptance of the proposed robotic CPS through semi-structured interviews with seventeen progress monitoring experts. The findings will guide construction management teams in adopting CPS in construction and drive further research in the human-centered development of CPS for construction.
Unsupervised learning objectives like language modeling and de-noising constitute a significant part in producing pre-trained models that perform various downstream applications from natural language understanding to conversational tasks. However, despite impressive conversational capabilities of recent large language model, their abilities to capture syntactic or semantic structure within text lag behind. We hypothesize that the mismatch between linguistic performance and competence in machines is attributable to insufficient transfer of linguistic structure knowledge to computational systems with currently popular pre-training objectives. We show that punctuation restoration transfers to improvements in in- and out-of-distribution performance on structure-related tasks like named entity recognition, open information extraction, chunking, and part-of-speech tagging. Punctuation restoration is an effective learning objective that can improve structure understanding and yield a more robust structure-aware representations of natural language.
Having revolutionized natural language processing (NLP) applications, large language models (LLMs) are expanding into the realm of multimodal inputs. Owing to their ability to interpret images, multimodal LLMs (MLLMs) have been primarily used for vision-language tasks. Currently, MLLMs have not yet been extended for domain-specific visual tasks, which require a more explicit understanding of visual information. We developed a method to transform domain-specific visual and vision-language datasets into a unified question answering format called Visual Question Answering Instruction (VQA-IN), thereby extending MLLM to domain-specific tasks. The VQA-IN was applied to train multiple MLLM architectures using smaller versions of LLMs (sLLMs). The experimental results indicated that the proposed method achieved a high score metric on domainspecific visual tasks while also maintaining its performance on vision-language tasks in a multitask manner.
The healthcare landscape is evolving, with patients seeking more reliable information about their health conditions, treatment options, and potential risks. Despite the abundance of information sources, the digital age overwhelms individuals with excess, often inaccurate information. Patients primarily trust doctors and hospital staff, highlighting the need for expert-endorsed health information. However, the pressure on experts has led to reduced communication time, impacting information sharing. To address this gap, we propose CataractBot, an experts-in-the-loop chatbot powered by large language models (LLMs). Developed in collaboration with a tertiary eye hospital in India, CataractBot answers cataract surgery related questions instantly by querying a curated knowledge base, and provides expert-verified responses asynchronously. CataractBot features multimodal support and multilingual capabilities. In an in-the-wild deployment study with 49 participants, CataractBot proved valuable, providing anytime accessibility, saving time, and accommodating diverse literacy levels. Trust was established through expert verification. Broadly, our results could inform future work on designing expert-mediated LLM bots.
Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences.Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for advanced information.This study proposed a novel framework SumRec for recommending information from open-domain chat dialogue.The study also examined the framework using ChatRec, a newly constructed dataset for training and evaluation. To extract the speaker and item characteristics, the SumRec framework employs a large language model (LLM) to generate a summary of the speaker information from a dialogue and to recommend information about an item according to the type of user.The speaker and item information are then input into a score estimation model, generating a recommendation score.Experimental results show that the SumRec framework provides better recommendations than the baseline method of using dialogues and item descriptions in their original form. Our dataset and code is publicly available at https://github.com/Ryutaro-A/SumRec
Image coding for machines (ICM) aims to compress images for machine analysis using recognition models rather than human vision. Hence, in ICM, it is important for the encoder to recognize and compress the information necessary for the machine recognition task. There are two main approaches in learned ICM; optimization of the compression model based on task loss, and Region of Interest (ROI) based bit allocation. These approaches provide the encoder with the recognition capability. However, optimization with task loss becomes difficult when the recognition model is deep, and ROI-based methods often involve extra overhead during evaluation. In this study, we propose a novel training method for learned ICM models that applies auxiliary loss to the encoder to improve its recognition capability and rate-distortion performance. Our method achieves Bjontegaard Delta rate improvements of 27.7% and 20.3% in object detection and semantic segmentation tasks, compared to the conventional training method.
Recent advancements in generative models have established state-of-the-art benchmarks in generating molecules and novel drug candidates. Despite these successes, a significant gap persists between generative models and the utilization of extensive biomedical knowledge, often systematized within knowledge graphs, whose potential to inform and enhance generative processes has not been realized. In this paper, we present a novel approach that bridges this divide by developing a framework for knowledge-enhanced generative models called K-DReAM. We develop a scalable methodology to extend the functionality of knowledge graphs while preserving semantic integrity and incorporate this contextual information into a generative framework to guide a diffusion-based model. The integration of knowledge graph embeddings with our generative model furnishes a robust mechanism for producing novel drug candidates possessing specific characteristics while ensuring validity and synthesizability. K-DReAM outperforms state-of-the-art generative models on both unconditional and targeted generation tasks.
In this work, we present an open-source implementation of the enumerative sphere shaping (ESS) algorithm used for probabilistic constellation shaping (PCS). PCS aims at closing the shaping gap caused by using uniformly distributed modulation symbols in channels for which information theory shows non-uniformly distributed signaling to be optimal. ESS is one such PCS algorithm that sets itself apart as it operates on a trellis representation of a subset of the possible symbol sequences. ESS leads to an empirical distribution of the symbols that closely approximates the optimal distribution for the additive white Gaussian noise (AWGN) channel. We provide an open-source implementation of this algorithm in the compiled language Rust, as well as Python bindings with which our Rust code can be called in a regular Python script. We also compare simulation results on the AWGN channel using our implementation with previous works on this topic.
Large Multimodal Models (LMMs) excel in natural language and visual understanding but are challenged by exacting tasks such as Knowledge-based Visual Question Answering (KB-VQA) which involve the retrieval of relevant information from document collections to use in shaping answers to questions. We present an extensive training and evaluation framework, M2KR, for KB-VQA. M2KR contains a collection of vision and language tasks which we have incorporated into a single suite of benchmark tasks for training and evaluating general-purpose multi-modal retrievers. We use M2KR to develop PreFLMR, a pre-trained version of the recently developed Fine-grained Late-interaction Multi-modal Retriever (FLMR) approach to KB-VQA, and we report new state-of-the-art results across a range of tasks. We also present investigations into the scaling behaviors of PreFLMR intended to be useful in future developments in general-purpose multi-modal retrievers.