A near-field wideband beamforming scheme is investigated for reconfigurable intelligent surface (RIS) assisted multiple-input multiple-output (MIMO) systems, in which a deep learning-based end-to-end (E2E) optimization framework is proposed to maximize the system spectral efficiency. To deal with the near-field double beam split effect, the base station is equipped with frequency-dependent hybrid precoding architecture by introducing sub-connected true time delay (TTD) units, while two specific RIS architectures, namely true time delay-based RIS (TTD-RIS) and virtual subarray-based RIS (SA-RIS), are exploited to realize the frequency-dependent passive beamforming at the RIS. Furthermore, the efficient E2E beamforming models without explicit channel state information are proposed, which jointly exploits the uplink channel training module and the downlink wideband beamforming module. In the proposed network architecture of the E2E models, the classical communication signal processing methods, i.e., polarized filtering and sparsity transform, are leveraged to develop a signal-guided beamforming network. Numerical results show that the proposed E2E models have superior beamforming performance and robustness to conventional beamforming benchmarks. Furthermore, the tradeoff between the beamforming gain and the hardware complexity is investigated for different frequency-dependent RIS architectures, in which the TTD-RIS can achieve better spectral efficiency than the SA-RIS while requiring additional energy consumption and hardware cost.
The ultra-reliable and low-latency communication (URLLC) service of the fifth-generation (5G) mobile communication network struggles to support safe robot operation. Nowadays, the sixth-generation (6G) mobile communication network is proposed to provide hyper-reliable and low-latency communication to enable safer control for robots. However, current 5G/ 6G research mainly focused on improving communication performance, while the robotics community mostly assumed communication to be ideal. To jointly consider communication and robotic control with a focus on the specific robotic task, we propose task-oriented and semantics-aware communication in robotic control (TSRC) to exploit the context of data and its importance in achieving the task at both transmitter and receiver. At the transmitter, we propose a deep reinforcement learning algorithm to generate optimal control and command (C&C) data and a proactive repetition scheme (DeepPro) to increase the successful transmission probability. At the receiver, we design the value of information (VoI) and age of information (AoI) based queue ordering mechanism (VA-QOM) to reorganize the queue based on the semantic information extracted from the AoI and the VoI. The simulation results validate that our proposed TSRC framework achieves a 91.5% improvement in the mean square error compared to the traditional unmanned aerial vehicle control framework.
Traffic volume data collection is a crucial aspect of transportation engineering and urban planning, as it provides vital insights into traffic patterns, congestion, and infrastructure efficiency. Traditional manual methods of traffic data collection are both time-consuming and costly. However, the emergence of modern technologies, particularly Light Detection and Ranging (LiDAR), has revolutionized the process by enabling efficient and accurate data collection. Despite the benefits of using LiDAR for traffic data collection, previous studies have identified two major limitations that have impeded its widespread adoption. These are the need for multiple LiDAR systems to obtain complete point cloud information of objects of interest, as well as the labor-intensive process of annotating 3D bounding boxes for object detection tasks. In response to these challenges, the current study proposes an innovative framework that alleviates the need for multiple LiDAR systems and simplifies the laborious 3D annotation process. To achieve this goal, the study employed a single LiDAR system, that aims at reducing the data acquisition cost and addressed its accompanying limitation of missing point cloud information by developing a Point Cloud Completion (PCC) framework to fill in missing point cloud information using point density. Furthermore, we also used zero-shot learning techniques to detect vehicles and pedestrians, as well as proposed a unique framework for extracting low to high features from the object of interest, such as height, acceleration, and speed. Using the 2D bounding box detection and extracted height information, this study is able to generate 3D bounding boxes automatically without human intervention.
Age of incorrect information (AoII) has recently been proposed as an alternative to existing information freshness metrics for real-time sampling and estimation problems involving information sources that are tracked by remote monitors. Different from existing metrics, AoII penalizes the incorrect information by increasing linearly with time as long as the source and the monitor are de-synchronized, and is reset when they are synchronized back. While AoII has generally been investigated for discrete time information sources, we develop a novel analytical model in this paper for push- and pull-based sampling and transmission of a continuous time Markov chain (CTMC) process. In the pull-based model, the sensor starts transmitting information on the observed CTMC only when a pull request from the monitor is received. On the other hand, in the push-based scenario, the sensor, being aware of the AoII process, samples and transmits when the AoII process exceeds a random threshold. The proposed analytical model for both scenarios is based on the construction of a discrete time MC (DTMC) making state transitions at the embedded epochs of synchronization points, using the theory of absorbing CTMCs, and in particular phase-type distributions. For a given sampling policy, analytical models to obtain the mean AoII and the average sampling rate are developed. Numerical results are presented to validate the analytical model as well as to provide insight on optimal sampling policies under sampling rate constraints.
The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key components: (1) We employ discrete wavelet transform that decomposes a complicated waveform into sub-band wavelets, which helps FreGrad to operate on a simple and concise feature space, (2) We design a frequency-aware dilated convolution that elevates frequency awareness, resulting in generating speech with accurate frequency information, and (3) We introduce a bag of tricks that boosts the generation quality of the proposed model. In our experiments, FreGrad achieves 3.7 times faster training time and 2.2 times faster inference speed compared to our baseline while reducing the model size by 0.6 times (only 1.78M parameters) without sacrificing the output quality. Audio samples are available at: https://mm.kaist.ac.kr/projects/FreGrad.
The advent of large language models (LLMs) such as ChatGPT has attracted considerable attention in various domains due to their remarkable performance and versatility. As the use of these models continues to grow, the importance of effective prompt engineering has come to the fore. Prompt optimization emerges as a crucial challenge, as it has a direct impact on model performance and the extraction of relevant information. Recently, evolutionary algorithms (EAs) have shown promise in addressing this issue, paving the way for novel optimization strategies. In this work, we propose a evolutionary multi-objective (EMO) approach specifically tailored for prompt optimization called EMO-Prompts, using sentiment analysis as a case study. We use sentiment analysis capabilities as our experimental targets. Our results demonstrate that EMO-Prompts effectively generates prompts capable of guiding the LLM to produce texts embodying two conflicting emotions simultaneously.
Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio. In AVSR, considerable efforts have been directed at datasets for facial features such as lip-readings, while they often fall short in evaluating the image comprehension capabilities in broader contexts. In this paper, we construct SlideAVSR, an AVSR dataset using scientific paper explanation videos. SlideAVSR provides a new benchmark where models transcribe speech utterances with texts on the slides on the presentation recordings. As technical terminologies that are frequent in paper explanations are notoriously challenging to transcribe without reference texts, our SlideAVSR dataset spotlights a new aspect of AVSR problems. As a simple yet effective baseline, we propose DocWhisper, an AVSR model that can refer to textual information from slides, and confirm its effectiveness on SlideAVSR.
Data is stored in both structured and unstructured form. Querying both, to power natural language conversations, is a challenge. This paper introduces dIR, Discrete Information Retrieval, providing a unified interface to query both free text and structured knowledge. Specifically, a Large Language Model (LLM) transforms text into expressive representation. After the text is extracted into columnar form, it can then be queried via a text-to-SQL Semantic Parser, with an LLM converting natural language into SQL. Where desired, such conversation may be effected by a multi-step reasoning conversational agent. We validate our approach via a proprietary question/answer data set, concluding that dIR makes a whole new class of queries on free text possible when compared to traditionally fine-tuned dense-embedding-model-based Information Retrieval (IR) and SQL-based Knowledge Bases (KB). For sufficiently complex queries, dIR can succeed where no other method stands a chance.
Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do not. On the basis of our empirical study, we discover that training on good-practice commits significantly contributes to the commit message generation. Motivated by this finding, we propose a novel knowledge-aware denoising learning method called KADEL. Considering that good-practice commits constitute only a small proportion of the dataset, we align the remaining training samples with these good-practice commits. To achieve this, we propose a model that learns the commit knowledge by training on good-practice commits. This knowledge model enables supplementing more information for training samples that do not conform to good practice. However, since the supplementary information may contain noise or prediction errors, we propose a dynamic denoising training method. This method composes a distribution-aware confidence function and a dynamic distribution list, which enhances the effectiveness of the training process. Experimental results on the whole MCMD dataset demonstrate that our method overall achieves state-of-the-art performance compared with previous methods. Our source code and data are available at https://github.com/DeepSoftwareAnalytics/KADEL
To autonomously navigate in real-world environments, special in search and rescue operations, Unmanned Aerial Vehicles (UAVs) necessitate comprehensive maps to ensure safety. However, the prevalent metric map often lacks semantic information crucial for holistic scene comprehension. In this paper, we proposed a system to construct a probabilistic metric map enriched with object information extracted from the environment from RGB-D images. Our approach combines a state-of-the-art YOLOv8-based object detection framework at the front end and a 2D SLAM method - CartoGrapher at the back end. To effectively track and position semantic object classes extracted from the front-end interface, we employ the innovative BoT-SORT methodology. A novel association method is introduced to extract the position of objects and then project it with the metric map. Unlike previous research, our approach takes into reliable navigating in the environment with various hollow bottom objects. The output of our system is a probabilistic map, which significantly enhances the map's representation by incorporating object-specific attributes, encompassing class distinctions, accurate positioning, and object heights. A number of experiments have been conducted to evaluate our proposed approach. The results show that the robot can effectively produce augmented semantic maps containing several objects (notably chairs and desks). Furthermore, our system is evaluated within an embedded computer - Jetson Xavier AGX unit to demonstrate the use case in real-world applications.