Search

The receiver design for multi-input multi-output (MIMO) ultra-reliable and low-latency communication (URLLC) systems can be a tough task due to the use of short channel codes and few pilot symbols. Consequently, error propagation can occur in traditional turbo receivers, leading to performance degradation. Moreover, the processing delay induced by information exchange between different modules may also be undesirable for URLLC. To address the issues, we advocate to perform joint channel estimation, detection, and decoding (JCDD) for MIMO URLLC systems encoded by short low-density parity-check (LDPC) codes. Specifically, we develop two novel JCDD problem formulations based on the maximum a posteriori (MAP) criterion for Gaussian MIMO channels and sparse mmWave MIMO channels, respectively, which integrate the pilots, the bit-to-symbol mapping, the LDPC code constraints, as well as the channel statistical information. Both the challenging large-scale non-convex problems are then solved based on the alternating direction method of multipliers (ADMM) algorithms, where closed-form solutions are achieved in each ADMM iteration. Furthermore, two JCDD neural networks, called JCDDNet-G and JCDDNet-S, are built by unfolding the derived ADMM algorithms and introducing trainable parameters. It is interesting to find via simulations that the proposed trainable JCDD receivers can outperform the turbo receivers with affordable computational complexities., Comment: 17 pages, 12 figures, accepted by IEEE Transactions on Wireless Communications

In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically leverage vast task planning datasets to enhance models' planning abilities. While these methods show promise, they struggle with complex long-horizon tasks, which require comprehending more context and generating longer action sequences. This paper addresses this limitation by proposing MLDT, theMulti-Level Decomposition Task planning method. This method innovatively decomposes tasks at the goal-level, task-level, and action-level to mitigate the challenge of complex long-horizon tasks. In order to enhance open-source LLMs' planning abilities, we introduce a goal-sensitive corpus generation method to create high-quality training data and conduct instruction tuning on the generated corpus. Since the complexity of the existing datasets is not high enough, we construct a more challenging dataset, LongTasks, to specifically evaluate planning ability on complex long-horizon tasks. We evaluate our method using various LLMs on four datasets in VirtualHome. Our results demonstrate a significant performance enhancement in robotic task planning, showcasing MLDT's effectiveness in overcoming the limitations of existing methods based on open-source LLMs as well as its practicality in complex, real-world scenarios.

Table understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures.To address these challenges, we propose HGT, a framework with a heterogeneous graph (HG)-enhanced large language model (LLM) to tackle few-shot TU tasks.It leverages the LLM by aligning the table semantics with the LLM's parametric knowledge through soft prompts and instruction turning and deals with complex tables by a multi-task pre-training scheme involving three novel multi-granularity self-supervised HG pre-training objectives.We empirically demonstrate the effectiveness of HGT, showing that it outperforms the SOTA for few-shot complex TU on several benchmarks.

Augmenting Large Language Models (LLMs) for Question Answering (QA) with domain specific data has attracted wide attention. However, domain data often exists in a hybrid format, including text and semi-structured tables, posing challenges for the seamless integration of information. Table-to-Text Generation is a promising solution by facilitating the transformation of hybrid data into a uniformly text-formatted corpus. Although this technique has been widely studied by the NLP community, there is currently no comparative analysis on how corpora generated by different table-to-text methods affect the performance of QA systems. In this paper, we address this research gap in two steps. First, we innovatively integrate table-to-text generation into the framework of enhancing LLM-based QA systems with domain hybrid data. Then, we utilize this framework in real-world industrial data to conduct extensive experiments on two types of QA systems (DSFT and RAG frameworks) with four representative methods: Markdown format, Template serialization, TPLM-based method, and LLM-based method. Based on the experimental results, we draw some empirical findings and explore the underlying reasons behind the success of some methods. We hope the findings of this work will provide a valuable reference for the academic and industrial communities in developing robust QA systems., Comment: Accepted to NAACL 2024 Industry Track Paper

Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs). Despite its potential, current benchmarks predominantly focus on coarse-grained knowledge, leaving the intricacies of fine-grained (FG) multimodal entity knowledge largely unexplored. This gap presents a notable challenge, as FG entity recognition is pivotal for the practical deployment and effectiveness of MLLMs in diverse real-world scenarios. To bridge this gap, we introduce MIKE, a comprehensive benchmark and dataset specifically designed for the FG multimodal entity knowledge editing. MIKE encompasses a suite of tasks tailored to assess different perspectives, including Vanilla Name Answering, Entity-Level Caption, and Complex-Scenario Recognition. In addition, a new form of knowledge editing, Multi-step Editing, is introduced to evaluate the editing efficiency. Through our extensive evaluations, we demonstrate that the current state-of-the-art methods face significant challenges in tackling our proposed benchmark, underscoring the complexity of FG knowledge editing in MLLMs. Our findings spotlight the urgent need for novel approaches in this domain, setting a clear agenda for future research and development efforts within the community., Comment: 8 pages

The attribution of question answering is to provide citations for supporting generated statements, and has attracted wide research attention. The current methods for automatically evaluating the attribution, which are often based on Large Language Models (LLMs), are still inadequate, particularly in recognizing subtle differences between attributions, and complex relationships between citations and statements. To compare these attribution evaluation methods and develop new ones, we introduce a set of fine-grained categories (i.e., supportive, insufficient, contradictory and irrelevant) for measuring the attribution, and develop a Complex Attributed Question Answering (CAQA) benchmark by leveraging knowledge graphs (KGs) for automatically generating attributions of different categories to question-answer pairs. Our analysis reveals that existing evaluators perform poorly under fine-grained attribution settings and exhibit weaknesses in complex citation-statement reasoning. Our CAQA benchmark, validated with human annotations, emerges as a promising tool for selecting and developing LLM attribution evaluators., Comment: 13 pages, 5 figures

Despite their competitive performance on knowledge-intensive tasks, large language models (LLMs) still have limitations in memorizing all world knowledge especially long tail knowledge. In this paper, we study the KG-augmented language model approach for solving the knowledge graph question answering (KGQA) task that requires rich world knowledge. Existing work has shown that retrieving KG knowledge to enhance LLMs prompting can significantly improve LLMs performance in KGQA. However, their approaches lack a well-formed verbalization of KG knowledge, i.e., they ignore the gap between KG representations and textual representations. To this end, we propose an answer-sensitive KG-to-Text approach that can transform KG knowledge into well-textualized statements most informative for KGQA. Based on this approach, we propose a KG-to-Text enhanced LLMs framework for solving the KGQA task. Experiments on several KGQA benchmarks show that the proposed KG-to-Text augmented LLMs approach outperforms previous KG-augmented LLMs approaches regarding answer accuracy and usefulness of knowledge statements.

In this paper, we investigate the design of statistically robust detectors for multi-input multi-output (MIMO) systems subject to imperfect channel state information (CSI). A robust maximum likelihood (ML) detection problem is formulated by taking into consideration the CSI uncertainties caused by both the channel estimation error and the channel variation. To address the challenging discrete optimization problem, we propose an efficient alternating direction method of multipliers (ADMM)-based algorithm, which only requires calculating closed-form solutions in each iteration. Furthermore, a robust detection network RADMMNet is constructed by unfolding the ADMM iterations and employing both model-driven and data-driven philosophies. Moreover, in order to relieve the computational burden, a low-complexity ADMM-based robust detector is developed using the Gaussian approximation, and the corresponding deep unfolding network LCRADMMNet is further established. On the other hand, we also provide a novel robust data-aided Kalman filter (RDAKF)-based channel tracking method, which can effectively refine the CSI accuracy and improve the performance of the proposed robust detectors. Simulation results validate the significant performance advantages of the proposed robust detection networks over the non-robust detectors with different CSI acquisition methods., Comment: 15 pages, 8 figures, 2 tables; Accepted by IEEE TCOM

With the increasing deployment of agricultural robots, the traditional manual spray of liquid fertilizer and pesticide is gradually being replaced by agricultural robots. For robotic precision spray application in vegetable farms, accurate plant phenotyping through instance segmentation and robust plant tracking are of great importance and a prerequisite for the following spray action. Regarding the robust tracking of vegetable plants, to solve the challenging problem of associating vegetables with similar color and texture in consecutive images, in this paper, a novel method of Multiple Object Tracking and Segmentation (MOTS) is proposed for instance segmentation and tracking of multiple vegetable plants. In our approach, contour and blob features are extracted to describe unique feature of each individual vegetable, and associate the same vegetables in different images. By assigning a unique ID for each vegetable, it ensures the robot to spray each vegetable exactly once, while traversing along the farm rows. Comprehensive experiments including ablation studies are conducted, which prove its superior performance over two State-Of-The-Art (SOTA) MOTS methods. Compared to the conventional MOTS methods, the proposed method is able to re-identify objects which have gone out of the camera field of view and re-appear again using the proposed data association strategy, which is important to ensure each vegetable be sprayed only once when the robot travels back and forth. Although the method is tested on lettuce farm, it can be applied to other similar vegetables such as broccoli and canola. Both code and the dataset of this paper is publicly released for the benefit of the community: https://github.com/NanH5837/LettuceMOTS.

Large-scale pre-trained language models (PLMs) such as BERT have recently achieved great success and become a milestone in natural language processing (NLP). It is now the consensus of the NLP community to adopt PLMs as the backbone for downstream tasks. In recent works on knowledge graph question answering (KGQA), BERT or its variants have become necessary in their KGQA models. However, there is still a lack of comprehensive research and comparison of the performance of different PLMs in KGQA. To this end, we summarize two basic KGQA frameworks based on PLMs without additional neural network modules to compare the performance of nine PLMs in terms of accuracy and efficiency. In addition, we present three benchmarks for larger-scale KGs based on the popular SimpleQuestions benchmark to investigate the scalability of PLMs. We carefully analyze the results of all PLMs-based KGQA basic frameworks on these benchmarks and two other popular datasets, WebQuestionSP and FreebaseQA, and find that knowledge distillation techniques and knowledge enhancement methods in PLMs are promising for KGQA. Furthermore, we test ChatGPT, which has drawn a great deal of attention in the NLP community, demonstrating its impressive capabilities and limitations in zero-shot KGQA. We have released the code and benchmarks to promote the use of PLMs on KGQA., Comment: Accepted by World Wide Web Journal

ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural language question answering using its own knowledge. Therefore, there is growing interest in exploring whether ChatGPT can replace traditional knowledge-based question answering (KBQA) models. Although there have been some works analyzing the question answering performance of ChatGPT, there is still a lack of large-scale, comprehensive testing of various types of complex questions to analyze the limitations of the model. In this paper, we present a framework that follows the black-box testing specifications of CheckList proposed by Ribeiro et. al. We evaluate ChatGPT and its family of LLMs on eight real-world KB-based complex question answering datasets, which include six English datasets and two multilingual datasets. The total number of test cases is approximately 190,000. In addition to the GPT family of LLMs, we also evaluate the well-known FLAN-T5 to identify commonalities between the GPT family and other LLMs. The dataset and code are available at https://github.com/tan92hl/Complex-Question-Answering-Evaluation-of-GPT-family.git, Comment: To be published in Proceedings of ISWC 2023, 22nd International Semantic Web Conference

Intelligent edge network is maturing to enable smart and efficient transportation systems. In this letter, we consider unmanned aerial vehicle (UAV)-assisted vehicular networks where UAVs provide caching and computing services in complement with base station (BS). One major challenge is that vehicles need to obtain timely situational awareness via orchestration of ubiquitous caching and computing resources. Note that cached data for vehicles' perception tasks contains time-varying context information, thus freshness of cached data should be considered in conjunction with task execution to guarantee timeliness of obtained status updates. To this end, we propose a two-stage performance metric to quantify the impact of cache refreshing and computation offloading decisions on the age of status updates. We formulate an energy minimization problem by jointly considering cache refreshing, computation offloading and aging of status updates. To facilitate online decision making, we propose a deep deterministic policy gradient(DDPG)-based solution procedure and incorporate differentiated experience replay mechanism to accelerate convergence. Simulation results show that the performance of proposed solution is competitive in terms of energy consumption for obtaining fresh status updates.

Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or bag-level de-noising techniques independently, neglecting the explicit interaction with cross levels. In this paper, we propose a hierarchical contrastive learning Framework for Distantly Supervised relation extraction (HiCLRE) to reduce noisy sentences, which integrate the global structural information and local fine-grained interaction. Specifically, we propose a three-level hierarchical learning framework to interact with cross levels, generating the de-noising context-aware representations via adapting the existing multi-head self-attention, named Multi-Granularity Recontextualization. Meanwhile, pseudo positive samples are also provided in the specific level for contrastive learning via a dynamic gradient-based data augmentation strategy, named Dynamic Gradient Adversarial Perturbation. Experiments demonstrate that HiCLRE significantly outperforms strong baselines in various mainstream DSRE datasets.

Knowledge-Enhanced Pre-trained Language Models (KEPLMs) are pre-trained models with relation triples injecting from knowledge graphs to improve language understanding abilities. To guarantee effective knowledge injection, previous studies integrate models with knowledge encoders for representing knowledge retrieved from knowledge graphs. The operations for knowledge retrieval and encoding bring significant computational burdens, restricting the usage of such models in real-world applications that require high inference speed. In this paper, we propose a novel KEPLM named DKPLM that Decomposes Knowledge injection process of the Pre-trained Language Models in pre-training, fine-tuning and inference stages, which facilitates the applications of KEPLMs in real-world scenarios. Specifically, we first detect knowledge-aware long-tail entities as the target for knowledge injection, enhancing the KEPLMs' semantic understanding abilities and avoiding injecting redundant information. The embeddings of long-tail entities are replaced by "pseudo token representations" formed by relevant knowledge triples. We further design the relational knowledge decoding task for pre-training to force the models to truly understand the injected knowledge by relation triple reconstruction. Experiments show that our model outperforms other KEPLMs significantly over zero-shot knowledge probing tasks and multiple knowledge-aware language understanding tasks. We further show that DKPLM has a higher inference speed than other competing models due to the decomposing mechanism., Comment: Accepted by AAAI22

The near-unity system detection efficiency (SDE) and excellent timing resolution of superconducting nanowire single-photon detectors (SNSPDs), combined with their other merits, have enabled many classical and quantum photonic applications. However, the prevalent design based on meandering nanowires makes SDE dependent on the polarization states of the incident photons; for unpolarized light, the major merit of high SDE would get compromised, which could be detrimental for photon-starved applications. Here, we create SNSPDs with an arced fractal geometry that almost completely eliminates this polarization dependence of the SDE, and we experimentally demonstrate 84$\pm$3$\%$ SDE, 1.02$^{+0.06}_{-0.02}$ polarization sensitivity at the wavelength of 1575 nm, and 20.8 ps timing jitter in a 0.1-W closed-cycle Gifford-McMahon cryocooler, at the base temperature of 2.0 K. This demonstration provides a novel, practical device structure of SNSPDs, allowing for operation in the visible, near-, and mid-infrared spectral ranges, and paves the way for polarization-insensitive single-photon detection with high SDE and high timing resolution, Comment: 8 pages, 4 figures

Statistical shape modeling (SSM) is widely used in biology and medicine as a new generation of morphometric approaches for the quantitative analysis of anatomical shapes. Technological advancements of in vivo imaging have led to the development of open-source computational tools that automate the modeling of anatomical shapes and their population-level variability. However, little work has been done on the evaluation and validation of such tools in clinical applications that rely on morphometric quantifications (e.g., implant design and lesion screening). Here, we systematically assess the outcome of widely used, state-of-the-art SSM tools, namely ShapeWorks, Deformetrica, and SPHARM-PDM. We use both quantitative and qualitative metrics to evaluate shape models from different tools. We propose validation frameworks for anatomical landmark/measurement inference and lesion screening. We also present a lesion screening method to objectively characterize subtle abnormal shape changes with respect to learned population-level statistics of controls. Results demonstrate that SSM tools display different levels of consistencies, where ShapeWorks and Deformetrica models are more consistent compared to models from SPHARM-PDM due to the groupwise approach of estimating surface correspondences. Furthermore, ShapeWorks and Deformetrica shape models are found to capture clinically relevant population-level variability compared to SPHARM-PDM models., Comment: 22 pages, 22 figures

Magnetic-responsive composites that consist of soft matrix embedded with hard-magnetic particles have recently been demonstrated as robust soft active materials for fast-transforming actuation. However, the deformation of the functional components commonly attains only a single actuation mode under external stimuli, which limits their capability of achieving tunable properties. To greatly enhance the versatility of soft active materials, we exploit a new class of programmable magnetic-responsive composites incorporated with a multifunctional joint design that allows asymmetric multimodal actuation under an external stimulation. We demonstrate that the proposed asymmetric multimodal actuation enables a plethora of novel applications ranging from the basic 1D/2D active structures with asymmetric shape-shifting to biomimetic crawling and swimming robots with efficient dynamic performance as well as 2D metamaterials with tunable properties. This new asymmetric multimodal actuation mechanism will open new avenues for the design of next-generation multifunctional soft robots, biomedical devices, and acoustic metamaterials.

Heavy metal pollution is a severe environmental problem affecting many water resources. The non-biodegradable nature of the heavy metals such as lead (Pb) causes severe human health issues, so their cost-effective, sensitive and rapid detection is needed. In this work, we describe a simple, facile and low cost modifications of multiwalled carbon nanotubes (MWCNT) and \b{eta}-cyclodextrin (\b{eta}CD) through non-covalent/physical (Phys) and a covalent Steglich esterification (SE) approaches. The Phys modification approach resulted Pb detection with a limit-of-detection (LoD) of 0.9 ppb, while the SE approach showed an LoD of 2.3 ppb, both of which are well below the WHO Pb concentration guideline of 10 ppb. The MWCNT-\b{eta}CD (Phys) based electrodes show negligible interference with other common heavy metal ions such as Cd2+ and Zn2+. The MWCNT-\b{eta}CD based electrodes were of low-cost owing to their simple synthesis approaches, exhibited good selectivity and reusability. The proposed MWCNT-\b{eta}CD based electrodes is a promising technology in developing a highly affordable and sensitive electrochemical sensing system of Pb in drinking water.

In this paper, we consider the weighted graph matching problem with partially disclosed correspondences between a number of anchor nodes. Our construction exploits recently introduced node signatures based on graph Laplacians, namely the Laplacian family signature (LFS) on the nodes, and the pairwise heat kernel map on the edges. In this paper, without assuming an explicit form of parametric dependence nor a distance metric between node signatures, we formulate an optimization problem which incorporates the knowledge of anchor nodes. Solving this problem gives us an optimized proximity measure specific to the graphs under consideration. Using this as a first order compatibility term, we then set up an integer quadratic program (IQP) to solve for a near optimal graph matching. Our experiments demonstrate the superior performance of our approach on randomly generated graphs and on two widely-used image sequences, when compared with other existing signature and adjacency matrix based graph matching methods., Comment: final version for CVPR2013

In this paper we propose an optimization-based framework to multiple object matching. The framework takes maps computed between pairs of objects as input, and outputs maps that are consistent among all pairs of objects. The central idea of our approach is to divide the input object collection into overlapping sub-collections and enforce map consistency among each sub-collection. This leads to a distributed formulation, which is scalable to large-scale datasets. We also present an equivalence condition between this decoupled scheme and the original scheme. Experiments on both synthetic and real-world datasets show that our framework is competitive against state-of-the-art multi-object matching techniques., Comment: Final version for CVPR2018

The Random Particle Mesh (RPM) method used to simulate turbulence-induced broadband noise in several aeroacoustic applications is extended to realise isotropic turbulence spectra. With this method turbulent fluctuations are synthesised by filtering white noise with a Gaussian filter kernel that in turn gives a Gaussian spectrum. The Gaussian function is smooth and its derivatives and integrals are again Gaussian functions. The Gaussian filter is efficient and finds wide-spread applications in stochastic signal processing. However in many applications Gaussian spectra do not correspond to real turbulence spectra. Thus in turbo-machines the von K\'arm\'an, Liepmann, and modified von K\'arm\'an spectra are more realistic model spectra. In this note we analytically derive weighting functions to realise arbitrary isotropic solenoidal spectra using a superposition of weighted Gaussian spectra of different length scales. The analytic weighting functions for the von K\'arm\'an, the Liepmann, and the modified von K\'arm\'an spectra are derived subsequently. Finally a method is proposed to discretise the problem using a limited number of Gaussian spectra. The effectivity of this approach is demonstrated by realising a von K\'arm\'an velocity spectrum using the RPM method., Comment: Preprint, submitted to Computers & Fluids

In this paper, we consider the approximate weighted graph matching problem and introduce stable and informative first and second order compatibility terms suitable for inclusion into the popular integer quadratic program formulation. Our approach relies on a rigorous analysis of stability of spectral signatures based on the graph Laplacian. In the case of the first order term, we derive an objective function that measures both the stability and informativeness of a given spectral signature. By optimizing this objective, we design new spectral node signatures tuned to a specific graph to be matched. We also introduce the pairwise heat kernel distance as a stable second order compatibility term; we justify its plausibility by showing that in a certain limiting case it converges to the classical adjacency matrix-based second order compatibility function. We have tested our approach on a set of synthetic graphs, the widely-used CMU house sequence, and a set of real images. These experiments show the superior performance of our first and second order compatibility terms as compared with the commonly used ones., Comment: final version for CVPR2014

A method for the theoretical determination of the lifetime of com- pressed plates at elevated temperatures is presented. In this approach, linearized equations are used throughout with the assumption that the plate material is a standard linear solid. The critical time (lifetime) is determined by reducing the time-dependent behavior to the time- independent response of purely elastic buckling. Theoretically predicted lifetimes of 2024-T3 (formerly 24S-T3) aluminum-alloy plates at 450 F are compared with experimental values obtained in previous work.