Searcharxiv⌕ Search

arXiv subjects

Liang Wu

Publications and source records attributed to Liang Wu.

At least 109 records · Page 6Linked to original sources
arXiv2024

A direct optimization algorithm for input-constrained MPC

Providing an execution time certificate is a pressing requirement when deploying Model Predictive Control (MPC) in real-time embedded systems such as microcontrollers. Real-time MPC requires that its worst-case (maximum) execution time must be theoretically guaranteed to be smaller than the sampling time in closed-loop. This technical note considers input-constrained MPC problems and exploits the structure of the resulting box-constrained QPs. Then, we propose a \textit{cost-free} and \textit{data-independent} initialization strategy, which enables us, for the first time, to remove the initialization assumption of feasible full-Newton interior-point algorithms. We prove that the number of iterations of our proposed algorithm is \textit{only dimension-dependent} (\textit{data-independent}), \textit{simple-calculated}, and \textit{exact} (not \textit{worst-case}) with the value $\left\lceil\frac{\log(\frac{2n}ε)}{-2\log(\frac{\sqrt{2n}}{\sqrt{2n}+\sqrt{2}-1})}\right\rceil \!+ 1$, where $n$ denotes the problem dimension and $ε$ denotes the constant stopping tolerance. These features enable our algorithm to trivially certify the execution time of nonlinear MPC (via online linearized schemes) or adaptive MPC problems. The execution-time-certified capability of our algorithm is theoretically and numerically validated through an open-loop unstable AFTI-16 example.

math.OC↗
arXiv2024

Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines

On modern industrial assembly lines, many intelligent algorithms have been developed to replace or supervise workers. However, we found that there were bottlenecks in both training datasets and real-time performance when deploying algorithms on actual assembly line. Therefore, we developed a promising strategy for expanding industrial datasets, which utilized large models with strong generalization abilities to achieve efficient, high-quality, and large-scale dataset expansion, solving the problem of insufficient and low-quality industrial datasets. We also applied this strategy to video action recognition. We proposed a method of converting hand action recognition problems into hand skeletal trajectory classification problems, which solved the real-time performance problem of industrial algorithms. In the "hand movements during wire insertion" scenarios on the actual assembly line, the accuracy of hand action recognition reached 98.8\%. We conducted detailed experimental analysis to demonstrate the effectiveness and superiority of the method, and deployed the entire process on Midea's actual assembly line.

cs.CV↗
arXiv2024

Time-certified Input-constrained NMPC via Koopman Operator

Determining solving-time certificates of nonlinear model predictive control (NMPC) implementations is a pressing requirement when deploying NMPC in production environments. Such a certificate guarantees that the NMPC controller returns a solution before the next sampling time. However, NMPC formulations produce nonlinear programs (NLPs) for which it is very difficult to derive their solving-time certificates. Our previous work, Wu and Braatz (2023), challenged this limitation with a proposed input-constrained MPC algorithm having exact iteration complexity but was restricted to linear MPC formulations. This work extends the algorithm to solve input-constrained NMPC problems, by using the Koopman operator and a condensing MPC technique. We illustrate the algorithm performance on a high-dimensional, nonlinear partial differential equation (PDE) control case study, in which we theoretically and numerically certify the solving time to be less than the sampling time.

math.OC↗
arXiv2024

An Execution-time-certified Riccati-based IPM Algorithm for RTI-based Input-constrained NMPC

Establishing an execution time certificate in deploying model predictive control (MPC) is a pressing and challenging requirement. As nonlinear MPC (NMPC) results in nonlinear programs, differing from quadratic programs encountered in linear MPC, deriving an execution time certificate for NMPC seems an impossible task. Our prior work \cite{wu2023direct} introduced an input-constrained MPC algorithm with the exact and only \textit{dimension-dependent} (\textit{data-independent}) number of floating-point operations ([flops]). This paper extends it to input-constrained NMPC problems via the real-time iteration (RTI) scheme, which results in \textit{data-varying} (but \textit{dimension-invariant}) input-constrained MPC problems. Therefore, applying our previous algorithm can certify the execution time based on the assumption that processors perform fixed [flops] in constant time. As the RTI-based scheme generally results in MPC with a long prediction horizon, this paper employs the efficient factorized Riccati recursion, whose computational cost scales linearly with the prediction horizon, to solve the Newton system at each iteration. The execution-time certified capability of the algorithm is theoretically and numerically validated through a case study involving nonlinear control of the chaotic Lorenz system.

eess.SY↗
arXiv2024

Collaborative Large Language Model for Recommender Systems

Recently, there has been growing interest in developing the next-generation recommender systems (RSs) based on pretrained large language models (LLMs). However, the semantic gap between natural language and recommendation tasks is still not well addressed, leading to multiple issues such as spuriously correlated user/item descriptors, ineffective language modeling on user/item data, inefficient recommendations via auto-regression, etc. In this paper, we propose CLLM4Rec, the first generative RS that tightly integrates the LLM paradigm and ID paradigm of RSs, aiming to address the above challenges simultaneously. We first extend the vocabulary of pretrained LLMs with user/item ID tokens to faithfully model user/item collaborative and content semantics. Accordingly, a novel soft+hard prompting strategy is proposed to effectively learn user/item collaborative/content token embeddings via language modeling on RS-specific corpora, where each document is split into a prompt consisting of heterogeneous soft (user/item) tokens and hard (vocab) tokens and a main text consisting of homogeneous item tokens or vocab tokens to facilitate stable and effective language modeling. In addition, a novel mutual regularization strategy is introduced to encourage CLLM4Rec to capture recommendation-related information from noisy user/item content. Finally, we propose a novel recommendation-oriented finetuning strategy for CLLM4Rec, where an item prediction head with multinomial likelihood is added to the pretrained CLLM4Rec backbone to predict hold-out items based on soft+hard prompts established from masked user-item interaction history, where recommendations of multiple items can be generated efficiently without hallucination. Codes are released at https://github.com/yaochenzhu/llm4rec.

cs.IR↗
arXiv2024

LinkSAGE: Optimizing Job Matching Using Graph Neural Networks

We present LinkSAGE, an innovative framework that integrates Graph Neural Networks (GNNs) into large-scale personalized job matching systems, designed to address the complex dynamics of LinkedIns extensive professional network. Our approach capitalizes on a novel job marketplace graph, the largest and most intricate of its kind in industry, with billions of nodes and edges. This graph is not merely extensive but also richly detailed, encompassing member and job nodes along with key attributes, thus creating an expansive and interwoven network. A key innovation in LinkSAGE is its training and serving methodology, which effectively combines inductive graph learning on a heterogeneous, evolving graph with an encoder-decoder GNN model. This methodology decouples the training of the GNN model from that of existing Deep Neural Nets (DNN) models, eliminating the need for frequent GNN retraining while maintaining up-to-date graph signals in near realtime, allowing for the effective integration of GNN insights through transfer learning. The subsequent nearline inference system serves the GNN encoder within a real-world setting, significantly reducing online latency and obviating the need for costly real-time GNN infrastructure. Validated across multiple online A/B tests in diverse product scenarios, LinkSAGE demonstrates marked improvements in member engagement, relevance matching, and member retention, confirming its generalizability and practical impact.

cs.LG↗
arXiv2023

Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey

Although the applications of artificial intelligence especially deep learning had greatly improved various aspects of intelligent manufacturing, they still face challenges for wide employment due to the poor generalization ability, difficulties to establish high-quality training datasets, and unsatisfactory performance of deep learning methods. The emergence of large scale foundational models(LSFMs) had triggered a wave in the field of artificial intelligence, shifting deep learning models from single-task, single-modal, limited data patterns to a paradigm encompassing diverse tasks, multimodal, and pre-training on massive datasets. Although LSFMs had demonstrated powerful generalization capabilities, automatic high-quality training dataset generation and superior performance across various domains, applications of LSFMs on intelligent manufacturing were still in their nascent stage. A systematic overview of this topic was lacking, especially regarding which challenges of deep learning can be addressed by LSFMs and how these challenges can be systematically tackled. To fill this gap, this paper systematically expounded current statue of LSFMs and their advantages in the context of intelligent manufacturing. and compared comprehensively with the challenges faced by current deep learning models in various intelligent manufacturing applications. We also outlined the roadmaps for utilizing LSFMs to address these challenges. Finally, case studies of applications of LSFMs in real-world intelligent manufacturing scenarios were presented to illustrate how LSFMs could help industries, improve their efficiency.

cs.AI↗
arXiv2023

AI-driven emergence of frequency information non-uniform distribution via THz metasurface spectrum prediction

Recently, artificial intelligence has been extensively deployed across various scientific disciplines, optimizing and guiding the progression of experiments through the integration of abundant datasets, whilst continuously probing the vast theoretical space encapsulated within the data. Particularly, deep learning models, due to their end-to-end adaptive learning capabilities, are capable of autonomously learning intrinsic data features, thereby transcending the limitations of traditional experience to a certain extent. Here, we unveil previously unreported information characteristics pertaining to different frequencies emerged during our work on predicting the terahertz spectral modulation effects of metasurfaces based on AI-prediction. Moreover, we have substantiated that our proposed methodology of simply adding supplementary multi-frequency inputs to the existing dataset during the target spectral prediction process can significantly enhance the predictive accuracy of the network. This approach effectively optimizes the utilization of existing datasets and paves the way for interdisciplinary research and applications in artificial intelligence, chemistry, composite material design, biomedicine, and other fields.

cs.LG↗
arXiv2023

Multifunctional magnetic oxide-MoS$_2$ heterostructures on silicon

Correlated oxides and related heterostructures are intriguing for developing future multifunctional devices by exploiting their exotic properties, but their integration with other materials, especially on Si-based platforms, is challenging. Here, van der Waals heterostructures of La$_{0.7}$Sr$_{0.3}$MnO$_3$ (LSMO), a correlated manganite perovskite, and MoS$_2$ are demonstrated on Si substrates with multiple functions. To overcome the problems due to the incompatible growth process, technologies involving freestanding LSMO membranes and van der Waals force-mediated transfer are used to fabricate the LSMO-MoS$_2$ heterostructures. The LSMO-MoS$_2$ heterostructures exhibit a gate-tunable rectifying behavior, based on which metal-semiconductor field-effect transistors (MESFETs) with on-off ratios of over 104 can be achieved. The LSMO-MoS$_2$ heterostructures can function as photodiodes displaying considerable open-circuit voltages and photocurrents. In addition, the colossal magnetoresistance of LSMO endows the LSMO-MoS$_2$ heterostructures with an electrically tunable magnetoresponse at room temperature. This work not only proves the applicability of the LSMO-MoS$_2$ heterostructure devices on Si-based platform but also demonstrates a paradigm to create multifunctional heterostructures from materials with disparate properties.

cond-mat.str-el↗
arXiv2023

MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a novel approach MaskOCR to unify vision and language pre-training in the classical encoder-decoder recognition framework. We adopt the masked image modeling approach to pre-train the feature encoder using a large set of unlabeled real text images, which allows us to learn strong visual representations. In contrast to introducing linguistic knowledge with an additional language model, we directly pre-train the sequence decoder. Specifically, we transform text data into synthesized text images to unify the data modalities of vision and language, and enhance the language modeling capability of the sequence decoder using a proposed masked image-language modeling scheme. Significantly, the encoder is frozen during the pre-training phase of the sequence decoder. Experimental results demonstrate that our proposed method achieves superior performance on benchmark datasets, including Chinese and English text images.

cs.CV↗
arXiv2023

GraphLLM: Boosting Graph Reasoning Ability of Large Language Model

The advancement of Large Language Models (LLMs) has remarkably pushed the boundaries towards artificial general intelligence (AGI), with their exceptional ability on understanding diverse types of information, including but not limited to images and audio. Despite this progress, a critical gap remains in empowering LLMs to proficiently understand and reason on graph data. Recent studies underscore LLMs' underwhelming performance on fundamental graph reasoning tasks. In this paper, we endeavor to unearth the obstacles that impede LLMs in graph reasoning, pinpointing the common practice of converting graphs into natural language descriptions (Graph2Text) as a fundamental bottleneck. To overcome this impediment, we introduce GraphLLM, a pioneering end-to-end approach that synergistically integrates graph learning models with LLMs. This synergy equips LLMs with the ability to proficiently interpret and reason on graph data, harnessing the superior expressive power of graph learning models. Our empirical evaluations across four fundamental graph reasoning tasks validate the effectiveness of GraphLLM. The results exhibit a substantial average accuracy enhancement of 54.44%, alongside a noteworthy context reduction of 96.45% across various graph reasoning tasks.

cs.CL↗
arXiv2023

Parallel in-memory wireless computing

Parallel wireless digital communication with ultralow power consumption is critical for emerging edge technologies such as 5G and Internet of Things. However, the physical separation between digital computing units and analogue transmission units in traditional wireless technology leads to high power consumption. Here we report a parallel in-memory wireless computing scheme. The approach combines in-memory computing with wireless communication using memristive crossbar arrays. We show that the system can be used for the radio transmission of a binary stream of 480 bits with a bit error rate of 0. The in-memory wireless computing uses two orders of magnitude less power than conventional technology (based on digital-to-analogue and analogue-to-digital converters). We also show that the approach can be applied to acoustic and optical wireless communications

cs.AR↗
arXiv2023

Three-state nematicity and magneto-optical Kerr effect in the charge density waves in kagome superconductors

The kagome lattice provides a fascinating playground to study geometrical frustration, topology and strong correlations. The newly-discovered kagome metals AV$_3$Sb$_5$ (where A can refer to K, Rb, or Cs) exhibit phenomena including topological band structure, symmetry-breaking charge-density waves and superconductivity. Nevertheless, the nature of the symmetry breaking in the charge-density wave phase is not yet clear, despite the fact that it is crucial in order to understand whether the superconductivity is unconventional. In this work, we perform scanning birefringence microscopy on all three members of this family and find that six-fold rotation symmetry is broken at the onset of the charge-density wave transition in all these compounds. We show that the three nematic domains are oriented at 120$^\circ$ to each other and propose that staggered charge-density wave orders with a relative $π$ phase shift between layers is a possibility that can explain these observations. We also perform magneto-optical Kerr effect and circular dichroism measurements. The onset of both signals is at the transition temperature, indicating broken time-reversal symmetry and the existence of the long-sought loop currents in that phase.

cond-mat.str-el↗
arXiv2023

Signatures of Z$_3$ Vestigial Potts-nematic order in van der Waals antiferromagnets

Layered van der Waals magnets have attracted much recent attention as a promising and versatile platform for exploring intrinsic two-dimensional magnetism. Within this broader class, the transition metal phosphorous trichalcogenides $M$P$X_3$ stand out as particularly interesting, as they provide a realization of honeycomb lattice magnetism and are known to display a variety of magnetic ordering phenomena as well as superconductivity under pressure. One example, found in a number of different materials, is commensurate single-$Q$ zigzag antiferromagnetic order, which spontaneously breaks the spatial threefold $(C_3)$ rotation symmetry of the honeycomb lattice. The breaking of multiple distinct symmetries in the magnetic phase suggests the possibility of a sequence of distinct transitions as a function of temperature, and a resulting intermediate $\mathbb{Z}_3$-nematic phase which exists as a paramagnetic vestige of zigzag magnetic order -- a scenario known as vestigial ordering. Here, we report the observation of key signatures of vestigial Potts-nematic order in rhombohedral FePSe$_3$. By performing linear dichroism imaging measurements -- an ideal probe of rotational symmetry breaking -- we find that the $C_3$ symmetry is already broken above the Néel temperature. We show that these observations are explained by a general Ginzburg-Landau model of vestigial nematic order driven by magnetic fluctuations and coupled to residual strain. An analysis of the domain structure as temperature is lowered and a comparison with zigzag-ordered monoclinic FePS$_3$ reveals a broader applicability of the Ginzburg-Landau model in the presence of external strain, and firmly establishes the $M$P$X_3$ magnets as a new experimental venue for studying the interplay between Potts-nematicity, magnetism and superconductivity.

cond-mat.str-el↗
arXiv2023

Channel Modeling for Heterogeneous Vehicular ISAC System with Shared Clusters

In this paper, we consider the channel modeling of a heterogeneous vehicular integrated sensing and communication (ISAC) system, where a dual-functional multi-antenna base station (BS) intends to communicate with a multi-antenna vehicular receiver (MR) and sense the surrounding environments simultaneously. The time-varying complex channel impulse responses (CIRs) of the sensing and communication channels are derived, respectively, in which the sensing and communication channels are correlated with shared clusters. The proposed models show great generality for the capability in covering both monostatic and bistatic sensing scenarios, and as well for considering both static clusters/targets and mobile clusters/targets. Important channel statistical characteristics, including time-varying spatial cross-correlation function (CCF) and temporal auto-correlation function (ACF), are derived and analyzed. Numerically results are provided to show the propagation characteristics of the proposed ISAC channel model. Finally, the proposed model is validated via the agreement between theoretical and simulated as well as measurement results.

eess.SP↗
arXiv2023

Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning

Objective: The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM). However, designing an effective control policy for the AP remains challenging due to the complex physiological processes, delayed insulin response, and inaccurate glucose measurements. While model predictive control (MPC) offers safety and stability through the dynamic model and safety constraints, it lacks individualization and is adversely affected by unannounced meals. Conversely, deep reinforcement learning (DRL) provides personalized and adaptive strategies but faces challenges with distribution shifts and substantial data requirements. Methods: We propose a hybrid control policy for the artificial pancreas (HyCPAP) to address the above challenges. HyCPAP combines an MPC policy with an ensemble DRL policy, leveraging the strengths of both policies while compensating for their respective limitations. To facilitate faster deployment of AP systems in real-world settings, we further incorporate meta-learning techniques into HyCPAP, leveraging previous experience and patient-shared knowledge to enable fast adaptation to new patients with limited available data. Results: We conduct extensive experiments using the FDA-accepted UVA/Padova T1DM simulator across three scenarios. Our approaches achieve the highest percentage of time spent in the desired euglycemic range and the lowest occurrences of hypoglycemia. Conclusion: The results clearly demonstrate the superiority of our methods for closed-loop glucose management in individuals with T1DM. Significance: The study presents novel control policies for AP systems, affirming the great potential of proposed methods for efficient closed-loop glucose control.

cs.AI↗
arXiv2023

Downlink Precoding for Cell-free FBMC/OQAM Systems With Asynchronous Reception

In this work, an efficient precoding design scheme is proposed for downlink cell-free distributed massive multiple-input multiple-output (DM-MIMO) filter bank multi-carrier (FBMC) systems with asynchronous reception and highly frequency selectivity. The proposed scheme includes a multiple interpolation structure to eliminate the impact of response difference we recently discovered, which has better performance in highly frequency-selective channels. Besides, we also consider the phase shift in asynchronous reception and introduce a phase compensation in the design process. The phase compensation also benefits from the multiple interpolation structure and better adapts to asynchronous reception. Based on the proposed scheme, we theoretically analyze its ergodic achievable rate performance and derive a closed-form expression. Simulation results show that the derived expression can accurately characterize the rate performance, and FBMC with the proposed scheme outperforms orthogonal frequency-division multiplexing (OFDM) in the asynchronous scenario.

cs.IT↗
arXiv2023

Reversible Non-Volatile Electronic Switching in a Near Room Temperature van der Waals Ferromagnet

The ability to reversibly toggle between two distinct states in a non-volatile method is important for information storage applications. Such devices have been realized for phase-change materials, which utilizes local heating methods to toggle between a crystalline and an amorphous state with distinct electrical properties. To expand such kind of switching between two topologically distinct phases requires non-volatile switching between two crystalline phases with distinct symmetries. Here we report the observation of reversible and non-volatile switching between two stable and closely-related crystal structures with remarkably distinct electronic structures in the near room temperature van der Waals ferromagnet Fe$_{5-δ}$GeTe$_2$. From a combination of characterization techniques we show that the switching is enabled by the ordering and disordering of an Fe site vacancy that results in distinct crystalline symmetries of the two phases that can be controlled by a thermal annealing and quenching method. Furthermore, from symmetry analysis as well as first principle calculations, we provide understanding of the key distinction in the observed electronic structures of the two phases: topological nodal lines compatible with the preserved global inversion symmetry in the site-disordered phase, and flat bands resulting from quantum destructive interference on a bipartite crystaline lattice formed by the presence of the site order as well as the lifting of the topological degeneracy due to the broken inversion symmetry in the site-ordered phase. Our work not only reveals a rich variety of quantum phases emergent in the metallic van der Waals ferromagnets due to the presence of site ordering, but also demonstrates the potential of these highly tunable two-dimensional magnets for memory and spintronics applications.

cond-mat.str-el↗