arXiv subjects

Liang Xu

Publications and source records attributed to Liang Xu.

At least 73 records · Page 4Linked to original sources

arXiv2024

Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble

As real-world knowledge is constantly evolving, ensuring the timeliness and accuracy of a model's knowledge is crucial. This has made knowledge editing in large language models increasingly important. However, existing knowledge editing methods face several challenges, including parameter localization coupling, imprecise localization, and a lack of dynamic interaction across layers. In this paper, we propose a novel knowledge editing method called Knowledge Neuronal Ensemble (KNE). A knowledge neuronal ensemble represents a group of neurons encoding specific knowledge, thus mitigating the issue of frequent parameter modification caused by coupling in parameter localization. The KNE method enhances the precision and accuracy of parameter localization by computing gradient attribution scores for each parameter at each layer. During the editing process, only the gradients and losses associated with the knowledge neuronal ensemble are computed, with error backpropagation performed accordingly, ensuring dynamic interaction and collaborative updates among parameters. Experimental results on three widely used knowledge editing datasets show that the KNE method significantly improves the accuracy of knowledge editing and achieves, or even exceeds, the performance of the best baseline methods in portability and locality metrics.

cs.CL↗

arXiv2024

Hyperparameter Tuning Through Pessimistic Bilevel Optimization

Automated hyperparameter search in machine learning, especially for deep learning models, is typically formulated as a bilevel optimization problem, with hyperparameter values determined by the upper level and the model learning achieved by the lower-level problem. Most of the existing bilevel optimization solutions either assume the uniqueness of the optimal training model given hyperparameters or adopt an optimistic view when the non-uniqueness issue emerges. Potential model uncertainty may arise when training complex models with limited data, especially when the uniqueness assumption is violated. Thus, the suitability of the optimistic view underlying current bilevel hyperparameter optimization solutions is questionable. In this paper, we propose pessimistic bilevel hyperparameter optimization to assure appropriate outer-level hyperparameters to better generalize the inner-level learned models, by explicitly incorporating potential uncertainty of the inner-level solution set. To solve the resulting computationally challenging pessimistic bilevel optimization problem, we develop a novel relaxation-based approximation method. It derives pessimistic solutions with more robust prediction models. In our empirical studies of automated hyperparameter search for binary linear classifiers, pessimistic solutions have demonstrated better prediction performances than optimistic counterparts when we have limited training data or perturbed testing data, showing the necessity of considering pessimistic solutions besides existing optimistic ones.

cs.LG↗

arXiv2024

Multi-scale Vehicle Localization In Heterogeneous Mobile Communication Networks

Low-latency and high-precision vehicle localization plays a significant role in enhancing traffic safety and improving traffic management for intelligent transportation. However, in complex road environments, the low latency and high precision requirements could not always be fulfilled due to the high complexity of localization computation. To tackle this issue, we propose a road-aware localization mechanism in heterogeneous networks (HetNet) of the mobile communication system, which enables real-time acquisition of vehicular position information, including the vehicular current road, segment within the road, and coordinates. By employing this multi-scale localization approach, the computational complexity can be greatly reduced while ensuring accurate positioning. Specifically, to reduce positioning search complexity and ensure positioning precision, roads are partitioned into low-dimensional segments with unequal lengths by the proposed singular point (SP) segmentation method. To reduce feature-matching complexity, distinctive salient features (SFs) are extracted sparsely representing roads and segments, which can eliminate redundant features while maximizing the feature information gain. The Cramér-Rao Lower Bound (CRLB) of vehicle positioning errors is derived to verify the positioning accuracy improvement brought from the segment partition and SF extraction. Additionally, through SF matching by integrating the inclusion and adjacency position relationships, a multi-scale vehicle localization (MSVL) algorithm is proposed to identify vehicular road signal patterns and determine the real-time segment and coordinates. Simulation results show that the proposed multi-scale localization mechanism can achieve lower latency and high precision compared to the benchmark schemes.

eess.SP↗

arXiv2024

Achieving the Multi-parameter Quantum Cramér-Rao Bound with Antiunitary Symmetry

The estimation of multiple parameters is a ubiquitous requirement in many quantum metrology applications. However, achieving the ultimate precision limit, i.e. the quantum Cramér-Rao bound, becomes challenging in these scenarios compared to single parameter estimation. To address this issue, optimizing the parameters encoding strategies with the aid of antiunitary symmetry is a novel and comprehensive approach. For demonstration, we propose two types of quantum statistical models exhibiting antiunitary symmetry in experiments. The results showcase the simultaneous achievement of ultimate precision for multiple parameters without any trade-off and the precision is improved at least twice compared to conventional encoding strategies. Our work emphasizes the significant potential of antiunitary symmetry in addressing multi-parameter estimation problems.

quant-ph↗

arXiv2024

A machine learning enhanced discontinuous Galerkin method for simulating transonic airfoil flow-fields

Accurate and rapid prediction of flow-fields is crucial for aerodynamic design. This work proposes a discontinuous Galerkin method (DGM) whose performance enhances with increasing data, for rapid simulation of transonic flow around airfoils under various flow conditions. A lightweight and continuously updated data-driven model is built offline to predict the roughly correct flow-field, and the DGM is then utilized to refine the detailed flow structures and provide the corrected data. During the construction of the data-driven model, a zonal proper orthogonal decomposition (POD) method is designed to reduce the dimensionality of flow-field while preserving more near-wall flow features, and a weighted-distance radial basis function (RBF) is constructed to enhance the generalization capability of flow-field prediction. Numerical results demonstrate that the lightweight data-driven model can predict the flow-field around a wide range of airfoils at Mach numbers ranging from 0.7 to 0.95 and angles of attack from -5 to 5 degrees by learning from sparse data, and maintains high accuracy of the location and essential features of flow structures (such as shock waves). In addition, the machine learning (ML) enhanced DGM is able to significantly improve the computational efficiency and simulation robustness as compared to normal DGMs in simulating transonic inviscid/viscous airfoil flow-fields on arbitrary grids, and further enables rapid aerodynamic evaluation of numerous sample points during the surrogate-based aerodynamic optimization.

physics.flu-dyn↗

arXiv2024

MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations

In this paper, we tackle the problem of how to build and benchmark a large motion model (LMM). The ultimate goal of LMM is to serve as a foundation model for versatile motion-related tasks, e.g., human motion generation, with interpretability and generalizability. Though advanced, recent LMM-related works are still limited by small-scale motion data and costly text descriptions. Besides, previous motion benchmarks primarily focus on pure body movements, neglecting the ubiquitous motions in context, i.e., humans interacting with humans, objects, and scenes. To address these limitations, we consolidate large-scale video action datasets as knowledge banks to build MotionBank, which comprises 13 video action datasets, 1.24M motion sequences, and 132.9M frames of natural and diverse human motions. Different from laboratory-captured motions, in-the-wild human-centric videos contain abundant motions in context. To facilitate better motion text alignment, we also meticulously devise a motion caption generation algorithm to automatically produce rule-based, unbiased, and disentangled text descriptions via the kinematic characteristics for each motion. Extensive experiments show that our MotionBank is beneficial for general motion-related tasks of human motion generation, motion in-context generation, and motion understanding. Video motions together with the rule-based text annotations could serve as an efficient alternative for larger LMMs. Our dataset, codes, and benchmark will be publicly available at https://github.com/liangxuy/MotionBank.

cs.CV↗

arXiv2024

Structured Deep Neural Network-Based Backstepping Trajectory Tracking Control for Lagrangian Systems

Deep neural networks (DNN) are increasingly being used to learn controllers due to their excellent approximation capabilities. However, their black-box nature poses significant challenges to closed-loop stability guarantees and performance analysis. In this paper, we introduce a structured DNN-based controller for the trajectory tracking control of Lagrangian systems using backing techniques. By properly designing neural network structures, the proposed controller can ensure closed-loop stability for any compatible neural network parameters. In addition, improved control performance can be achieved by further optimizing neural network parameters. Besides, we provide explicit upper bounds on tracking errors in terms of controller parameters, which allows us to achieve the desired tracking performance by properly selecting the controller parameters. Furthermore, when system models are unknown, we propose an improved Lagrangian neural network (LNN) structure to learn the system dynamics and design the controller. We show that in the presence of model approximation errors and external disturbances, the closed-loop stability and tracking control performance can still be guaranteed. The effectiveness of the proposed approach is demonstrated through simulations.

cs.RO↗

arXiv2024

HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects

Generating human-object interactions (HOIs) is critical with the tremendous advances of digital avatars. Existing datasets are typically limited to humans interacting with a single object while neglecting the ubiquitous manipulation of multiple objects. Thus, we propose HIMO, a large-scale MoCap dataset of full-body human interacting with multiple objects, containing 3.3K 4D HOI sequences and 4.08M 3D HOI frames. We also annotate HIMO with detailed textual descriptions and temporal segments, benchmarking two novel tasks of HOI synthesis conditioned on either the whole text prompt or the segmented text prompts as fine-grained timeline control. To address these novel tasks, we propose a dual-branch conditional diffusion model with a mutual interaction module for HOI synthesis. Besides, an auto-regressive generation pipeline is also designed to obtain smooth transitions between HOI segments. Experimental results demonstrate the generalization ability to unseen object geometries and temporal compositions.

cs.CV↗

arXiv2024

Cooperative Global $\mathcal{K}$-exponential Tracking Control of Multiple Mobile Robots -- Extended Version

This paper studies the cooperative tracking control problem for multiple mobile robots over a directed communication network. First, it is shown that the closed-loop system is uniformly globally asymptotically stable under the proposed distributed continuous feedback control law, where an explicit strict Lyapunov function is constructed. Then, by investigating the convergence rate, it is further proven that the closed-loop system is globally $\mathcal{K}$-exponentially stable. Moreover, to make the proposed control law more practical, the distributed continuous feedback control law is generalized to a distributed sampled-data feedback control law using the emulation approach, based on the strong integral input-to-state stable Lyapunov function. Numerical simulations are presented to validate the effectiveness of the proposed control methods.

eess.SY↗

arXiv2024

SMPISD-MTPNet: Scene Semantic Prior-Assisted Infrared Ship Detection Using Multi-Task Perception Networks

Infrared ship detection (IRSD) has received increasing attention in recent years due to the robustness of infrared images to adverse weather. However, a large number of false alarms may occur in complex scenes. To address these challenges, we propose the Scene Semantic Prior-Assisted Multi-Task Perception Network (SMPISD-MTPNet), which includes three stages: scene semantic extraction, deep feature extraction, and prediction. In the scene semantic extraction stage, we employ a Scene Semantic Extractor (SSE) to guide the network by the features extracted based on expert knowledge. In the deep feature extraction stage, a backbone network is employed to extract deep features. These features are subsequently integrated by a fusion network, enhancing the detection capabilities across targets of varying sizes. In the prediction stage, we utilize the Multi-Task Perception Module, which includes the Gradient-based Module and the Scene Segmentation Module, enabling precise detection of small and dim targets within complex scenes. For the training process, we introduce the Soft Fine-tuning training strategy to suppress the distortion caused by data augmentation. Besides, due to the lack of a publicly available dataset labelled for scenes, we introduce the Infrared Ship Dataset with Scene Segmentation (IRSDSS). Finally, we evaluate the network and compare it with state-of-the-art (SOTA) methods, indicating that SMPISD-MTPNet outperforms existing approaches. The source code and dataset for this research can be accessed at https://github.com/greekinRoma/KMNDNet.

cs.CV↗

arXiv2024

Progress and Perspectives on Weak-value Amplification

Weak-value amplification (WVA) is a metrological protocol that effectively amplifies ultra-small physical effects, making it highly applicable in the fields of quantum sensing and metrology. However, the amplification effect is achieved through post-selection, which leads to a significant decrease in signal intensity. Consequently, there is a heated debate regarding the trade-off between the amplification effect and the success probability of post-selection, questioning whether WVA surpasses conventional measurement (CM) in terms of measurement precision. Extensive research indicates that the specific theoretical assumptions and experimental conditions play crucial roles in determining the respective advantages of WVA and CM. WVA provides new perspectives for recognizing the important role of post-selection in precision metrology. It demonstrates significant advantages in two aspects: (i) WVA based on the phase space interaction provides feasible strategies to practically achieve the Heisenberg-scaling precision using only classical resources. (ii) WVA exhibits robustness against certain types of technical noise and imperfections of detectors. Moreover, WVA allows for various modifications to extend the applicable scope and enhance the metrological performance in corresponding situations. Despite substantial progress in recent years, the inherent connection between the advantages of WVA and its unique features remains incompletely understood. In this paper, we systematically review the recent advances in the WVA scheme, with a particular focus on the ultimate precision of WVA under diverse conditions. Our objective is to provide a comprehensive perspective on the benefits of WVA in precision measurement and facilitate the realization of its full potential.

quant-ph↗

arXiv2024

Resource-efficient Direct Characterization of General Density Matrix

Sequential weak measurements allow the direct extraction of individual density-matrix elements instead of globally reconstructing the whole density matrix, opening a new avenue for the characterization of quantum systems. Nevertheless, the requirement of multiple coupling for each qudit of quantum systems and the lack of appropriate precision evaluation constraint its applicability extension, especially for multi-qudit quantum systems. Here, we propose a resource-efficient scheme (RES) to directly characterize the density matrix of general multi-qudit systems, which not only optimizes the measurements but also establishes a feasible estimation analysis. In this scheme, an efficient observable of quantum system is constructed such that a single meter state coupled to each qudit is sufficient to extract the corresponding density-matrix element. An appropriate model based on the statistical distribution of errors are used to evaluate the precision and feasibility of the scheme. We experimentally apply the RES to the direct characterization of general single-photon qutrit states and two-photon entangled states. The results show that the RES outperforms the sequential schemes in terms of efficiency and precision in both weak- and strong- coupling scenarios. This work sheds new light on the practical characterization of large-scale quantum systems and investigation of their non-classical properties.

quant-ph↗

arXiv2024

Investigating Instabilities in Magnetized Low-pressure Capacitively-Coupled RF Plasma using Particle-in-Cell (PIC) Simulations

The effect of a uniform magnetic field on particle transport in low-pressure radio frequency (RF) capacitively coupled plasma (CCP) has been studied using a particle-in-cell (PIC) model. Three distinct regimes of plasma behavior can be identified as a function of the magnetic field. In the first regime at low magnetic fields, asymmetric plasma profiles are observed within the CCP chamber due to the effect of E x B drift. As the magnetic field increases, instabilities develop and form self-organized spoke-shaped structures that are distinctly seen within the bulk plasma closer to the sheath. In this second regime, the spoke-shaped coherent structures rotate inside the plasma chamber in the - E x B direction, where E and B are the DC electric and magnetic field vectors, respectively, and the DC electric field exists in the sheath and pre-sheath regions. The spoke rotation frequency is in the MHz range. As the magnetic field strength increases further, the rotating coherent spokes continue to exist near the sheath. The coherent structures are, however, accompanied by new small-scale incoherent structures originating and moving within the bulk plasma region away from the sheath. This is the third regime of plasma behavior. The threshold values of the magnetic field between these regimes were found not to vary with changing plasma reactor geometry (e.g., area ratio between ground and powered electrodes) or the use of an external capacitor between the RF-powered electrode and the RF source. The threshold values of the magnetic field between these regimes shift toward higher values with increasing gas pressure. This paper provides guidance on the upper limit of the magnetic field for instability-free operation in low-pressure CCP-based semiconductor deposition and etch systems that use the external magnetic field for plasma uniformity control.

physics.plasm-ph↗

arXiv2024

Enabling Large-Scale and High-Precision Fluid Simulations on Near-Term Quantum Computers

Quantum computational fluid dynamics (QCFD) offers a promising alternative to classical computational fluid dynamics (CFD) by leveraging quantum algorithms for higher efficiency. This paper introduces a comprehensive QCFD method, including an iterative method "Iterative-QLS" that suppresses error in quantum linear solver, and a subspace method to scale the solution to a larger size. We implement our method on a superconducting quantum computer, demonstrating successful simulations of steady Poiseuille flow and unsteady acoustic wave propagation. The Poiseuille flow simulation achieved a relative error of less than $0.2\%$, and the unsteady acoustic wave simulation solved a 5043-dimensional matrix. We emphasize the utilization of the quantum-classical hybrid approach in applications of near-term quantum computers. By adapting to quantum hardware constraints and offering scalable solutions for large-scale CFD problems, our method paves the way for practical applications of near-term quantum computers in computational science.

physics.comp-ph↗

arXiv2024

SuperCLUE-Fin: Graded Fine-Grained Analysis of Chinese LLMs on Diverse Financial Tasks and Applications

The SuperCLUE-Fin (SC-Fin) benchmark is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs). It assesses FLMs across six financial application domains and twenty-five specialized tasks, encompassing theoretical knowledge and practical applications such as compliance, risk management, and investment analysis. Using multi-turn, open-ended conversations that mimic real-life scenarios, SC-Fin measures models on a range of criteria, including accurate financial understanding, logical reasoning, clarity, computational efficiency, business acumen, risk perception, and compliance with Chinese regulations. In a rigorous evaluation involving over a thousand questions, SC-Fin identifies a performance hierarchy where domestic models like GLM-4 and MoonShot-v1-128k outperform others with an A-grade, highlighting the potential for further development in transforming theoretical knowledge into pragmatic financial solutions. This benchmark serves as a critical tool for refining FLMs in the Chinese context, directing improvements in financial knowledge databases, standardizing financial interpretations, and promoting models that prioritize compliance, risk management, and secure practices. We create a contextually relevant and comprehensive benchmark that drives the development of AI in the Chinese financial sector. SC-Fin facilitates the advancement and responsible deployment of FLMs, offering valuable insights for enhancing model performance and usability for both individual and institutional users in the Chinese market..~\footnote{Our benchmark can be found at \url{https://www.CLUEbenchmarks.com}}.

cs.CL↗

arXiv2024

On-chip Real-time Hyperspectral Imager with Full CMOS Resolution Enabled by Massively Parallel Neural Network

Traditional spectral imaging methods are constrained by the time-consuming scanning process, limiting the application in dynamic scenarios. One-shot spectral imaging based on reconstruction has been a hot research topic recently and the primary challenges still lie in both efficient fabrication techniques suitable for mass production and the high-speed, high-accuracy reconstruction algorithm for real-time spectral imaging. In this study, we introduce an innovative on-chip real-time hyperspectral imager that leverages nanophotonic film spectral encoders and a Massively Parallel Network (MP-Net), featuring a 4 * 4 array of compact, all-dielectric film units for the micro-spectrometers. Each curved nanophotonic film unit uniquely modulates incident light across the underlying 3 * 3 CMOS image sensor (CIS) pixels, enabling a high spatial resolution equivalent to the full CMOS resolution. The implementation of MP-Net, specially designed to address variability in transmittance and manufacturing errors such as misalignment and non-uniformities in thin film deposition, can greatly increase the structural tolerance of the device and reduce the preparation requirement, further simplifying the manufacturing process. Tested in varied environments on both static and moving objects, the real-time hyperspectral imager demonstrates the robustness and high-fidelity spatial-spectral data capabilities across diverse scenarios. This on-chip hyperspectral imager represents a significant advancement in real-time, high-resolution spectral imaging, offering a versatile solution for applications ranging from environmental monitoring, remote sensing to consumer electronics.

physics.optics↗

arXiv2024

Neural Exponential Stabilization of Control-affine Nonlinear Systems

This paper proposes a novel learning-based approach for achieving exponential stabilization of nonlinear control-affine systems. We leverage the Control Contraction Metrics (CCMs) framework to co-synthesize Neural Contraction Metrics (NCMs) and Neural Network (NN) controllers. First, we transform the infinite-dimensional semi-definite program (SDP) for CCM computation into a tractable inequality feasibility problem using element-wise bounds of matrix-valued functions. The terms in the inequality can be efficiently computed by our novel algorithms. Second, we propose a free parametrization of NCMs guaranteeing positive definiteness and the satisfaction of a partial differential equation, regardless of trainable parameters. Third, this parametrization and the inequality condition enable the design of contractivity-enforcing regularizers, which can be incorporated while designing the NN controller for exponential stabilization of the underlying nonlinear systems. Furthermore, when the training loss goes to zero, we provide formal guarantees on verification of the NCM and the exponentional stabilization under the NN controller. Finally, we validate our method through benchmark experiments on set-point stabilization and increasing the region of attraction of a locally pre-stabilized closed-loop system.

eess.SY↗

arXiv2024

ReGenNet: Towards Human Action-Reaction Synthesis

Humans constantly interact with their surrounding environments. Current human-centric generative models mainly focus on synthesizing humans plausibly interacting with static scenes and objects, while the dynamic human action-reaction synthesis for ubiquitous causal human-human interactions is less explored. Human-human interactions can be regarded as asymmetric with actors and reactors in atomic interaction periods. In this paper, we comprehensively analyze the asymmetric, dynamic, synchronous, and detailed nature of human-human interactions and propose the first multi-setting human action-reaction synthesis benchmark to generate human reactions conditioned on given human actions. To begin with, we propose to annotate the actor-reactor order of the interaction sequences for the NTU120, InterHuman, and Chi3D datasets. Based on them, a diffusion-based generative model with a Transformer decoder architecture called ReGenNet together with an explicit distance-based interaction loss is proposed to predict human reactions in an online manner, where the future states of actors are unavailable to reactors. Quantitative and qualitative results show that our method can generate instant and plausible human reactions compared to the baselines, and can generalize to unseen actor motions and viewpoint changes.

cs.CV↗