arXiv subjects

Weidong Liu

Publications and source records attributed to Weidong Liu.

At least 19 recordsLinked to original sources

arXiv2026

EviSI: An Evaluation Agent for Simultaneous Interpreting

Simultaneous speech-to-speech translation requires understanding, translation and spoken delivery while the source stream continues. To support timely delivery and limit accumulated delay, systems adopt reformulation and summarization, which can preserve meaning while departing from written references. BLEU and COMET may not reliably distinguish such variation from semantic loss. We introduce EviSI, a large language model evaluation agent adapting the error analysis and penalty principles of Multidimensional Quality Metrics (MQM). It constructs shared source evidence, assesses semantic fidelity and oral expression, reconciles overlapping errors and scores deterministically. EviSI recovers the aggregate human system ranking for English to Chinese. Mean Kendall agreement with human system rankings within corpora reaches 0.707 for English to Chinese and 0.467 for Chinese to English, exceeding evaluated baselines. An extension across five directions shows positive concordance with COMET without human ratings. Individual output agreement with humans remains mixed.

cs.CL↗

arXiv2026

A CPU+DCU Heterogeneous Parallel Framework for Post-Processing Reconstruction in Quantum Circuit Cutting

In the NISQ era, limited qubit resources make it difficult to execute large quantum circuits directly on real hardware. Quantum circuit cutting mitigates this limitation by decomposing a large circuit into smaller subcircuits, but it shifts substantial overhead to classical post-processing. As circuit size, complexity, and cut count increase, reconstruction becomes a major computational and storage bottleneck. This paper presents a CPU+DCU heterogeneous parallel framework for circuit-cutting post-processing reconstruction. Instead of constructing a dense $2^n$-dimensional probability vector or returning only high-probability states, the framework reconstructs the nonzero-probability states in the original output distribution from subcircuit measurement results. It combines heterogeneous CPU+DCU execution with a high/low-word integer representation for global basis-state indices beyond 64 bits and a three-level cooperative storage mechanism spanning device memory, host memory, and out-of-core storage. Experiments on the Songshan supercomputer show that the framework maintains high reconstruction fidelity while achieving up to $259\times$ speedup over an optimized serial baseline on linear-cluster states and up to $4\times$ speedup over a homogeneous CPU-parallel method on random circuits. The framework can also complete reconstruction tasks at the hundred-qubit scale. These results demonstrate that HPC-oriented heterogeneous reconstruction can effectively alleviate the classical post-processing bottleneck and improve reconstruction scalability.

quant-ph↗

arXiv2026

Unlocking Directional Radiation in Pinching-Antenna Systems: Geometry-Aware Design and Experimental Verification

Pinching-antenna systems (PASS) have recently attracted growing interest as a flexible architecture for creating "last-meter" line-of-sight wireless links through dielectric waveguides and reconfigurable radiation points. While modeling pinching antennas (PAs) as isotropic point radiators has enabled tractable analyses and demonstrated the performance gains of PASS, their practical radiation characteristics remain underexplored. This article investigates PASS from the perspective of PA geometry. Starting from the physical coupling principle, we explain why PA shape affects the induced polarization current and incorporate directional gain into the channel model. The full-wave simulations are conducted to show how different PA geometries and orientations reshape the internal field distribution and far-field radiation pattern. A 60 GHz prototype video transmission experiment is further presented to demonstrate the link-level impact of changing PA states. Finally, promising applications enabled by geometry-aware directional PASS are highlighted.

eess.SY↗

arXiv2026

Student Competency Assessment and Presentation Methods Based on Algorithm Courses

This full research paper describes the assessment and presentation of student competencies in algorithm courses, grounded in the CC2020 competency model. With the growing emphasis on bridging the gap between academic training and industry demands, competency-based education, which integrates knowledge, skills, and dispositions, has become pivotal in computer science education. To bridge the gap, we need to develop a comprehensive framework to evaluate competencies (knowledge, skills, and dispositions) in computer science education. The research aims to analyze learning behavior patterns, design methods for competency assessment in algorithm courses, and evaluate the difficulty of course experiments to inform curriculum design. We collected programming experiment and written assignment data from 169 students, adapting it to the xAPI specification for unified analysis. In this work, Markov process modeling was employed to analyze behavioral sequences, revealing cognitive patterns during programming tasks. Multiple methods were applied to quantify competencies (knowledge, skills, dispositions) and identify distinct student clusters. Course difficulty was quantified using proactiveness metrics derived from submission timeliness. This work contributes a scalable framework for competency assessment in algorithm courses and offers actionable insights for personalized teaching and curriculum optimization. Practically, it enables instructors to tailor interventions based on student clusters and optimize task difficulty. Future work will integrate more students' performance to validate competency models and extend the framework to broader computer science curricula.

cs.CY↗

arXiv2026

Geometry-Dependent Radiation of Pinching Antennas: Theory, Simulation, and Measurement

Most existing studies achieve beamforming by adjusting the positions of pinching antennas (PAs) and typically model PAs as isotropic radiators. However, under the dielectric scatterer model, the PA radiation pattern depends on its geometry. This letter investigates the radiation patterns of PAs with different geometries through full-wave simulations and measurements, and demonstrates how geometry influences the radiation directivity. In addition, an arc-shaped PA is introduced to enable transmit-direction control in PA systems. A PA system prototype consisting of a dielectric waveguide, waveguide transitions, and a PA element is proposed. Prototype measurements are used to validate the simulations and to characterize the directivity of square and triangular PAs, and the measurement procedure can be applied to obtain radiation patterns for PAs with general geometries. The simulation and measurement results jointly demonstrate that PA geometry is critical in PA systems because it influences the radiation characteristics significantly.

eess.SY↗

arXiv2025

Robust Variational Bayes by Min-Max Median Aggregation

We propose a robust and scalable variational Bayes (VB) framework designed to effectively handle contamination and outliers in dataset. Our approach partitions the data into $m$ disjoint subsets and formulates a joint optimization problem based on robust aggregation principles. A key insight is that the full posterior distribution is equivalent to the minimizer of the mean Kullback-Leibler (KL) divergence from the $m$-powered local posterior distributions. To enhance robustness, we replace the mean KL divergence with a min-max median formulation. The min-max formulation not only ensures consistency between the KL minimizer and the Evidence Lower Bound (ELBO) maximizer but also facilitates the establishment of improved statistical rates for the mean of variational posterior. We observe a notable discrepancy in the $m$-powered marginal log likelihood function contingent on the presence of local latent variables. To address this, we treat these two scenarios separately to guarantee the consistency of the aggregated variational posterior. Specifically, when local latent variables are present, we introduce an aggregate-and-rescale strategy. Theoretically, we provide a non-asymptotic analysis of our proposed posterior, incorporating a refined analysis of Bernstein-von Mises (BvM) theorem to accommodate a diverging number of subsets $m$. Our findings indicate that the two-stage approach yields a smaller approximation error compared to directly aggregating the $m$-powered local posteriors. Furthermore, we establish a nearly optimal statistical rate for the mean of the proposed posterior, advancing existing theories related to min-max median estimators. The efficacy of our method is demonstrated through extensive simulation studies.

stat.ME↗

arXiv2025

A Bias-Correction Decentralized Stochastic Gradient Algorithm with Momentum Acceleration

Distributed stochastic optimization algorithms can simultaneously process large-scale datasets, significantly accelerating model training. However, their effectiveness is often hindered by the sparsity of distributed networks and data heterogeneity. In this paper, we propose a momentum-accelerated distributed stochastic gradient algorithm, termed Exact-Diffusion with Momentum (EDM), which mitigates the bias from data heterogeneity and incorporates momentum techniques commonly used in deep learning to enhance convergence rate. Our theoretical analysis demonstrates that the EDM algorithm converges sub-linearly to the neighborhood of the optimal solution, the radius of which is irrespective of data heterogeneity, when applied to non-convex objective functions; under the Polyak-Lojasiewicz condition, which is a weaker assumption than strong convexity, it converges linearly to the target region. Our analysis techniques employed to handle momentum in complex distributed parameter update structures yield a sufficiently tight convergence upper bound, offering a new perspective for the theoretical analysis of other momentum-based distributed algorithms.

cs.LG↗

arXiv2024

A Short Review for Ontology Learning: Stride to Large Language Models Trend

Ontologies provide formal representation of knowledge shared within Semantic Web applications. Ontology learning involves the construction of ontologies from a given corpus. In the past years, ontology learning has traversed through shallow learning and deep learning methodologies, each offering distinct advantages and limitations in the quest for knowledge extraction and representation. A new trend of these approaches is relying on large language models (LLMs) to enhance ontology learning. This paper gives a review in approaches and challenges of ontology learning. It analyzes the methodologies and limitations of shallow-learning-based and deep-learning-based techniques for ontology learning, and provides comprehensive knowledge for the frontier work of using LLMs to enhance ontology learning. In addition, it proposes several noteworthy future directions for further exploration into the integration of LLMs with ontology learning tasks.

cs.IR↗

arXiv2024

Multi-Level Sequence Denoising with Cross-Signal Contrastive Learning for Sequential Recommendation

Sequential recommender systems (SRSs) aim to suggest next item for a user based on her historical interaction sequences. Recently, many research efforts have been devoted to attenuate the influence of noisy items in sequences by either assigning them with lower attention weights or discarding them directly. The major limitation of these methods is that the former would still prone to overfit noisy items while the latter may overlook informative items. To the end, in this paper, we propose a novel model named Multi-level Sequence Denoising with Cross-signal Contrastive Learning (MSDCCL) for sequential recommendation. To be specific, we first introduce a target-aware user interest extractor to simultaneously capture users' long and short term interest with the guidance of target items. Then, we develop a multi-level sequence denoising module to alleviate the impact of noisy items by employing both soft and hard signal denoising strategies. Additionally, we extend existing curriculum learning by simulating the learning pattern of human beings. It is worth noting that our proposed model can be seamlessly integrated with a majority of existing recommendation models and significantly boost their effectiveness. Experimental studies on five public datasets are conducted and the results demonstrate that the proposed MSDCCL is superior to the state-of-the-art baselines. The source code is publicly available at https://github.com/lalunex/MSDCCL/tree/main.

cs.IR↗

arXiv2024

OneBit: Towards Extremely Low-bit Large Language Models

Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs. However, current quantization methods suffer severe performance degradation when the bit-width is extremely reduced, and thus focus on utilizing 4-bit or 8-bit values to quantize models. This paper boldly quantizes the weight matrices of LLMs to 1-bit, paving the way for the extremely low bit-width deployment of LLMs. For this target, we introduce a 1-bit model compressing framework named OneBit, including a novel 1-bit parameter representation method to better quantize LLMs as well as an effective parameter initialization method based on matrix decomposition to improve the convergence speed of the quantization framework. Sufficient experimental results indicate that OneBit achieves good performance (at least 81% of the non-quantized performance on LLaMA models) with robust training processes when only using 1-bit weight matrices.

cs.CL↗

arXiv2024

Efficient Sparse Least Absolute Deviation Regression with Differential Privacy

In recent years, privacy-preserving machine learning algorithms have attracted increasing attention because of their important applications in many scientific fields. However, in the literature, most privacy-preserving algorithms demand learning objectives to be strongly convex and Lipschitz smooth, which thus cannot cover a wide class of robust loss functions (e.g., quantile/least absolute loss). In this work, we aim to develop a fast privacy-preserving learning solution for a sparse robust regression problem. Our learning loss consists of a robust least absolute loss and an $\ell_1$ sparse penalty term. To fast solve the non-smooth loss under a given privacy budget, we develop a Fast Robust And Privacy-Preserving Estimation (FRAPPE) algorithm for least absolute deviation regression. Our algorithm achieves a fast estimation by reformulating the sparse LAD problem as a penalized least square estimation problem and adopts a three-stage noise injection to guarantee the $(\epsilon,\delta)$-differential privacy. We show that our algorithm can achieve better privacy and statistical accuracy trade-off compared with the state-of-the-art privacy-preserving regression algorithms. In the end, we conduct experiments to verify the efficiency of our proposed FRAPPE algorithm.

stat.ML↗

arXiv2023

Vision-language Assisted Attribute Learning

Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization. Existing attribute learning methods often treat the missing labels as negative or simply ignore them all during training, either of which could hamper the model performance to a great extent. To overcome these limitations, in this paper we leverage the available vision-language knowledge to explicitly disclose the missing labels for enhancing model learning. Given an image, we predict the likelihood of each missing attribute label assisted by an off-the-shelf vision-language model, and randomly select to ignore those with high scores in training. Our strategy strikes a good balance between fully ignoring and negatifying the missing labels, as these high scores are found to be informative on revealing label ambiguity. Extensive experiments show that our proposed vision-language assisted loss can achieve state-of-the-art performance on the newly cleaned VAW dataset. Qualitative evaluation demonstrates the ability of the proposed method in predicting more complete attributes.

cs.CV↗

arXiv2023

Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning

Reinforcement learning has emerged as one of the prominent topics attracting attention in modern statistical learning, with policy evaluation being a key component. Unlike the traditional machine learning literature on this topic, our work emphasizes statistical inference for the model parameters and value functions of reinforcement learning algorithms. While most existing analyses assume random rewards to follow standard distributions, we embrace the concept of robust statistics in reinforcement learning by simultaneously addressing issues of outlier contamination and heavy-tailed rewards within a unified framework. In this paper, we develop a fully online robust policy evaluation procedure, and establish the Bahadur-type representation of our estimator. Furthermore, we develop an online procedure to efficiently conduct statistical inference based on the asymptotic distribution. This paper connects robust statistics and statistical inference in reinforcement learning, offering a more versatile and reliable approach to online policy evaluation. Finally, we validate the efficacy of our algorithm through numerical experiments conducted in simulations and real-world reinforcement learning experiments.

stat.ML↗

arXiv2023

Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf

Communication games, which we refer to as incomplete information games that heavily depend on natural language communication, hold significant research value in fields such as economics, social science, and artificial intelligence. In this work, we explore the problem of how to engage large language models (LLMs) in communication games, and in response, propose a tuning-free framework. Our approach keeps LLMs frozen, and relies on the retrieval and reflection on past communications and experiences for improvement. An empirical study on the representative and widely-studied communication game, ``Werewolf'', demonstrates that our framework can effectively play Werewolf game without tuning the parameters of the LLMs. More importantly, strategic behaviors begin to emerge in our experiments, suggesting that it will be a fruitful journey to engage LLMs in communication games and associated domains.

cs.CL↗

arXiv2023

Pluggable Neural Machine Translation Models via Memory-augmented Adapters

Although neural machine translation (NMT) models perform well in the general domain, it remains rather challenging to control their generation behavior to satisfy the requirement of different users. Given the expensive training cost and the data scarcity challenge of learning a new model from scratch for each user requirement, we propose a memory-augmented adapter to steer pretrained NMT models in a pluggable manner. Specifically, we construct a multi-granular memory based on the user-provided text samples and propose a new adapter architecture to combine the model representations and the retrieved results. We also propose a training strategy using memory dropout to reduce spurious dependencies between the NMT model and the memory. We validate our approach on both style- and domain-specific experiments and the results indicate that our method can outperform several representative pluggable baselines.

cs.CL↗

arXiv2023

Distributed Semi-Supervised Sparse Statistical Inference

The debiased estimator is a crucial tool in statistical inference for high-dimensional model parameters. However, constructing such an estimator involves estimating the high-dimensional inverse Hessian matrix, incurring significant computational costs. This challenge becomes particularly acute in distributed setups, where traditional methods necessitate computing a debiased estimator on every machine. This becomes unwieldy, especially with a large number of machines. In this paper, we delve into semi-supervised sparse statistical inference in a distributed setup. An efficient multi-round distributed debiased estimator, which integrates both labeled and unlabelled data, is developed. We will show that the additional unlabeled data helps to improve the statistical rate of each round of iteration. Our approach offers tailored debiasing methods for $M$-estimation and generalized linear models according to the specific form of the loss function. Our method also applies to a non-smooth loss like absolute deviation loss. Furthermore, our algorithm is computationally efficient since it requires only one estimation of a high-dimensional inverse covariance matrix. We demonstrate the effectiveness of our method by presenting simulation studies and real data applications that highlight the benefits of incorporating unlabeled data.

stat.ML↗

arXiv2023

Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality

Stochastic gradient descent with momentum (SGDM) has been widely used in many machine learning and statistical applications. Despite the observed empirical benefits of SGDM over traditional SGD, the theoretical understanding of the role of momentum for different learning rates in the optimization process remains widely open. We analyze the finite-sample convergence rate of SGDM under the strongly convex settings and show that, with a large batch size, the mini-batch SGDM converges faster than the mini-batch SGD to a neighborhood of the optimal value. Additionally, our findings, supported by theoretical analysis and numerical experiments, indicate that SGDM permits broader choices of learning rates. Furthermore, we analyze the Polyak-averaging version of the SGDM estimator, establish its asymptotic normality, and justify its asymptotic equivalence to the averaged SGD. The asymptotic distribution of the averaged SGDM enables uncertainty quantification of the algorithm output and statistical inference of the model parameters.

cs.LG↗

arXiv2023

A review of distributed statistical inference

The rapid emergence of massive datasets in various fields poses a serious challenge to traditional statistical methods. Meanwhile, it provides opportunities for researchers to develop novel algorithms. Inspired by the idea of divide-and-conquer, various distributed frameworks for statistical estimation and inference have been proposed. They were developed to deal with large-scale statistical optimization problems. This paper aims to provide a comprehensive review for related literature. It includes parametric models, nonparametric models, and other frequently used models. Their key ideas and theoretical properties are summarized. The trade-off between communication cost and estimate precision together with other concerns are discussed.

stat.CO↗