arXiv subjects

Yanfang Liu

Publications and source records attributed to Yanfang Liu.

At least 19 recordsLinked to original sources

arXiv2026

NICE: A Theory-Grounded Diagnostic Benchmark for Social Intelligence of LLMs

As large language models (LLMs) are increasingly applied in social contexts such as emotional companionship and customer service, measuring their social intelligence has become critical to the quality and safety of human-AI interaction. However, existing social intelligence benchmarks lack a unified framework that organizes social abilities into a unified structure, and therefore cannot enable fine-grained diagnosis. To build the first holistic diagnostic evaluation grounded in social theory, we first construct a social intelligence framework through a literature review and multi-stage expert validation guided by psychometric principles. The resulting framework includes 4 categories and 11 dimensions, each further specified by fine-grained capability facets. Building on this framework, we introduce NICE (Norm, Interaction, Cognition, Experience), a diagnostic benchmark of 137 items operationalized through representative Chinese contexts. Across 5 frontier LLMs and a human reference group, models score higher in aggregate accuracy yet show a consistent weakness in Communication, which the framework localizes to 3 specific capability facets: multi-turn communication, nonverbal communication, and synchrony. NICE thus reframes social intelligence evaluation toward theory-grounded diagnosis of socially consequential weaknesses in LLMs.

cs.AI↗

arXiv2025

DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA

Multi-hop reasoning for question answering (QA) plays a critical role in retrieval-augmented generation (RAG) for modern large language models (LLMs). The accurate answer can be obtained through retrieving relational structure of entities from knowledge graph (KG). Regarding the inherent relation-dependency and reasoning pattern, multi-hop reasoning can be in general classified into two categories: i) parallel fact-verification multi-hop reasoning question, i.e., requiring simultaneous verifications of multiple independent sub-questions; and ii) chained multi-hop reasoning questions, i.e., demanding sequential multi-step inference with intermediate conclusions serving as essential premises for subsequent reasoning. Currently, the multi-hop reasoning approaches singly employ one of two techniques: LLM response-based fact verification and KG path-based chain construction. Nevertheless, the former excels at parallel fact-verification but underperforms on chained reasoning tasks, while the latter demonstrates proficiency in chained multi-hop reasoning but suffers from redundant path retrieval when handling parallel fact-verification reasoning. These limitations deteriorate the efficiency and accuracy for multi-hop QA tasks. To address this challenge, we propose a novel dual-track KG verification and reasoning framework DTKG, which is inspired by the Dual Process Theory in cognitive science. Specifically, DTKG comprises two main stages: the Classification Stage and the Branch Processing Stage.

cs.AI↗

arXiv2025

RGMem: Renormalization Group-inspired Memory Evolution for Language Agents

Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term, cross-session user states. Existing approaches, including retrieval-augmented generation and explicit memory systems, primarily operate at the fact level, making it difficult to distill stable preferences and deep user traits from evolving and potentially conflicting dialogues.To address this challenge, we propose RGMem, a self-evolving memory framework inspired by the renormalization group (RG) perspective on multi-scale organization and emergence. RGMem models long-term conversational memory as a multi-scale evolutionary process: episodic interactions are transformed into semantic facts and user insights, which are then progressively integrated through hierarchical coarse-graining, thresholded updates, and rescaling into a dynamically evolving user profile.By explicitly separating fast-changing evidence from slow-varying traits and enabling non-linear, phase-transition-like dynamics, RGMem enables robust personalization beyond flat retrieval or static summarization. Extensive experiments on the LOCOMO and PersonaMem benchmarks demonstrate that RGMem consistently outperforms SOTA memory systems, achieving stronger cross-session continuity and improved adaptation to evolving user preferences. Code is available at https://github.com/fenhg297/RGMem

cs.AI↗

arXiv2025

Generative AI Models for Learning Flow Maps of Stochastic Dynamical Systems in Bounded Domains

Simulating stochastic differential equations (SDEs) in bounded domains, presents significant computational challenges due to particle exit phenomena, which requires accurate modeling of interior stochastic dynamics and boundary interactions. Despite the success of machine learning-based methods in learning SDEs, existing learning methods are not applicable to SDEs in bounded domains because they cannot accurately capture the particle exit dynamics. We present a unified hybrid data-driven approach that combines a conditional diffusion model with an exit prediction neural network to capture both interior stochastic dynamics and boundary exit phenomena. Our ML model consists of two major components: a neural network that learns exit probabilities using binary cross-entropy loss with rigorous convergence guarantees, and a training-free diffusion model that generates state transitions for non-exiting particles using closed-form score functions. The two components are integrated through a probabilistic sampling algorithm that determines particle exit at each time step and generates appropriate state transitions. The performance of the proposed approach is demonstrated via three test cases: a one-dimensional simplified problem for theoretical verification, a two-dimensional advection-diffusion problem in a bounded domain, and a three-dimensional problem of interest to magnetically confined fusion plasmas.

stat.ML↗

arXiv2024

A Training-Free Conditional Diffusion Model for Learning Stochastic Dynamical Systems

This study introduces a training-free conditional diffusion model for learning unknown stochastic differential equations (SDEs) using data. The proposed approach addresses key challenges in computational efficiency and accuracy for modeling SDEs by utilizing a score-based diffusion model to approximate their stochastic flow map. Unlike the existing methods, this technique is based on an analytically derived closed-form exact score function, which can be efficiently estimated by Monte Carlo method using the trajectory data, and eliminates the need for neural network training to learn the score function. By generating labeled data through solving the corresponding reverse ordinary differential equation, the approach enables supervised learning of the flow map. Extensive numerical experiments across various SDE types, including linear, nonlinear, and multi-dimensional systems, demonstrate the versatility and effectiveness of the method. The learned models exhibit significant improvements in predicting both short-term and long-term behaviors of unknown stochastic systems, often surpassing baseline methods like GANs in estimating drift and diffusion coefficients.

cs.LG↗

arXiv2024

Beyond the Yield Barrier: Variational Importance Sampling Yield Analysis

Optimal mean shift vector (OMSV)-based importance sampling methods have long been prevalent in yield estimation and optimization as an industry standard. However, most OMSV-based methods are designed heuristically without a rigorous understanding of their limitations. To this end, we propose VIS, the first variational analysis framework for yield problems, enabling a systematic refinement for OMSV. For instance, VIS reveals that the classic OMSV is suboptimal, and the optimal/true OMSV should always stay beyond the failure boundary, which enables a free improvement for all OMSV-based methods immediately. Using VIS, we show a progressive refinement for the classic OMSV including incorporation of full covariance in closed form, adjusting for asymmetric failure distributions, and capturing multiple failure regions, each of which contributes to a progressive improvement of more than 2x. Inheriting the simplicity of OMSV, the proposed method retains simplicity and robustness yet achieves up to 29.03x speedup over the state-of-the-art (SOTA) methods. We also demonstrate how the SOTA yield optimization, ASAIS, can immediately benefit from our True OMSV, delivering a 1.20x and 1.27x improvement in performance and efficiency, respectively, without additional computational overhead.

cs.CE↗

arXiv2024

LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation

Few-shot segmentation models excel in metal defect detection due to their rapid generalization ability to new classes and pixel-level segmentation, rendering them ideal for addressing data scarcity issues and achieving refined object delineation in industrial applications. Existing works neglect the \textit{Intra-Class Differences}, inherent in metal surface defect data, which hinders the model from learning sufficient knowledge from the support set to guide the query set segmentation. Specifically, it can be categorized into two types: the \textit{Semantic Difference} induced by internal factors in metal samples and the \textit{Distortion Difference} caused by external factors of surroundings. To address these differences, we introduce a \textbf{L}ocal d\textbf{E}scriptor based \textbf{R}easoning and \textbf{E}xcitation \textbf{Net}work (\textbf{LERENet}) to learn the two-view guidance, i.e., local and global information from the graph and feature space, and fuse them to segment precisely. Since the relation structure of local features embedded in graph space will help to eliminate \textit{Semantic Difference}, we employ Multi-Prototype Reasoning (MPR) module, extracting local descriptors based prototypes and analyzing local-view feature relevance in support-query pairs. Besides, due to the global information that will assist in countering the \textit{Distortion Difference} in observations, we utilize Multi-Prototype Excitation (MPE) module to capture the global-view relations in support-query pairs. Finally, we employ an Information Fusion Module (IFM) to fuse learned prototypes in local and global views to generate pixel-level masks. Our comprehensive experiments on defect datasets demonstrate that it outperforms existing benchmarks, establishing a new state-of-the-art.

cs.CV↗

arXiv2023

Deep Bayesian Reinforcement Learning for Spacecraft Proximity Maneuvers and Docking

In the pursuit of autonomous spacecraft proximity maneuvers and docking(PMD), we introduce a novel Bayesian actor-critic reinforcement learning algorithm to learn a control policy with the stability guarantee. The PMD task is formulated as a Markov decision process that reflects the relative dynamic model, the docking cone and the cost function. Drawing from the principles of Lyapunov theory, we frame the temporal difference learning as a constrained Gaussian process regression problem. This innovative approach allows the state-value function to be expressed as a Lyapunov function, leveraging the Gaussian process and deep kernel learning. We develop a novel Bayesian quadrature policy optimization procedure to analytically compute the policy gradient while integrating Lyapunov-based stability constraints. This integration is pivotal in satisfying the rigorous safety demands of spaceflight missions. The proposed algorithm has been experimentally evaluated on a spacecraft air-bearing testbed and shows impressive and promising performance.

cs.RO↗

arXiv2023

Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimation

We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, variational auto-encoders, are usually considered as unsupervised learning models, because labeled data are usually unavailable for training. Despite the success of the generative models, there are several issues with the unsupervised training, e.g., requirement of reversible architectures, vanishing gradients, and training instability. To enable supervised learning in generative models, we utilize the score-based diffusion model to generate labeled data. Unlike existing diffusion models that train neural networks to learn the score function, we develop a training-free score estimation method. This approach uses mini-batch-based Monte Carlo estimators to directly approximate the score function at any spatial-temporal location in solving an ordinary differential equation (ODE), corresponding to the reverse-time stochastic differential equation (SDE). This approach can offer both high accuracy and substantial time savings in neural network training. Once the labeled data are generated, we can train a simple fully connected neural network to learn the generative model in the supervised manner. Compared with existing normalizing flow models, our method does not require to use reversible neural networks and avoids the computation of the Jacobian matrix. Compared with existing diffusion models, our method does not need to solve the reverse-time SDE to generate new samples. As a result, the sampling efficiency is significantly improved. We demonstrate the performance of our method by applying it to a set of 2D datasets as well as real data from the UCI repository.

cs.LG↗

arXiv2023

Contrastive Prompt Learning-based Code Search based on Interaction Matrix

Code search aims to retrieve the code snippet that highly matches the given query described in natural language. Recently, many code pre-training approaches have demonstrated impressive performance on code search. However, existing code search methods still suffer from two performance constraints: inadequate semantic representation and the semantic gap between natural language (NL) and programming language (PL). In this paper, we propose CPLCS, a contrastive prompt learning-based code search method based on the cross-modal interaction mechanism. CPLCS comprises:(1) PL-NL contrastive learning, which learns the semantic matching relationship between PL and NL representations; (2) a prompt learning design for a dual-encoder structure that can alleviate the problem of inadequate semantic representation; (3) a cross-modal interaction mechanism to enhance the fine-grained mapping between NL and PL. We conduct extensive experiments to evaluate the effectiveness of our approach on a real-world dataset across six programming languages. The experiment results demonstrate the efficacy of our approach in improving semantic representation quality and mapping ability between PL and NL.

cs.SE↗

arXiv2023

Seeking the Yield Barrier: High-Dimensional SRAM Evaluation Through Optimal Manifold

Being able to efficiently obtain an accurate estimate of the failure probability of SRAM components has become a central issue as model circuits shrink their scale to submicrometer with advanced technology nodes. In this work, we revisit the classic norm minimization method. We then generalize it with infinite components and derive the novel optimal manifold concept, which bridges the surrogate-based and importance sampling (IS) yield estimation methods. We then derive a sub-optimal manifold, optimal hypersphere, which leads to an efficient sampling method being aware of the failure boundary called onion sampling. Finally, we use a neural coupling flow (which learns from samples like a surrogate model) as the IS proposal distribution. These combinations give rise to a novel yield estimation method, named Optimal Manifold Important Sampling (OPTIMIS), which keeps the advantages of the surrogate and IS methods to deliver state-of-the-art performance with robustness and consistency, with up to 3.5x in efficiency and 3x in accuracy over the best of SOTA methods in High-dimensional SRAM evaluation.

cs.LG↗

arXiv2022

Deterministic-Statistical Approach for an Inverse Acoustic Source Problem using Multiple Frequency Limited Aperture Data

We propose a deterministic-statistical method for an inverse source problem using multiple frequency limited aperture far field data. The direct sampling method is used to obtain a disc such that it contains the compact support of the source. The Dirichlet eigenfunctions of the disc are used to expand the source function. Then the inverse problem is recast as a statistical inference problem for the expansion coefficients and the Bayesian inversion is employed to reconstruct the coefficients. The stability of the statistical inverse problem with respect to the measured data is justified in the sense of Hellinger distance. A preconditioned Crank-Nicolson (pCN) Metropolis-Hastings (MH) algorithm is implemented to explore the posterior density function of the unknowns. Numerical examples show that the proposed method is effective for both smooth and non-smooth sources given limited-aperture data.

math.NA↗

arXiv2022

A clinically relevant online patient QA solution with daily CT scans and EPID-based in vivo dosimetry: A feasible study on rectal cancer

Adaptive radiation therapy (ART) could protect organs at risk (OARs) while maintain high dose coverage to targets. However, there still lack efficient online patient QA methods. We aim to develop a clinically relevant online patient quality assurance (QA) solution for ART using daily CT scans and electronic portal imaging device (EPID)-based in vivo dosimetry. Ten patients with rectal cancer at our center were included. Patients' daily CT scans and portal images were collected to generate reconstructed 3D dose distributions. Contours of targets and OARs were recontoured on these daily CT scans by a clinician or an auto-segmentation algorithm, then dose-volume indices were calculated, and the percent deviation of these indices to their original plans were determined. This deviation was regarded as the metric for clinically relevant patient QA. The tolerance level was obtained using a 95% interval of the QA metric distribution. These deviations could be further divided into anatomically relevant or delivery relevant indicators for error source analysis. Finally, our QA solution was validated on an additional six clinical patients. In rectal cancer, the lower and upper tolerance of the QA metric for PTV ΔD95 (%) were [-3.11%, 2.35%], and for PTV ΔD2 (%) were [-0.78%, 3.23%]. In validation, the 68% for PTV ΔD95 (%) and the 79% for PTV ΔD2 ({%)of the 28 fractions are within tolerances of the QA metrics. By using four or more out-of-tolerance QA metrics as an action level, there were 5 fractions (18%) have four or more out-of-tolerance QA metrics in validation patient dataset. The online patient QA solution using daily CT scans and EPID-based in vivo dosimetry is clinically feasible. Source of error analysis has the potential for distinguishing sources of error and guiding ART for future treatments.

physics.med-ph↗

arXiv2022

First implementation of full-workflow automation in radiotherapy: the All-in-One solution on rectal cancer

The aim of this work is to describe the technical characteristics of an AI-powered radiotherapy workflow that enables full-process automation (All-in-One), evaluate its performance implemented for on-couch initial treatment of rectal cancer, and provide insight into the behavior of full-workflow automation in the specialty of radiotherapy. The All-in-One workflow was developed based on a CT-integrated linear accelerator. It incorporates routine radiotherapy procedures from simulation, autosegmentation, autoplanning, image guidance, beam delivery, and in vivo quality assurance (QA) into one scheme, with critical decision points involved, while the patient is on the treatment couch during the whole process. For the enrolled ten patients with rectal cancer, minor modifications of the autosegmented target volumes were required, and the Dice similarity coefficient and 95% Hausdorff distance before and after modifications were 0.892{\pm}0.061 and 18.2{\pm}13.0 mm, respectively. The autosegmented normal tissues and automatic plans were clinically acceptable without any modifications or reoptimization. The pretreatment IGRT corrections were within 2 mm in all directions, and the EPID-based in vivo QA showed a γ passing rate better than 97{\%} (3{\%}/3 mm/10{\%} threshold). The duration of the whole process was 23.2{\pm}3.5 minutes, depending mostly on the time required for manual modification and plan evaluation. The All-in-One workflow enables full automation of the entire radiotherapy process by seamlessly integrating multiple routine procedures. The one-stop solution shortens the time scale it takes to ready the first treatment from days to minutes, significantly improving the patient experience and the efficiency of the workflow, and shows potential to facilitate the clinical application of online adaptive replanning.

physics.med-ph↗

arXiv2021

A deterministic-statistical approach to reconstruct moving sources using sparse partial data

We consider the reconstruction of moving sources using partial measured data. A two-step deterministic-statistical approach is proposed. In the first step, an approximate direct sampling method is developed to obtain the locations of the sources at different times. Such information is coded in the priors, which is critical for the success of the Bayesian method in the second step. The well-posedness of the posterior measure is analyzed in the sense of the Hellinger distance. Both steps are based on the same physical model and use the same set of measured data. The combined approach inherits the merits of the deterministic method and Bayesian inversion as demonstrated by the numerical examples.

math.NA↗

arXiv2020

Quality-Bayesian approach to inverse acoustic source problems with partial data

A quality-Bayesian approach, combining the direct sampling method and the Bayesian inversion, is proposed to reconstruct the locations and intensities of the unknown acoustic sources using partial data. First, we extend the direct sampling method by constructing a new indicator function to obtain the approximate locations of the sources. The behavior of the indicator is analyzed. Second, the inverse problem is formulated as a statistical inference problem using the Bayes' formula. The well-posedness of the posterior distribution is proved. The source locations obtained in the first step are coded in the priors. Then an Metropolis-Hastings MCMC algorithm is used to explore the posterior density. Both steps use the same physical model and measured data. Numerical experiments show that the proposed method is effective even with partial data.

math.NA↗

arXiv2019

On Generalized LDPC Codes for 5G Ultra Reliable Communication

Generalized low-density parity-check (GLDPC) codes, where single parity-check (SPC) constraint nodes are replaced with generalized constraint (GC) nodes, are a promising class of codes for low latency communication. In this paper, a practical construction of quasi-cyclic (QC) GLDPC codes is proposed, where the proportion of generalized constraints is determined by an asymptotic analysis. We analyze the message passing process and complexity of a GLDPC code over the additive white gaussian noise (AWGN) channel and present a constraint-to-variable update rule based on the specific codewords of the component code. The block error rate (BLER) performance of the GLDPC codes, combined with a complementary outer code, is shown to outperform a variety of state-of-the-art code and decoder designs with suitable lengths and rates for the 5G Ultra Reliable Communication (URC) regime over an additive white gaussian noise (AWGN) channel with quadrature PSK (QPSK) modulation.

cs.IT↗

arXiv2019

An inverse medium problem using Stekloff eigenvalues and a Bayesian approach

This paper studies the reconstruction of Stekloff eigenvalues and the index of refraction of an inhomogeneous medium from Cauchy data. The inverse spectrum problem to reconstruct Stekloff eigenvalues is investigated using a new integral equation for the reciprocity gap method. Given reconstructed eigenvalues, a Bayesian approach is proposed to estimate the index of refraction. Moreover, since it is impossible to know the multiplicities of the reconstructed eigenvalues and since the eigenvalues can be complex, we employ the recently developed spectral indicator method to compute Stekloff eigenvalues. Numerical experiments validate the effectiveness of the proposed methods.

math-ph↗