arXiv subjects

Meng Zhao

Publications and source records attributed to Meng Zhao.

At least 37 records · Page 2Linked to original sources

arXiv2025

Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learning

Multi-party dialogues, common in collaborative scenarios like brainstorming sessions and negotiations, pose significant challenges due to their complexity and diverse speaker roles. Current methods often use graph neural networks to model dialogue context, capturing structural dynamics but heavily relying on annotated graph structures and overlooking individual speaking styles. To address these challenges, we propose CMR, a Contrastive learning-based Multi-party dialogue Response generation framework. CMR employs a two-stage self-supervised contrastive learning framework. First, it captures global differences in speaking styles across individuals. Then, it focuses on intra-conversation comparisons to identify thematic transitions and contextually relevant facts. To the best of our knowledge, this is the first approach that applies contrastive learning in multi-party dialogue generation. Experimental results demonstrate that CMR not only significantly outperforms state-of-the-art models, but also generalizes well to large pre-trained language models, effectively enhancing their capability in handling multi-party conversations.

cs.CL↗

arXiv2025

Slow, Nanometer Light Confinement Observed in Atomically Thin TaS2

Extreme light confinement down to the atomic scale has been theoretically predicted for ultrathin, Ta-based transition metal dichalcogenides (TMDs). In this work, we experimentally demonstrate in 2H-TaS$_2$ monolayers and bilayers a lateral confinement ratio up to 300 at large wave vectors of $q = 0.15 \, Å^{-1}$, and slow light behaviour with a group velocity $\sim 10^{-4}c$. Quantitative momentum-resolved electron energy loss spectroscopy (q-EELS) with a momentum resolution of $0.0056 \, Å^{-1}$ was used as a platform for the nanoscale optical measurements. With it, momentum-dispersed, two-dimensional (2D) plasmon resonances were experimentally observed, showing a transition from 2D to 3D Coulomb interaction in the high-momentum regime, equivalent to light confinement volumes of $1\text{-}2 \, \text{nm}^3$. Remarkably, the resonant modes do not enter the electron-hole continuum, predicting even further enhanced optical field confinements for this material at cryogenic temperatures.

cond-mat.mtrl-sci↗

arXiv2025

Association between nutritional factors, inflammatory biomarkers and cancer types: an analysis of NHANES data using machine learning

Background. Diet and inflammation are critical factors influencing cancer risk. However, the combined impact of nutritional status and inflammatory biomarkers on cancer status and type, using machine learning (ML), remains underexplored. Objectives. This study investigates the association between nutritional factors, inflammatory biomarkers, and cancer status, and whether these relationships differ across cancer types using National Health and Nutrition Examination Survey (NHANES) data. Methods. We analyzed 24 macro- and micronutrients, C-reactive protein (CRP), and the advanced lung cancer inflammation index (ALI) in 26,409 NHANES participants (2,120 with cancer). Multivariable logistic regression assessed associations with cancer prevalence. We also examined whether these features differed across the five most common cancer types. To evaluate predictive value, we applied three ML models - Logistic Regression, Random Forest, and XGBoost - on the full feature set. Results. The cohort's mean age was 49.1 years; 34.7% were obese. Comorbidities such as anemia and liver conditions, along with nutritional factors like protein and several vitamins, were key predictors of cancer status. Among the models, Random Forest performed best, achieving an accuracy of 0.72. Conclusions. Higher-quality nutritional intake and lower levels of inflammation may offer protective effects against cancer. These findings highlight the potential of combining nutritional and inflammatory markers with ML to inform cancer prevention strategies.

q-bio.QM↗

arXiv2025

Selective Complementary Feature Fusion and Modal Feature Compression Interaction for Brain Tumor Segmentation

Efficient modal feature fusion strategy is the key to achieve accurate segmentation of brain glioma. However, due to the specificity of different MRI modes, it is difficult to carry out cross-modal fusion with large differences in modal features, resulting in the model ignoring rich feature information. On the other hand, the problem of multi-modal feature redundancy interaction occurs in parallel networks due to the proliferation of feature dimensions, further increase the difficulty of multi-modal feature fusion at the bottom end. In order to solve the above problems, we propose a noval complementary feature compression interaction network (CFCI-Net), which realizes the complementary fusion and compression interaction of multi-modal feature information with an efficient mode fusion strategy. Firstly, we propose a selective complementary feature fusion (SCFF) module, which adaptively fuses rich cross-modal feature information by complementary soft selection weights. Secondly, a modal feature compression interaction (MFCI) transformer is proposed to deal with the multi-mode fusion redundancy problem when the feature dimension surges. The MFCI transformer is composed of modal feature compression (MFC) and modal feature interaction (MFI) to realize redundancy feature compression and multi-mode feature interactive learning. %In MFI, we propose a hierarchical interactive attention mechanism based on multi-head attention. Evaluations on the BraTS2019 and BraTS2020 datasets demonstrate that CFCI-Net achieves superior results compared to state-of-the-art models. Code: https://github.com/CDmm0/CFCI-Net

eess.IV↗

arXiv2024

Short-Term Evolution and Risks of Debris Cloud Stemming from Collisions in Geostationary Orbit

The increasing population of objects in geostationary orbit has raised concerns about the potential risks posed by debris clouds resulting from fragmentation. The short-term evolution and associated hazards of debris generated by collisions in the geostationary region is investigated in this study. The initial distribution of two debris clouds is modeled using a single probability density function. The combined distribution of the evolved clouds is determined by solving boundary value problems. The risks associated with these debris clouds are evaluated by calculating the instantaneous impact rate and cumulative collision probability. The probability of collisions with millimeter-sized fragments may increase to 1% within 36 hours, while the probability of collisions with fragments 5 cm or larger is approximately $10^{-5}$. These findings underscore the vulnerability of the geostationary region to space traffic accidents.

astro-ph.EP↗

arXiv2024

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement Learning from Human Feedback (RLHF). Despite its promising efficacy, DPO faces a notable drawback: "verbosity", a common over-optimization phenomenon also observed in RLHF. While previous studies mainly attributed verbosity to biased labels within the data, we propose that the issue also stems from an inherent algorithmic length reliance in DPO. Specifically, we suggest that the discrepancy between sequence-level Kullback-Leibler (KL) divergences between chosen and rejected sequences, used in DPO, results in overestimated or underestimated rewards due to varying token lengths. Empirically, we utilize datasets with different label lengths to demonstrate the presence of biased rewards. We then introduce an effective downsampling approach, named SamPO, to eliminate potential length reliance. Our experimental evaluations, conducted across three LLMs of varying scales and a diverse array of conditional and open-ended benchmarks, highlight the efficacy of SamPO in mitigating verbosity, achieving improvements of 5% to 12% over DPO through debaised rewards. Our codes can be accessed at: https://github.com/LuJunru/SamPO/.

cs.CL↗

arXiv2024

Polynomial mixing for the white-forced Navier-Stokes system in the whole space

We study the mixing properties of the white-forced Navier-Stokes system in the whole space $\mathbb{R}^2$. Assuming that the noise is sufficiently non-degenerate, we prove the uniqueness of stationary measure and polynomial mixing in the dual-Lipschitz metric. The proof combines the coupling method with a Foiaş-Prodi type estimate, weighted growth estimates for trajectories, and an estimate for the Leray projector involving Muckenhoupt $A_2$-class weights.

math.AP↗

arXiv2024

Self-Supervised State Space Model for Real-Time Traffic Accident Prediction Using eKAN Networks

Accurate prediction of traffic accidents across different times and regions is vital for public safety. However, existing methods face two key challenges: 1) Generalization: Current models rely heavily on manually constructed multi-view structures, like POI distributions and road network densities, which are labor-intensive and difficult to scale across cities. 2) Real-Time Performance: While some methods improve accuracy with complex architectures, they often incur high computational costs, limiting their real-time applicability. To address these challenges, we propose SSL-eKamba, an efficient self-supervised framework for traffic accident prediction. To enhance generalization, we design two self-supervised auxiliary tasks that adaptively improve traffic pattern representation through spatiotemporal discrepancy awareness. For real-time performance, we introduce eKamba, an efficient model that redesigns the Kolmogorov-Arnold Network (KAN) architecture. This involves using learnable univariate functions for input activation and applying a selective mechanism (Selective SSM) to capture multi-variate correlations, thereby improving computational efficiency. Extensive experiments on two real-world datasets demonstrate that SSL-eKamba consistently outperforms state-of-the-art baselines. This framework may also offer new insights for other spatiotemporal tasks. Our source code is publicly available at http://github.com/KevinT618/SSL-eKamba.

cs.LG↗

arXiv2024

An Artificial Neural Network for Image Classification Inspired by Aversive Olfactory Learning Circuits in Caenorhabditis Elegans

This study introduces an artificial neural network (ANN) for image classification task, inspired by the aversive olfactory learning circuits of the nematode Caenorhabditis elegans (C. elegans). Despite the remarkable performance of ANNs in a variety of tasks, they face challenges such as excessive parameterization, high training costs and limited generalization capabilities. C. elegans, with its simple nervous system comprising only 302 neurons, serves as a paradigm in neurobiological research and is capable of complex behaviors including learning. This research identifies key neural circuits associated with aversive olfactory learning in C. elegans through behavioral experiments and high-throughput gene sequencing, translating them into an image classification ANN architecture. Additionally, two other image classification ANNs with distinct architectures were constructed for comparative performance analysis to highlight the advantages of bio-inspired design. The results indicate that the ANN inspired by the aversive olfactory learning circuits of C. elegans achieves higher accuracy, better consistency and faster convergence rates in image classification task, especially when tackling more complex classification challenges. This study not only showcases the potential of bio-inspired design in enhancing ANN capabilities but also provides a novel perspective and methodology for future ANN design.

cs.NE↗

arXiv2024

Local and global existence for the stochastic Prandtl equation driven by multiplicative noises in two and three dimensions

In this paper, we are concerned with the local and global existence for the stochastic Prandtl equation in two and three dimensions, which governs the velocity field inside the boundary layer that appears in the inviscid limit of the stochastic Navier-Stokes equation with non-slip boundary condition. New problem arises when establishing the well-posedness in the stochastic regime: one can never derive a pathwise control of the energy functional which is used to describe the analytic radius of the solution in the deterministic setting. To this end, we establish higher-order estimates in the conormal Sobolev spaces in order to get rid of the dependence of the analytic radius on the unknown. Three approximate schemes are constructed for solving the stochastic Prandtl equation, and a local well-posedness is obtained in a tangentially analytic and normally Sobolev-type space. Furthermore, we study the stochastic Prandtl equation driven by a tangential random diffusion, and find that the noise regularizes the equation in the sense that in both two and three dimensions, there exists a global Gevrey-2 solution with high probability and the radius growing linearly in time.

math.AP↗

arXiv2024

Partial Difference Sets with Denniston Parameters in Elementary Abelian $p$-Groups

Denniston \cite{D1969} constructed partial difference sets (PDS) with parameters $(2^{3m}, (2^{m+r}-2^m+2^r)(2^m-1), 2^m-2^r+(2^{m+r}-2^m+2^r)(2^r-2), (2^{m+r}-2^m+2^r)(2^r-1))$ in elementary abelian groups of order $2^{3m}$ for all $m\geq 2$ and $1 \leq r < m$. These PDS correspond to maximal arcs in the Desarguesian projective planes PG$(2, 2^m)$. Davis et al. \cite{DHJP2024} and also De Winter \cite{dewinter23} presented constructions of PDS with Denniston parameters $(p^{3m}, (p^{m+r}-p^m+p^r)(p^m-1), p^m-p^r+(p^{m+r}-p^m+p^r)(p^r-2), (p^{m+r}-p^m+p^r)(p^r-1))$ in elementary abelian groups of order $p^{3m}$ for all $m \geq 2$ and $r \in \{1, m-1\}$, where $p$ is an odd prime. The constructions in \cite{DHJP2024, dewinter23} are particularly intriguing, as it was shown by Ball, Blokhuis, and Mazzocca \cite{BBM1997} that no nontrivial maximal arcs in PG$(2, q^m)$ exist for any odd prime power $q$. In this paper, we show that PDS with Denniston parameters $(q^{3m}, (q^{m+r}-q^m+q^r)(q^m-1), q^m-q^r+(q^{m+r}-q^m+q^r)(q^r-2), (q^{m+r}-q^m+q^r)(q^r-1))$ exist in elementary abelian groups of order $q^{3m}$ for all $m \geq 2$ and $1 \leq r < m$, where $q$ is an arbitrary prime power.

math.CO↗

arXiv2024

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation. We propose AccDiffusion, an accurate method for patch-wise higher-resolution image generation without training. An in-depth analysis in this paper reveals an identical text prompt for different patches causes repeated object generation, while no prompt compromises the image details. Therefore, our AccDiffusion, for the first time, proposes to decouple the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of an image patch. Besides, AccDiffusion also introduces dilated sampling with window interaction for better global consistency in higher-resolution image generation. Experimental comparison with existing methods demonstrates that our AccDiffusion effectively addresses the issue of repeated object generation and leads to better performance in higher-resolution image generation.

cs.CV↗

arXiv2024

Synergizing Machine Learning with ACOPF: A Comprehensive Overview

Alternative current optimal power flow (ACOPF) problems have been studied for over fifty years, and yet the development of an optimal algorithm to solve them remains a hot and challenging topic for researchers because of their nonlinear and nonconvex nature. A number of methods based on linearization and convexification have been proposed to solve to ACOPF problems, which result in near-optimal or local solutions, not optimal solutions. Nowadays, with the prevalence of machine learning, some researchers have begun to utilize this technology to solve ACOPF problems using the historical data generated by the grid operators. The present paper reviews the research on solving ACOPF problems using machine learning and neural networks and proposes future studies. This body of research is at the beginning of this area, and further exploration can be undertaken into the possibilities of solving ACOPF problems using machine learning.

math.OC↗

arXiv2024

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors

Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in MCQs within few-shot scenarios, in which the LLM's performance may be influenced by the presentation of answer choices, leaving the selection bias during Supervised Fine-Tuning (SFT) unexplored. In this paper, we reveal that selection bias persists in the SFT phase , primarily due to the LLM's inadequate Multiple Choice Symbol Binding (MCSB) ability. This limitation implies that the model struggles to associate the answer options with their corresponding symbols (e.g., A/B/C/D) effectively. To enhance the model's MCSB capability, we first incorporate option contents into the loss function and subsequently adjust the weights of the option symbols and contents, guiding the model to understand the option content of the current symbol. Based on this, we introduce an efficient SFT algorithm for MCQs, termed Point-wise Intelligent Feedback (PIF). PIF constructs negative instances by randomly combining the incorrect option contents with all candidate symbols, and proposes a point-wise loss to provide feedback on these negative samples into LLMs. Our experimental results demonstrate that PIF significantly reduces the model's selection bias by improving its MCSB capability. Remarkably, PIF exhibits a substantial enhancement in the accuracy for MCQs.

cs.CL↗

arXiv2024

Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters numerous challenges, including the objective mismatch issue, leading to suboptimal performance in Natural Language Understanding (NLU) tasks. To address this limitation, we propose a novel Reinforcement Learning framework enhanced with Label-sensitive Reward (RLLR) to amplify the performance of LLMs in NLU tasks. By incorporating label-sensitive pairs into reinforcement learning, our method aims to adeptly capture nuanced label-sensitive semantic features during RL, thereby enhancing natural language understanding. Experiments conducted on five diverse foundation models across eight tasks showcase promising results. In comparison to Supervised Fine-tuning models (SFT), RLLR demonstrates an average performance improvement of 1.54%. Compared with RLHF models, the improvement averages at 0.69%. These results reveal the effectiveness of our method for LLMs in NLU tasks. Code and data available at: https://github.com/MagiaSN/ACL2024_RLLR.

cs.CL↗

arXiv2024

Roadmap on Data-Centric Materials Science

Science is and always has been based on data, but the terms "data-centric" and the "4th paradigm of" materials research indicate a radical change in how information is retrieved, handled and research is performed. It signifies a transformative shift towards managing vast data collections, digital repositories, and innovative data analytics methods. The integration of Artificial Intelligence (AI) and its subset Machine Learning (ML), has become pivotal in addressing all these challenges. This Roadmap on Data-Centric Materials Science explores fundamental concepts and methodologies, illustrating diverse applications in electronic-structure theory, soft matter theory, microstructure research, and experimental techniques like photoemission, atom probe tomography, and electron microscopy. While the roadmap delves into specific areas within the broad interdisciplinary field of materials science, the provided examples elucidate key concepts applicable to a wider range of topics. The discussed instances offer insights into addressing the multifaceted challenges encountered in contemporary materials research.

cond-mat.mtrl-sci↗

arXiv2024

UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systems

Knowledge-based dialogue systems with internet retrieval have recently attracted considerable attention from researchers. The dialogue systems overcome a major limitation of traditional knowledge dialogue systems, where the timeliness of knowledge cannot be assured, hence providing greater practical application value. Knowledge-based dialogue systems with internet retrieval can be typically segmented into three tasks: Retrieval Decision, Query Generation, and Response Generation. However, many of studies assumed that all conversations require external knowledge to continue, neglecting the critical step of determining when retrieval is necessary. This assumption often leads to an over-dependence on external knowledge, even when it may not be required. Our work addresses this oversight by employing a single unified model facilitated by prompt and multi-task learning approaches. This model not only decides whether retrieval is necessary but also generates retrieval queries and responses. By integrating these functions, our system leverages the full potential of pre-trained models and reduces the complexity and costs associated with deploying multiple models. We conducted extensive experiments to investigate the mutual enhancement among the three tasks in our system. What is more, the experiment results on the Wizint and Dusinc datasets not only demonstrate that our unified model surpasses the baseline performance for individual tasks, but also reveal that it achieves comparable results when contrasted with SOTA systems that deploy separate, specialized models for each task.

cs.IR↗

arXiv2024

An eigenvalue problem for self-similar patterns in Hele-Shaw flows

Hele-Shaw problems are prototypes to study the interface dynamics. Linear theory suggests the existence of self-similar patterns in a Hele-Shaw flow. That is, with a specific injection flux the interface shape remains unchanged while its size increases. In this paper, we explore the existence of self-similar patterns in the nonlinear regime and develop a rigorous nonlinear theory characterizing their fundamental features. Using a boundary integral formulation, we pose the question of self-similarity as a generalized nonlinear eigenvalue problem, involving two nonlinear integral operators. The flux constant $C$ is the eigenvalue and the corresponding self-similar pattern $\mathbf{x}$ is the eigenvector. We develop a quasi-Newton method to solve the problem and show the existence of nonlinear shapes with $k$-fold dominated symmetries. The influence of initial guesses on the self-similar patterns is investigated. We are able to obtain a desired self-similar shape once the initial guess is properly chosen. Our results go beyond the predictions of linear theory and establish a bridge between the linear theory and simulations.

math.AP↗