Author name cluster

Qing Ye

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

1 author row

AAAI Conference 2026 Conference Paper

AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing

Qingyu Zhang
Chunlei Xin
Xuanang Chen
Yaojie Lu
Hongyu Lin
Xianpei Han
Le Sun
Qing Ye

Goal-driven persuasive dialogue, exemplified by applications like telemarketing, requires sophisticated multi-turn planning and strict factual faithfulness, which remains a significant challenge for even state-of-the-art Large Language Models (LLMs). A lack of task-specific data often limits previous works, and direct LLM application suffers from strategic brittleness and factual hallucination. In this paper, we first construct and release TeleSalesCorpus, the first real-world-grounded dialogue dataset for this domain. We then propose AI-Salesman, a novel framework featuring a dual-stage architecture. For the training stage, we design a Bayesian-supervised reinforcement learning algorithm that learns robust sales strategies from noisy dialogues. For the inference stage, we introduce the Dynamic Outline-Guided Agent (DOGA), which leverages a pre-built script library to provide dynamic, turn-by-turn strategic guidance. Moreover, we design a comprehensive evaluation framework that combines fine-grained metrics for key sales skills with the LLM-as-a-Judge paradigm. Experimental results demonstrate that our proposed AI-Salesman significantly outperforms baseline models in both automatic metrics and comprehensive human evaluations, showcasing its effectiveness in complex persuasive scenarios.

PDF Details DOI

EAAI Journal 2026 Journal Article

Appearance-semantic graphical model for human-object interaction detection

Qing Ye
Tao Yang
Xikun Wang
Yongmei Zhang

Human object interaction detection has important applications in fields such as surveillance system and autonomous driving. But the existing methods of human-object interaction detection include the following limitations: insufficient use of spatial information and insufficient referential information when detecting interaction categories. Aiming at these problems, we proposed an appearance-semantic graphical model for human-object interaction detection algorithm. To solve the insufficient use of spatial information problem, we proposed a Depthwise Separable convolutional Multi-Resolution feature Enhancement Network, which extracts features through multiple resolution feature branches in parallel and utilizes the attention mechanism to shift the focus of the network to the region where the interaction occurs. This network can more adequately extract the image features and enhance the feature expression. To solve the problem of insufficient referential information, we proposed an Appearance - Semantic interaction reasoning Graphical Model. The model consists of a two-layer graphical model, constructing the graphical model with the target appearance feature vectors and word vectors as the nodes of the appearance layer and the semantic layer. The corresponding nodes are connected by unidirectional edges, using graph convolution for information transfer, which enriches the referential information in the recognition process. The mean average precision of the algorithm proposed in this paper is 63. 31% (Scenario 2) and 31. 86% (Known Object) on the interaction behavior recognition benchmark datasets Verbs in Common Objects in Context and Humans Interacting with Common Objects, respectively. The effectiveness of our algorithm has been verified in comparison with some other human-object interaction detection methods. The method shows great potential in practical applications such as surveillance system and autonomous driving.

Details DOI

AAAI Conference 2025 Conference Paper

A Spatio-temporal Cluster-aware Supervised Learning Framework for Predicting County-level Drug Overdose Deaths

Zixuan Feng
Qing Ye
Weijun Xie
Qiushi Chen

The soaring drug overdose crisis in the United States has claimed more than half a million lives in the past decade and remains a major public health threat. The ability to predict drug overdose deaths at the county level can help local communities develop action plans in response to emerging changes. Applying off-the-shelf machine learning algorithms for prediction can be challenging due to the heterogeneous risk profiles of the counties and suppressed data in common publicly available data sources. To fill these gaps, we develop a cluster-aware supervised learning (CASL) framework to enhance the prediction of county-level drug overdose deaths. This CASL model simultaneously clusters counties into groups based on geographical and socioeconomic characteristics and minimizes the loss function that accounts for suppressed values and cluster-specific regularization. Our computational study uses real-world data from 2010 to 2021, focusing on the ten states most severely impacted by the drug overdose crisis. The results demonstrate that our proposed CASL framework significantly outperforms state-of-the-art methods by achieving a superior balance in prediction accuracy for both unsuppressed and suppressed observations. The proposed model also identifies different clusters of counties, capturing heterogeneous patterns of overdose mortality among counties of diverse characteristics.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths

Jindi Lv
Yuhao Zhou
Mingjia Shi
Zhiyuan Liang
Panpan Zhang
Xiaojiang Peng
Wangbo Zhao
Zheng Zhu

Mamba has proven efficient for long-sequence modeling in vision tasks. However, when token reduction techniques are applied to improve efficiency, Mamba-based models exhibit drastic performance degradation compared to Vision Transformers (ViTs). This decline is potentially attributed to Mamba's chain-like scanning mechanism, which we hypothesize not only induces cascading losses in token connectivity but also limits the diversity of spatial receptive fields. In this paper, we propose Asymmetric Multi-scale Vision Mamba (AMVim), a novel architecture designed to enhance pruning robustness. AMVim employs a dual-path structure, integrating a window-aware scanning mechanism into one path while retaining sequential scanning in the other. This asymmetry design promotes token connection diversity and enables multi-scale information flow, reinforcing spatial awareness. Empirical results demonstrate that AMVim achieves state-of-the-art pruning robustness. During token reduction, AMVim-T achieves a substantial 34\% improvement in training-free accuracy with identical model sizes and FLOPs. Meanwhile, AMVim-S exhibits only a 1. 5\% accuracy drop, performing comparably to ViT. Notably, AMVim also delivers superior performance during pruning-free settings, further validating its architectural advantages.

PDF Details

NeurIPS Conference 2023 Conference Paper

PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.

Mingjia Shi
Yuhao Zhou
Kai Wang
Huaizheng Zhang
Shudong Huang
Qing Ye
Jiancheng Lv

Classical federated learning (FL) enables training machine learning models without sharing data for privacy preservation, but heterogeneous data characteristic degrades the performance of the localized model. Personalized FL (PFL) addresses this by synthesizing personalized models from a global model via training on local data. Such a global model may overlook the specific information that the clients have been sampled. In this paper, we propose a novel scheme to inject personalized prior knowledge into the global model in each client, which attempts to mitigate the introduced incomplete information problem in PFL. At the heart of our proposed approach is a framework, the $\textit{PFL with Bregman Divergence}$ (pFedBreD), decoupling the personalized prior from the local objective function regularized by Bregman divergence for greater adaptability in personalized scenarios. We also relax the mirror descent (RMD) to extract the prior explicitly to provide optional strategies. Additionally, our pFedBreD is backed up by a convergence analysis. Sufficient experiments demonstrate that our method reaches the $\textit{state-of-the-art}$ performances on 5 datasets and outperforms other methods by up to 3. 5% across 8 benchmarks. Extensive analyses verify the robustness and necessity of proposed designs. The code will be made public.

PDF Details

TIST Journal 2021 Journal Article

PP-PG: Combining Parameter Perturbation with Policy Gradient Methods for Effective and Efficient Explorations in Deep Reinforcement Learning

Shilei Li
Meng Li
Jiongming Su
Shaofei Chen
Zhimin Yuan
Qing Ye

Efficient and stable exploration remains a key challenge for deep reinforcement learning (DRL) operating in high-dimensional action and state spaces. Recently, a more promising approach by combining the exploration in the action space with the exploration in the parameters space has been proposed to get the best of both methods. In this article, we propose a new iterative and close-loop framework by combining the evolutionary algorithm (EA), which does explorations in a gradient-free manner directly in the parameters space with an actor-critic, and the deep deterministic policy gradient (DDPG) reinforcement learning algorithm, which does explorations in a gradient-based manner in the action space to make these two methods cooperate in a more balanced and efficient way. In our framework, the policies represented by the EA population (the parametric perturbation part) can evolve in a guided manner by utilizing the gradient information provided by the DDPG and the policy gradient part (DDPG) is used only as a fine-tuning tool for the best individual in the EA population to improve the sample efficiency. In particular, we propose a criterion to determine the training steps required for the DDPG to ensure that useful gradient information can be generated from the EA generated samples and the DDPG and EA part can work together in a more balanced way during each generation. Furthermore, within the DDPG part, our algorithm can flexibly switch between fine-tuning the same previous RL-Actor and fine-tuning a new one generated by the EA according to different situations to further improve the efficiency. Experiments on a range of challenging continuous control benchmarks demonstrate that our algorithm outperforms related works and offers a satisfactory trade-off between stability and sample efficiency.

Details DOI

YNICL Journal 2019 Journal Article

Disrupted functional and structural connectivity within default mode network contribute to WMH-related cognitive impairment

Xin Chen
Lili Huang
Qing Ye
Dan Yang
Ruomeng Qin
Caimei Luo
Mengchun Li
Bing Zhang

AIMS: The prevalence of white matter hyperintensities (WMH) rises dramatically with aging. Both the progression of WMH and changing patterns of default mode network (DMN) have been proven to be closely associated with cognitive function. The present study hypothesized that changes in functional connectivity and structural connectivity of DMN contributed to WMH related cognitive impairment. METHODS: A total of 116 subjects were enrolled from the Cerebral Small Vessel Disease Register in Drum Tower Hospital of Nanjing University, and were distributed across three categories according to Fazekas rating scale: WMH I (n = 57), WMH II (n = 34), and WMH III(n = 25). All participants underwent neuropsychological tests and multimodal MRI scans, including diffusion tensor imaging and resting-state fMRI imaging. The alterations of functional connectivity and structural connectivity within the DMN were further explored. RESULTS: Age and hypertension were risk factors for WMH progression. Subjects with a higher WMH burden displayed higher DMN functional connectivity in the medial frontal gyrus, while lower DMN functional connectivity in the thalamus. After adjusting for aging, gender, and education, the increased DMN functional connectivity in the medial frontal gyrus, and the increased mean diffusivity of the white matter tracts between the hippocampus and posterior cingulate cortex were independent indicators of worse performance in memory. Moreover, the decreased DMN functional connectivity in the thalamus and increased mean diffusivity of the white matter tracts between the thalamus and posterior cingulate cortex were independent risk factors for a slower processing speed. CONCLUSION: The changes in functional connectivity and structural connectivity within the DMN attributed to WMH progression were responsible for the development of cognitive impairment.

Details DOI

YNICL Journal 2017 Journal Article

Brain insulin resistance deteriorates cognition by altering the topological features of brain networks

Fan Su
Hao Shu
Qing Ye
Zan Wang
Chunming Xie
Baoyu Yuan
Zhijun Zhang
Feng Bai

Insulin resistance represents one of the mechanisms underlying the link between type 2 diabetes (T2D) and Alzheimer's disease (AD), and we explored its in vivo neurobiology related to cognition based on a pathway-based genetic association analyses. Eighty-seven mild cognitive impairment (MCIs) subjects and 135 matched controls (HCs) were employed at baseline, and they underwent functional MRI scans, clinical evaluations and exon sequencings of 20 genes related to brain insulin resistance. A longitudinal study for an average of 35 months was performed to assess their cognitive decline over time. By using cognition as the phenotype, we detected genes that modified cognitive impairments, including AKT2, PIK3CB, IGF1R, PIK3CD, MTOR, IDE, AKT1S1 and AKT1. Based on these loci, the mass univariate modeling was utilized to construct the functional network. The MCIs showed disconnections mainly in the cerebellum-frontal-temporal regions, while compensations may occur in frontal-parietal regions to maintain the overall network efficiency. Moreover, the behavioral significance of the network was highlighted, as topological characteristics of the medial temporal lobe and the prefrontal cortex partially determine longitudinal cognitive decline. Our results suggested that the restoration of insulin activity represents a promising therapeutic target for alleviating cognitive decline associated with T2D and AD.

Details DOI