arXiv subjects

Ningning Zhang

Publications and source records attributed to Ningning Zhang.

8 recordsLinked to original sources

arXiv2026

HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents

Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under continuous interaction settings. Inspired by cognitive theories, we propose HiMem, a hierarchical long-term memory framework for long-horizon dialogues, designed to support memory construction, retrieval, and dynamic updating during sustained interactions. HiMem constructs cognitively consistent Episode Memory via a Topic-Aware Event--Surprise Dual-Channel Segmentation strategy, and builds Note Memory that captures stable knowledge through a multi-stage information extraction pipeline. These two memory types are semantically linked to form a hierarchical structure that bridges concrete interaction events and abstract knowledge, enabling efficient retrieval without sacrificing information fidelity. HiMem supports both hybrid and best-effort retrieval strategies to balance accuracy and efficiency, and incorporates conflict-aware Memory Reconsolidation to revise and supplement stored knowledge based on retrieval feedback. This design enables continual memory self-evolution over long-term use. Experimental results on long-horizon dialogue benchmarks demonstrate that HiMem consistently outperforms representative baselines in accuracy, consistency, and long-term reasoning, while maintaining favorable efficiency. Overall, HiMem provides a principled and scalable design paradigm for building adaptive and self-evolving LLM-based conversational agents. The code is available at https://github.com/jojopdq/HiMem.

cs.AI↗

arXiv2025

Credible Plan-Driven RAG Method for Multi-Hop Question Answering

Retrieval-augmented generation (RAG) has demonstrated strong performance in single-hop question answering (QA) by integrating external knowledge into large language models (LLMs). However, its effectiveness remains limited in multi-hop QA, which demands both stable reasoning and factual consistency. Existing approaches often provide partial solutions, addressing either reasoning trajectory stability or factual verification, but rarely achieving both simultaneously. To bridge this gap, we propose PAR-RAG, a three-stage Plan-then-Act-and-Review framework inspired by the PDCA cycle. PAR-RAG incorporates semantic complexity as a unifying principle through three key components: (i) complexity-aware exemplar selection guides plan generation by aligning decomposition granularity with question difficulty, thereby stabilizing reasoning trajectories; (ii) execution follows a structured retrieve-then-read process; and (iii) dual verification identifies and corrects intermediate errors while dynamically adjusting verification strength based on question complexity: emphasizing accuracy for simple queries and multi-evidence consistency for complex ones. This cognitively inspired framework integrates theoretical grounding with practical robustness. Experiments across diverse benchmarks demonstrate that PAR-RAG consistently outperforms competitive baselines, while ablation studies confirm the complementary roles of complexity-aware planning and dual verification. Collectively, these results establish PAR-RAG as a robust and generalizable framework for reliable multi-hop reasoning.

cs.CL↗

arXiv2024

Exploring the Impact of AI-generated Image Tools on Professional and Non-professional Users in the Art and Design Fields

The rapid proliferation of AI-generated image tools is transforming the art and design fields, challenging traditional notions of creativity and impacting both professional and non-professional users. For the purposes of this paper, we define 'professional users' as individuals who self-identified in our survey as 'artists,' 'designers,' 'filmmakers,' or 'art and design students,' and 'non-professional users' as individuals who self-identified as 'others.' This study explores how AI-generated image tools influence these different user groups. Through an online survey (N=380) comprising 173 professional users and 207 non-professional users, we examine differences in the utilization of AI tools, user satisfaction and challenges, applications in creative processes, perceptions and impacts, and acceptance levels. Our findings indicate persistent concerns about image quality, cost, and copyright issues. Additionally, the usage patterns of non-professional users suggest that AI tools have the potential to democratize creative processes, making art and design tasks more accessible to individuals without traditional expertise. This study provides insights into the needs of different user groups and offers recommendations for developing more user-centered AI tools, contributing to the broader discussion on the future of AI in the art and design fields.

cs.HC↗

arXiv2024

Gravity effects on a bio-inspired self-burrowing probe in granular soils

In recent years, self-burrowing probes have been studied since they can be suitable for soil monitoring in locations with limited access such as outer space bodies and underneath existing structures. We study the performance of a self-burrowing probe under different gravity conditions, from low gravity (i.e., 1/6g, 1/3g and 1g) to high gravity (i.e., 5g, 10g and 15g), specifically in terms of penetration distance and energy consumption. Results show that the probe reaches efficient penetration in all gravity conditions and that it achieves larger penetration distances in high gravity conditions. However, the penetration efficiency, shown as unit energy per meter, is higher in low gravity. Additionally, we prove that a simple dimensional analysis provides reasonable scaling factors for first order effects in forces, velocities and energy. The findings in this study give confidence to the potential use of self-burrowing probes in campaigns of soil testing and sensor deployment in outer space or centrifuges in which the gravity conditions can differ from Earth.

cond-mat.soft↗

arXiv2024

MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention

Problematic smartphone use negatively affects physical and mental health. Despite the wide range of prior research, existing persuasive techniques are not flexible enough to provide dynamic persuasion content based on users' physical contexts and mental states. We first conducted a Wizard-of-Oz study (N=12) and an interview study (N=10) to summarize the mental states behind problematic smartphone use: boredom, stress, and inertia. This informs our design of four persuasion strategies: understanding, comforting, evoking, and scaffolding habits. We leveraged large language models (LLMs) to enable the automatic and dynamic generation of effective persuasion content. We developed MindShift, a novel LLM-powered problematic smartphone use intervention technique. MindShift takes users' in-the-moment app usage behaviors, physical contexts, mental states, goals \& habits as input, and generates personalized and dynamic persuasive content with appropriate persuasion strategies. We conducted a 5-week field experiment (N=25) to compare MindShift with its simplified version (remove mental states) and baseline techniques (fixed reminder). The results show that MindShift improves intervention acceptance rates by 4.7-22.5% and reduces smartphone usage duration by 7.4-9.8%. Moreover, users have a significant drop in smartphone addiction scale scores and a rise in self-efficacy scale scores. Our study sheds light on the potential of leveraging LLMs for context-aware persuasion in other behavior change domains.

cs.CL↗

arXiv2023

Quantiled conditional variance, skewness, and kurtosis by Cornish-Fisher expansion

The conditional variance, skewness, and kurtosis play a central role in time series analysis. These three conditional moments (CMs) are often studied by some parametric models but with two big issues: the risk of model mis-specification and the instability of model estimation. To avoid the above two issues, this paper proposes a novel method to estimate these three CMs by the so-called quantiled CMs (QCMs). The QCM method first adopts the idea of Cornish-Fisher expansion to construct a linear regression model, based on $n$ different estimated conditional quantiles. Next, it computes the QCMs simply and simultaneously by using the ordinary least squares estimator of this regression model, without any prior estimation of the conditional mean. Under certain conditions, the QCMs are shown to be consistent with the convergence rate $n^{-1/2}$. Simulation studies indicate that the QCMs perform well under different scenarios of Cornish-Fisher expansion errors and quantile estimation errors. In the application, the study of QCMs for three exchange rates demonstrates the effectiveness of financial rescue plans during the COVID-19 pandemic outbreak, and suggests that the existing ``news impact curve'' functions for the conditional skewness and kurtosis may not be suitable.

stat.ME↗

arXiv2023

Big portfolio selection by graph-based conditional moments method

How to do big portfolio selection is very important but challenging for both researchers and practitioners. In this paper, we propose a new graph-based conditional moments (GRACE) method to do portfolio selection based on thousands of stocks or more. The GRACE method first learns the conditional quantiles and mean of stock returns via a factor-augmented temporal graph convolutional network, which guides the learning procedure through a factor-hypergraph built by the set of stock-to-stock relations from the domain knowledge as well as the set of factor-to-stock relations from the asset pricing knowledge. Next, the GRACE method learns the conditional variance, skewness, and kurtosis of stock returns from the learned conditional quantiles by using the quantiled conditional moment (QCM) method. The QCM method is a supervised learning procedure to learn these conditional higher-order moments, so it largely overcomes the computational difficulty from the classical high-dimensional GARCH-type methods. Moreover, the QCM method allows the mis-specification in modeling conditional quantiles to some extent, due to its regression-based nature. Finally, the GRACE method uses the learned conditional mean, variance, skewness, and kurtosis to construct several performance measures, which are criteria to sort the stocks to proceed the portfolio selection in the well-known 10-decile framework. An application to NASDAQ and NYSE stock markets shows that the GRACE method performs much better than its competitors, particularly when the performance measures are comprised of conditional variance, skewness, and kurtosis.

stat.ML↗

arXiv2022

Multiscale reconstruction of porous media based on multiple dictionaries learning

Digital modeling of the microstructure is important for studying the physical and transport properties of porous media. Multiscale modeling for porous media can accurately characterize macro-pores and micro-pores in a large-FoV (field of view) high-resolution three-dimensional pore structure model. This paper proposes a multiscale reconstruction algorithm based on multiple dictionaries learning, in which edge patterns and micro-pore patterns from homology high-resolution pore structure are introduced into low-resolution pore structure to build a fine multiscale pore structure model. The qualitative and quantitative comparisons of the experimental results show that the results of multiscale reconstruction are similar to the real high-resolution pore structure in terms of complex pore geometry and pore surface morphology. The geometric, topological and permeability properties of multiscale reconstruction results are almost identical to those of the real high-resolution pore structures. The experiments also demonstrate the proposal algorithm is capable of multiscale reconstruction without regard to the size of the input. This work provides an effective method for fine multiscale modeling of porous media.

eess.IV↗