arXiv subjects

Peng Zhang

Publications and source records attributed to Peng Zhang.

At least 289 records · Page 16Linked to original sources

arXiv2025

Improving LLM-powered Recommendations with Personalized Information

Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively. In this paper, we propose a pipeline called CoT-Rec, which integrates two key Chain-of-Thought (CoT) processes -- user preference analysis and item perception analysis -- into LLM-powered recommendations, thereby enhancing the utilization of LLMs' reasoning abilities. CoT-Rec consists of two stages: (1) personalized information extraction, where user preferences and item perception are extracted, and (2) personalized information utilization, where this information is incorporated into the LLM-powered recommendation process. Experimental results demonstrate that CoT-Rec shows potential for improving LLM-powered recommendations. The implementation is publicly available at https://github.com/jhliu0807/CoT-Rec.

cs.IR↗

arXiv2025

Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspective

The rapid advancement of AI, including Large Language Models, has propelled autonomous agents forward, accelerating the human-agent teaming (HAT) paradigm to leverage complementary strengths. However, HAT research remains fragmented, often focusing on isolated team development phases or specific challenges like trust calibration while overlooking the real-world need for adaptability. Addressing these gaps, a process dynamics perspective is adopted to systematically review HAT using the T$^4$ framework: Team Formation, Task and Role Development, Team Development, and Team Improvement. Each phase is examined in terms of its goals, actions, and evaluation metrics, emphasizing the co-evolution of task and team dynamics. Special focus is given to the second and third phases, highlighting key factors such as team roles, shared mental model, and backup behaviors. This holistic perspective identifies future research directions for advancing long-term adaptive HAT.

cs.HC↗

arXiv2025

Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation

Span-level emotion-cause-category triplet extraction represents a novel and complex challenge within emotion cause analysis. This task involves identifying emotion spans, cause spans, and their associated emotion categories within the text to form structured triplets. While prior research has predominantly concentrated on clause-level emotion-cause pair extraction and span-level emotion-cause detection, these methods often confront challenges originating from redundant information retrieval and difficulty in accurately determining emotion categories, particularly when emotions are expressed implicitly or ambiguously. To overcome these challenges, this study explores a fine-grained approach to span-level emotion-cause-category triplet extraction and introduces an innovative framework that leverages instruction tuning and data augmentation techniques based on large language models. The proposed method employs task-specific triplet extraction instructions and utilizes low-rank adaptation to fine-tune large language models, eliminating the necessity for intricate task-specific architectures. Furthermore, a prompt-based data augmentation strategy is developed to address data scarcity by guiding large language models in generating high-quality synthetic training data. Extensive experimental evaluations demonstrate that the proposed approach significantly outperforms existing baseline methods, achieving at least a 12.8% improvement in span-level emotion-cause-category triplet extraction metrics. The results demonstrate the method's effectiveness and robustness, offering a promising avenue for advancing research in emotion cause analysis. The source code is available at https://github.com/zxgnlp/InstruDa-LLM.

cs.CL↗

arXiv2025

Spiking Neural Network for Intra-cortical Brain Signal Decoding

Decoding brain signals accurately and efficiently is crucial for intra-cortical brain-computer interfaces. Traditional decoding approaches based on neural activity vector features suffer from low accuracy, whereas deep learning based approaches have high computational cost. To improve both the decoding accuracy and efficiency, this paper proposes a spiking neural network (SNN) for effective and energy-efficient intra-cortical brain signal decoding. We also propose a feature fusion approach, which integrates the manually extracted neural activity vector features with those extracted by a deep neural network, to further improve the decoding accuracy. Experiments in decoding motor-related intra-cortical brain signals of two rhesus macaques demonstrated that our SNN model achieved higher accuracy than traditional artificial neural networks; more importantly, it was tens or hundreds of times more efficient. The SNN model is very suitable for high precision and low power applications like intra-cortical brain-computer interfaces.

cs.HC↗

arXiv2025

Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid advancements in AI safety techniques, models have become increasingly adept at circumventing these straightforward tests, limiting their effectiveness in revealing underlying biases and ethical stances. To address this limitation, we propose an upgraded value alignment benchmark that moves beyond single-sentence prompts by incorporating multi-turn dialogues and narrative-based scenarios. This approach enhances the stealth and adversarial nature of the evaluation, making it more robust against superficial safeguards implemented in modern LLMs. We design and implement a dataset that includes conversational traps and ethically ambiguous storytelling, systematically assessing LLMs' responses in more nuanced and context-rich settings. Experimental results demonstrate that this enhanced methodology can effectively expose latent biases that remain undetected in traditional single-shot evaluations. Our findings highlight the necessity of contextual and dynamic testing for value alignment in LLMs, paving the way for more sophisticated and realistic assessments of AI ethics and safety.

cs.CL↗

arXiv2025

A reduced-scale autonomous morphing vehicle prototype with enhanced aerodynamic efficiency

Road vehicles contribute to significant levels of greenhouse gas (GHG) emissions. A potential strategy for improving their aerodynamic efficiency and reducing emissions is through active adaptation of their exterior shapes to the aerodynamic environment. In this study, we present a reduced-scale morphing vehicle prototype capable of actively interacting with the aerodynamic environment to enhance fuel economy. Morphing is accomplished by retrofitting a deformable structure actively actuated by built-in motors. The morphing vehicle prototype is integrated with an optimization algorithm that can autonomously identify the structural shape that minimizes aerodynamic drag. The performance of the morphing vehicle prototype is investigated through an extensive experimental campaign in a large-scale wind tunnel facility. The autonomous optimization algorithm identifies an optimal morphing shape that can elicit an 8.5% reduction in the mean drag force. Our experiments provide a comprehensive dataset that validates the efficiency of shape morphing, demonstrating a clear and consistent decrease in the drag force as the vehicle transitions from a suboptimal to the optimal shape. Insights gained from experiments on scaled-down models provide valuable guidelines for the design of full-size morphing vehicles, which could lead to appreciable energy savings and reductions in GHG emissions. This study highlights the feasibility and benefits of real-time shape morphing under conditions representative of realistic road environments, paving the way for the realization of full-scale morphing vehicles with enhanced aerodynamic efficiency and reduced GHG emissions.

cs.RO↗

arXiv2025

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

Real-time interactive video-chat portraits have been increasingly recognized as the future trend, particularly due to the remarkable progress made in text and voice chat technologies. However, existing methods primarily focus on real-time generation of head movements, but struggle to produce synchronized body motions that match these head actions. Additionally, achieving fine-grained control over the speaking style and nuances of facial expressions remains a challenge. To address these limitations, we introduce a novel framework for stylized real-time portrait video generation, enabling expressive and flexible video chat that extends from talking head to upper-body interaction. Our approach consists of the following two stages. The first stage involves efficient hierarchical motion diffusion models, that take both explicit and implicit motion representations into account based on audio inputs, which can generate a diverse range of facial expressions with stylistic control and synchronization between head and body movements. The second stage aims to generate portrait video featuring upper-body movements, including hand gestures. We inject explicit hand control signals into the generator to produce more detailed hand movements, and further perform face refinement to enhance the overall realism and expressiveness of the portrait video. Additionally, our approach supports efficient and continuous generation of upper-body portrait video in maximum 512 * 768 resolution at up to 30fps on 4090 GPU, supporting interactive video-chat in real-time. Experimental results demonstrate the capability of our approach to produce portrait videos with rich expressiveness and natural upper-body movements.

cs.CV↗

arXiv2025

On Distributional Discrepancy for Experimental Design with General Assignment Probabilities

We investigate experimental design for randomized controlled trials (RCTs) with both equal and unequal treatment-control assignment probabilities. Our work makes progress on the connection between the distributional discrepancy minimization (DDM) problem introduced by Harshaw et al. (2024) and the design of RCTs. We make two main contributions: First, we prove that approximating the optimal solution of the DDM problem within a certain constant error is NP-hard. Second, we introduce a new Multiplicative Weights Update (MWU) algorithm for the DDM problem, which improves the Gram-Schmidt walk algorithm used by Harshaw et al. (2024) when assignment probabilities are unequal. Building on the framework of Harshaw et al. (2024) and our MWU algorithm, we then develop the MWU design, which reduces the worst-case mean squared error in estimating the average treatment effect. Finally, we present a comprehensive simulation study comparing our design with commonly used designs.

stat.ME↗

arXiv2025

Dynamical Mode Recognition of Turbulent Flames in a Swirl-stabilized Annular Combustor by a Time-series Learning Approach

Thermoacoustic instability in annular combustors, essential to aero engines and modern gas turbines, can severely impair operational stability and efficiency, accurately recognizing and understanding various combustion modes is the prerequisite for understanding and controlling combustion instabilities. However, the high-dimensional spatial-temporal dynamics of turbulent flames typically pose considerable challenges to mode recognition. Based on the bidirectional temporal and nonlinear dimensionality reduction models, this study introduces a two-layer bidirectional long short-term memory variational autoencoder, Bi-LSTM-VAE model, to effectively recognize dynamical modes in annular combustion systems. Specifically, leveraging 16 pressure signals from a swirl-stabilized annular combustor, the model maps complex dynamics into a low-dimensional latent space while preserving temporal dependency and nonlinear behavior features through the recurrent neural network structure. The results show that the novel Bi-LSTM-VAE method enables a clear representation of combustion states in two-dimensional state space. Analysis of latent variable distributions reveals distinct patterns corresponding to a wide range of equivalence ratios and premixed fuel and air mass flow rates, offering novel insights into mode classification and transitions, highlighting this model's potential for deciphering complex thermoacoustic phenomena.

cs.LG↗

arXiv2025

Stabilization Analysis and Mode Recognition of Kerosene Supersonic Combustion: A Deep Learning Approach Based on Res-CNN-beta-VAE

The scramjet engine is a key propulsion system for hypersonic vehicles, leveraging supersonic airflow to achieve high specific impulse, making it a promising technology for aerospace applications. Understanding and controlling the complex interactions between fuel injection, turbulent combustion, and aerodynamic effects of compressible flows are crucial for ensuring stable combustion in scramjet engines. However, identifying stable modes in scramjet combustors is often challenging due to limited experimental measurement means and extremely complex spatiotemporal evolution of supersonic turbulent combustion. This work introduces an innovative deep learning framework that combines dimensionality reduction via the Residual Convolutional Neural Network-beta-Variational Autoencoder (Res-CNN-beta-VAE) model with unsupervised clustering (K-means) to identify and analyze dynamical combustion modes in a supersonic combustor. By mapping high-dimensional data of combustion snapshots to a reduced three-dimensional latent space, the Res-CNN-beta-VAE model captures the essential temporal and spatial features of flame behaviors and enables the observation of transitions between combustion states. By analyzing the standard deviation of latent variable trajectories, we introduce a novel method for objectively distinguishing between dynamic transitions, which provides a scalable and expert-independent alternative to traditional classification methods. Besides, the unsupervised K-means clustering approach effectively identifies the complex interplay between the cavity and the jet-wake stabilization mechanisms, offering new insights into the system's behavior across different gas-to-liquid mass flow ratios (GLRs).

physics.flu-dyn↗

arXiv2025

MDiff-FMT: Morphology-aware Diffusion Model for Fluorescence Molecular Tomography with Small-scale Datasets

Fluorescence molecular tomography (FMT) is a sensitive optical imaging technology widely used in biomedical research. However, the ill-posedness of the inverse problem poses a huge challenge to FMT reconstruction. Although end-to-end deep learning algorithms have been widely used to address this critical issue, they still suffer from high data dependency and poor morphological restoration. In this paper, we report for the first time a morphology-aware diffusion model, MDiff-FMT, based on denoising diffusion probabilistic model (DDPM) to achieve high-fidelity morphological reconstruction for FMT. First, we use the noise addition of DDPM to simulate the process of the gradual degradation of morphological features, and achieve fine-grained reconstruction of morphological features through a stepwise probabilistic sampling mechanism, avoiding problems such as loss of structure details that may occur in end-to-end deep learning methods. Additionally, we introduce the conditional fluorescence image as structural prior information to sample a high-fidelity reconstructed image from the noisy images. Numerous numerical and real phantom experimental results show that the proposed MDiff-FMT achieves SOTA results in morphological reconstruction of FMT without relying on large-scale datasets.

eess.IV↗

arXiv2025

Evolution of the Three Spectral Components in the Prompt Emission of GRB 240825A

The prompt emission of Gamma-Ray Bursts (GRBs) could be composed of different spectral components, such as a dominant non-thermal Band component in the keV-MeV range, a subdominant quasi-thermal component, and an additional hard non-thermal component extending into the GeV range. The existence and evolutionary behaviors of these components could place strong implication on physical models, such as ejecta composition and dissipation processes. Although numerous GRBs have been found to exhibit one or two spectral components, reports of GRBs containing all three components remain rare. In this letter, based on the joint observations of GRB 240825A from multiple gamma-ray telescopes, we conduct a comprehensive temporal and spectral analysis to identify the presence and evolution of all three components. The bulk Lorentz factor of this bright and relatively short-duration burst is independently calculated using the thermal and hard non-thermal components, supporting a jet penetration scenario. The multi-segment broken powerlaw feature observed in the flux light curves suggests the presence of an early afterglow in the keV-MeV band and hints at a possible two-jet structure. Furthermore, the observed transition from positive to negative on the spectral lag can be interpreted as an independent evolution of the soft and hard components, leading to misalignment in the cross-correlation function (CCF) analysis of pulses.

astro-ph.HE↗

arXiv2025

Action Functional as an Early Warning Indicator in the Space of Probability Measures via Schrödinger Bridge

Critical transitions and tipping phenomena between two meta-stable states in stochastic dynamical systems are a significant scientific issue. In this work, we expand the methodology of identifying the most probable transition pathway between two meta-stable states with Onsager-Machlup action functional, to investigate the evolutionary transition dynamics between two meta-stable invariant sets with Schrödinger bridge. In contrast to existing methodologies such as statistical analysis, bifurcation theory, information theory, statistical physics, topology, and graph theory for early warning indicators, we introduce a novel framework on Early Warning Signals (EWS) within the realm of probability measures that align with the entropy production rate (EPR). To validate our framework, we apply it to the Morris-Lecar model and investigate the transition dynamics between a meta-stable state and a stable invariant set (the limit cycle or homoclinic orbit) under various conditions. Additionally, we analyze real Alzheimer's data from the Alzheimer's Disease Neuroimaging Initiative database to explore EWS indicating the transition from healthy to pre-AD states. This framework not only expands the transition pathway to encompass measures between two specified densities on invariant sets, but also demonstrates the potential of our early warning indicators for complex diseases.

math.DS↗

arXiv2025

Search for Double Beta Decay of $^{136}$Xe to the $0^+_1$ Excited State of $^{136}$Ba with PandaX-4T

We perform a search of double beta decay of $^{136}$Xe to the excited state, $0^+_1$, of $^{136}$Ba (2$νββ$-0$_1^+$), using the dual-phase xenon detector of PandaX-4T with the first 94.9-day commissioning data. The multi-site events are reconstructed up to the MeV energy scale, which helps to improve the background model significantly. The background contribution from the stainless steel platform outside PandaX-4T cryostat is evaluated for the first time. No significant evidence for 2$νββ$-$0_1^+$ is observed, resulting in a lower limit on half-life of $7.5 \times 10^{22}$ yr at the 90% confidence level. This is the first experimental limit on such a rare decay in a natural xenon-based detector.

nucl-ex↗

arXiv2025

Search for MeV-Scale Axionlike Particles and Dark Photons with PandaX-4T

Axionlike particles (ALPs) and dark photons (DPs) are viable dark matter particle candidates. We have searched for possible ALP/DP signals in the PandaX-4T liquid xenon detector using 440 kg$\cdot$yr of data. A binned likelihood fit is constructed to search for possible mono-energetic peaks induced by the absorption processes between ALPs/DPs and atomic electrons of xenon. A detailed temporal model of decays associated with xenon isotopes is introduced to constrain the number of background events. No signal excess over background expectations is observed, and we have established the most stringent exclusion limits for most ALP/DP masses across the range of 150 keV/$c^2$ to 1 MeV/$c^2$. The improvement is particularly significant within the mass range of \text{150-400}~keV/$c^2$, with the average factor of 3.5 compared to previous results.

hep-ex↗

arXiv2025

YouthCare: Building a Personalized Collaborative Video Censorship Tool to Support Parent-Child Joint Media Engagement

To mitigate the negative impacts of online videos on teenagers, existing research and platforms have implemented various parental mediation mechanisms, such as Parent-Child Joint Media Engagement (JME). However, JME generally relies heavily on parents' time, knowledge, and experience. To fill this gap, we aim to design an automatic tool to help parents/children censor videos more effectively and efficiently in JME. For this goal, we first conducted a formative study to identify the needs and expectations of teenagers and parents for such a system. Based on the findings, we designed YouthCare, a personalized collaborative video censorship tool that supports parents and children to collaboratively filter out inappropriate content and select appropriate content in JME. An evaluation with 10 parent-child pairs demonstrated YouthCare's several strengths in supporting video censorship, while also highlighting some potential problems. These findings inspire us to propose several insights for the future design of parent-child collaborative JME systems.

cs.HC↗

arXiv2025

RemiHaven: Integrating "In-Town" and "Out-of-Town" Peers to Provide Personalized Reminiscence Support for Older Drifters

With increasing social mobility and an aging society, more older adults in China are migrating to new cities, known as "older drifters." Due to fewer social connections and cultural adaptation challenges, they face negative emotions such as loneliness and depression. While reminiscence-based interventions have been used to improve older adults' psychological well-being, challenges such as the lack of tangible materials and limited social resources constrain the feasibility of traditional reminiscence approaches for older drifters. To address this challenge, we designed RemiHaven, a personalized reminiscence support tool based on a two-phase formative study. It integrates "In-Town" and "Out-of-Town" peer agents to enhance personalization, engagement, and emotional resonance in the reminiscence process, powered by Multimodal Large Language Models (MLLMs). Our evaluations show RemiHaven's strengths in supporting reminiscence while identifying potential challenges. We conclude by offering insights for the future design of reminiscence support tools for older migrants.

cs.HC↗

arXiv2025

Back to business: SLX 1746--331 after 13 years of silence

The black hole candidate system SLX 1746--331 was back to business in 2023, after a long silence of roughly 13 years. An outburst was observed thoroughly by \textit{Insight}-HXMT and \textit{NICER}. The outburst is characterized by spectral dominance of the soft state, where the joint \textit{Insight}-HXMT and \textit{NICER} spectral analysis shows the temperature dependence of the disk flux follows $T_{\rm in}^{3.98}$, and thus suggests that the inner disk reaches to ISCO during almost the entire outburst. By assuming 0.3 $L_{\rm Edd}$ for the peak flux and an inclination angle of zero degrees, the lower limit of the compact object hosted in this system is estimated as 3.28$\pm 2.14 M_\odot$. We also look into the relation of the disk temperature and disk flux for a sample of black hole systems, and by taking the disk temperature derived in the outburst of SLX 1746--331, such a relation results in a mass estimation of $5.2 \pm 4.5M_\odot$. Finally, the spin of the compact object is constrained to larger than 0.8 with a spectral model of kerrbb.

astro-ph.HE↗