Arrow Research search

Author name cluster

Meng Sun

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.

12 papers
2 author rows

Possible papers

12

EAAI Journal 2026 Journal Article

Merging physics and neural network: A promising tool for prognostics and health management

  • Fujin Wang
  • Weiyuan Liu
  • Meng Sun
  • Zhi Zhai
  • Zhibin Zhao
  • Xuefeng Chen

With the rapid advancement of Industry 4. 0 and intelligent manufacturing, Prognostics and Health Management (PHM) has emerged as a pivotal component for ensuring the safety, reliability, and efficiency of complex industrial systems. By enabling real-time monitoring, fault diagnosis, and life prediction, PHM system effectively reduces equipment failure rates, extends system lifespans, and optimizes maintenance strategies, thereby achieving cost savings and enhanced productivity. The rapid development of modern signal processing and artificial intelligence technologies has significantly driven the progress of PHM theories, resulting in a plethora of innovative methodologies. While purely physics-based and purely data-driven approaches have their strengths, their limitations are equally evident. As a promising alternative, PHM technologies that merge physics and neural network are gaining traction, leveraging the advantages of both paradigms to pioneer a new framework for health management. This study defines a novel classification framework for PHM that synthesizes physics-based and neural network-based approaches. Within this framework, we examine and categorize relevant published studies, providing a tutorial to assist researchers in quickly mastering these techniques. Furthermore, we summarize the characteristics of each architecture and discuss their implementation challenges, advantages, and limitations.

Details DOI

AAAI Conference 2026 Conference Paper

Modeling Item-Level Dynamic Variability with Residual Diffusion for Bundle Recommendation

  • Dong Zhang
  • Lin Li
  • Ming Li
  • Amran Bhuiyan
  • Meng Sun
  • Xiaohui Tao
  • Jimmy Huang

Existing solutions for bundle recommendation (BR) have achieved remarkable effectiveness for predicting the user’s preference for prebuilt bundles. However, bundle-item (B-I) affiliation will vary dynamically in real scenarios. For ex ample, a bundle themed as ‘casual outfit’ may add ‘hat’ or remove ‘watch’ due to factors such as seasonal variations, changes in user preferences or inventory adjustments. Our empirical study demonstrates that the performance of main stream BR models may fluctuate or decline under item-level variability. This paper makes the first attempt to address the above problem and proposes Residual Diffusion for Bundle Recommendation (RDiffBR) as a model-agnostic generative framework which can assist a BR model in adapting this sce nario. During the initial training of the BR model, RDiffBR employs a residual diffusion model to process the item-level bundle embeddings which are generated by the BR model to represent bundle theme via a forward-reverse process. In the inference stage, RDiffBR reverses item-level bundle em beddings obtained by the well-trained bundle model under B-I variability scenarios to generate the effective item-level bundle embeddings. In particular, the residual connection in our residual approximator significantly enhances BR mod els’ ability to generate high-quality item-level bundle embed dings. Experiments on six BRmodelsandfourpublicdatasets from different domains show that RDiffBR improves the per formance of Recall and NDCG of backbone BR models by up to 23%, while only increases training time about 4%.

PDF Details DOI

ICML Conference 2025 Conference Paper

Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies

  • Qi Ju 0001
  • Thomas Tellier
  • Meng Sun
  • Zhemei Fang
  • Yunfeng Luo

Artificial intelligence (AI) has surpassed top human players in a variety of games. In imperfect information games, these achievements have primarily been driven by Counterfactual Regret Minimization (CFR) and its variants for computing Nash equilibrium. However, most existing research has focused on maximizing payoff, while largely neglecting the importance of strategic diversity and the need for varied play styles, thereby limiting AI’s adaptability to different user preferences. To address this gap, we propose Preference-CFR (Pref-CFR), a novel method that incorporates two key parameters: preference degree and vulnerability degree. These parameters enable the AI to adjust its strategic distribution within an acceptable performance loss threshold, thereby enhancing its adaptability to a wider range of strategic demands. In our experiments with Texas Hold’em, Pref-CFR successfully trained Aggressive and Loose Passive styles that not only match original CFR-based strategies in performance but also display clearly distinct behavioral patterns. Notably, for certain hand scenarios, Pref-CFR produces strategies that diverge significantly from both conventional expert heuristics and original CFR outputs, potentially offering novel insights for professional players.

Details

NeurIPS Conference 2024 Conference Paper

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models

  • Yihao Zhang
  • Zeming Wei
  • Jun Sun
  • Meng Sun

Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their behaviors through the lens of inner representation. However, developing practical and efficient methods for applying these representations for general and flexible model editing remains challenging. In this work, we explore how to leverage insights from representation engineering to guide the editing of LLMs by deploying a representation discriminator as an editing oracle. We first identify the importance of a robust and reliable discriminator during editing, then propose an \textbf{A}dversarial \textbf{R}epresentation \textbf{E}ngineering (\textbf{ARE}) framework to provide a unified and interpretable approach for conceptual model editing without compromising baseline performance. Experiments on multiple tasks demonstrate the effectiveness of ARE in various model editing scenarios. Our code and data are available at \url{https: //github. com/Zhang-Yihao/Adversarial-Representation-Engineering}.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Temporal Adaptive RGBT Tracking with Modality Prompt

  • Hongyu Wang
  • Xiaotao Liu
  • Yifan Li
  • Meng Sun
  • Dian Yuan
  • Jing Liu

RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving. Existing RGBT trackers fully explore the spatial information between the template and the search region and locate the target based on the appearance matching results. However, these RGBT trackers have very limited exploitation of temporal information, either ignoring temporal information or exploiting it through online sampling and training. The former struggles to cope with the object state changes, while the latter neglects the correlation between spatial and temporal information. To alleviate these limitations, we propose a novel Temporal Adaptive RGBT Tracking framework, named as TATrack. TATrack has a spatio-temporal two-stream structure and captures temporal information by an online updated template, where the two-stream structure refers to the multi-modal feature extraction and cross-modal interaction for the initial template and the online update template respectively. TATrack contributes to comprehensively exploit spatio-temporal information and multi-modal information for target localization. In addition, we design a spatio-temporal interaction (STI) mechanism that bridges two branches and enables cross-modal interaction to span longer time scales. Extensive experiments on three popular RGBT tracking benchmarks show that our method achieves state-of-the-art performance, while running at real-time speed.

PDF Details DOI

IROS Conference 2023 Conference Paper

Domain Adaptation on Point Clouds for 6D Pose Estimation in Bin-Picking Scenarios

  • Liang Zhao
  • Meng Sun
  • Wei Jie Lv
  • Xinyu Zhang
  • Long Zeng 0001

Training with simulated data is a common approach in pose estimation research. However, a sim-to-real gap between clean simulated data and noisy real data will seriously weaken the generalization ability of the algorithm, especially for point clouds. To address this problem, this paper proposes a domain adaptive pose estimation network (DAPE-Net). For the feature extracted from the backbone, the network will conduct the real and simulation discrimination based on a feature discriminator, and complete the pose estimation by adversarial training. This makes the network pay more attention to the domain invariant features of simulation and real point clouds to complete domain adaptation. In our experiment, DAPE-Net improved the performance of pose estimation by 10%. To solve the problem that domain adaptation requires a small amount of real data, we propose a scheme that can semi-automatically collect real data in bin-picking scenarios for 6D pose estimation.

Details

AAAI Conference 2021 Conference Paper

Decision-Guided Weighted Automata Extraction from Recurrent Neural Networks

  • Xiyue Zhang
  • Xiaoning Du
  • Xiaofei Xie
  • Lei Ma
  • Yang Liu
  • Meng Sun

Recurrent Neural Networks (RNNs) have demonstrated their effectiveness in learning and processing sequential data (e. g. , speech and natural language). However, due to the black-box nature of neural networks, understanding the decision logic of RNNs is quite challenging. Some recent progress has been made to approximate the behavior of an RNN by weighted automata. They provide better interpretability, but still suffer from poor scalability. In this paper, we propose a novel approach to extracting weighted automata with the guidance of a target RNN’s decision and context information. In particular, we identify the patterns of RNN’s step-wise predictive decisions to instruct the formation of automata states. Further, we propose a state composition method to enhance the context-awareness of the extracted model. Our in-depth evaluations on typical RNN tasks, including language model and classification, demonstrate the effectiveness and advantage of our method over the state-of-the-arts. The evaluation results show that our method can achieve accurate approximation of an RNN even on large-scale tasks.

PDF Details