Author name cluster

Libo Zhang

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.

18 papers

1 author row

EAAI Journal 2026 Journal Article

A new reconstruction-based method for multivariate time series anomaly detection with diffusion models

Hegui Zhu
Xiao Liu
Yinghao Zhang
Libo Zhang

Time series anomaly detection plays an important role in various fields, such as abnormal driving behaviors in autonomous driving, predictive maintenance in manufacturing, and network security for Cyber–Physical Systems, etc. Most anomaly detectors are reconstruction-based methods utilizing Autoencoders to reconstruct time series. However, these methods are relatively difficult to obtain a high-quality reconstructed sequence applicable for anomaly detection between poor and excessive reconstruction. To address this issue, we propose a novel Reconstruction-based Anomaly Detection method with Diffusion Models (ReADD). More concretely, it employs the inherent characteristics of diffusion models by adding noise to the original data and then crafts a denoising network considering feature information instead of the comprehensive assessment of feature and temporal dependencies to obtain the reconstructed sequence. ReADD redefines the reconstruction process through diffusion models, whose goal is not to directly optimize the similarity between input and output, but to enhance the distinction between normal points and anomalies by disrupting the anomalies. Numerous experiments on four real-world datasets, Mars Science Laboratory rover (MSL), Soil Moisture Active Passive (SMAP), Pooled Server Metrics (PSM), and Secure Water Treatment (SWaT) demonstrate that our proposed ReADD obtains superior performance compared to other reconstruction-based anomaly detection approaches. In particular, ReADD achieves an average improvement of 7. 01% in Precision ( P ), 6. 23% in Recall ( R ), and 6. 87% in F1-Score ( F 1 ), respectively.

Details DOI

AAMAS Conference 2026 Conference Paper

Situational-Constrained Multi-Agent Coordination through Correlated Equilibria

Libo Zhang
Zhirui Zeng
Yang Chen
Jiamou Liu

Correlated Equilibria (CE) provide a robust framework for balancing individual and collective incentives in multi-agent coordination. However, real-world applications often impose situational constraints, i. e. , context-dependent requirements triggered only under specific conditions (e. g. , emergency protocols), which challenge existing methods. To address this, we propose Situational-Constrained Density-Based Correlated Equilibria (SC-DBCE) within a Markov game framework. We develop Situational-Constrained Correlated Policy Iteration (SC-CPI), the first RL algorithm capable of solving these equilibria using a smooth Log-Sum-Exp optimization mechanism. Experiments across multiple scenarios demonstrate that SC-CPI consistently outperforms baselines in both equilibrium quality and constraint adherence.

PDF

NeurIPS Conference 2025 Conference Paper

Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning

Haolin Pan
Hongyu Lin
Haoran Luo
Yang Liu
Kaichun Yao
Libo Zhang
Mingjie Xing
Yanjun Wu

Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large Language Models (LLMs) have shown promise in automating compiler tuning, two significant challenges still remain: the absence of high-quality reasoning datasets for agents training, and limited effective interactions with the compilation environment. In this work, we introduce Compiler-R1, the first reinforcement learning (RL)-driven framework specifically augmenting LLM capabilities for compiler auto-tuning. Compiler-R1 features a curated, high-quality reasoning dataset and a novel two-stage end-to-end RL training pipeline, enabling efficient environment exploration and learning through an outcome-based reward. Extensive experiments across seven datasets demonstrate Compiler-R1 achieving an average 8. 46\% IR instruction count reduction compared to opt -Oz, showcasing the strong potential of RL-trained LLMs for compiler optimization. Our code and datasets are publicly available at https: //github. com/Panhaolin2001/Compiler-R1.

PDF Details

NeurIPS Conference 2025 Conference Paper

Robust Ego-Exo Correspondence with Long-Term Memory

Yijun Hu
Bing Fan
Xin Gu
海青任
Dongfang Liu
Heng Fan
Libo Zhang

Establishing object-level correspondence between egocentric and exocentric views is essential for intelligent assistants to deliver precise and intuitive visual guidance. However, this task faces numerous challenges, including extreme viewpoint variations, occlusions, and the presence of small objects. Existing approaches usually borrow solutions from video object segmentation models, but still suffer from the aforementioned challenges. Recently, the Segment Anything Model 2 (SAM 2) has shown strong generalization capabilities and excellent performance in video object segmentation. Yet, when simply applied to the ego-exo correspondence (EEC) task, SAM 2 encounters severe difficulties due to ineffective ego-exo feature fusion and limited long-term memory capacity, especially for long videos. Addressing these problems, we propose a novel EEC framework based on SAM 2 with long-term memories by presenting a dual-memory architecture and an adaptive feature routing module inspired by Mixture-of-Experts (MoE). Compared to SAM 2, our approach features (i) a Memory-View MoE module which consists of a dual-branch routing mechanism to adaptively assign contribution weights to each expert feature along both channel and spatial dimensions, and (ii) a dual-memory bank system with a simple yet effective compression strategy to retain critical long-term information while eliminating redundancy. In the extensive experiments on the challenging EgoExo4D benchmark, our method, dubbed LM-EEC, achieves new state-of-the-art results and significantly outperforms existing methods and the SAM 2 baseline, showcasing its strong generalization across diverse scenarios. Our code and model are available at https: //github. com/juneyeeHu/LM-EEC.

PDF Details

IJCAI Conference 2025 Conference Paper

Situational-Constrained Sequential Resources Allocation via Reinforcement Learning

Libo Zhang
Yang Chen
Toru Takisaka
Kaiqi Zhao
Weidong Li
Jiamou Liu

Sequential Resource Allocation with situational constraints presents a significant challenge in real-world applications, where resource demands and priorities are context-dependent. This paper introduces a novel framework, SCRL, to address this problem. We formalize situational constraints as logic implications and develop a new algorithm that dynamically penalizes constraint violations. To handle situational constraints effectively, we propose a probabilistic selection mechanism to overcome limitations of traditional constraint reinforcement learning (CRL) approaches. We evaluate SCRL across two scenarios: medical resource allocation during a pandemic and pesticide distribution in agriculture. Experiments demonstrate that SCRL outperforms existing baselines in satisfying constraints while maintaining high resource efficiency, showcasing its potential for real-world, context-sensitive decision-making tasks.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm

Yang Chen
Menglin Zou
Jiaqi Zhang
Yitan Zhang
Junyi Yang
Gaël Gendron
Libo Zhang
Jiamou Liu

Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, which often lead to {\em unstable} training. Recent non-adversarial IRL approaches improve stability by jointly learning reward and policy via energy-based formulations but lack formal guarantees. This work bridges this gap. We first present a unified view showing canonical non-adversarial methods explicitly or implicitly maximize the likelihood of expert behavior, which is equivalent to minimizing the expected return gap. This insight leads to our main contribution: Trust Region Reward Optimization (TRRO), a framework that guarantees monotonic improvement in this likelihood via a Minorization-Maximization process. We instantiate TRRO into Proximal Inverse Reward Optimization (PIRO), a practical and stable IRL algorithm. Theoretically, TRRO provides the IRL counterpart to the stability guarantees of Trust Region Policy Optimization (TRPO) in forward RL. Empirically, PIRO matches or surpasses state-of-the-art baselines in reward recovery, policy imitation with high sample efficiency on MuJoCo and Gym-Robotics benchmarks and a real-world animal behavior modeling task.

PDF Details

AAAI Conference 2024 Conference Paper

Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables

Yang Chen
Xiao Lin
Bo Yan
Libo Zhang
Jiamou Liu
Neset Özkan Tan
Michael Witbrock

Designing suitable reward functions for numerous interacting intelligent agents is challenging in real-world applications. Inverse reinforcement learning (IRL) in mean field games (MFGs) offers a practical framework to infer reward functions from expert demonstrations. While promising, the assumption of agent homogeneity limits the capability of existing methods to handle demonstrations with heterogeneous and unknown objectives, which are common in practice. To this end, we propose a deep latent variable MFG model and an associated IRL method. Critically, our method can infer rewards from different yet structurally similar tasks without prior knowledge about underlying contexts or modifying the MFG model itself. Our experiments, conducted on simulated scenarios and a real-world spatial taxi-ride pricing problem, demonstrate the superiority of our approach over state-of-the-art IRL methods in MFGs.

PDF Details DOI

YNIMG Journal 2024 Journal Article

Neural mechanisms underlying placebo and nocebo effects in tonic muscle pain

Min Chen
Xiao Wu
Libo Zhang
Fengrui Zhang
Linling Li
Yingying Zhang
Donglin Xiong
Yunhai Qiu

Pain is a highly subjective and multidimensional experience, significantly influenced by various psychological factors. Placebo analgesia and nocebo hyperalgesia exemplify this influence, where inert treatments result in pain relief or exacerbation, respectively. While extensive research has elucidated the psychological and neural mechanisms behind these effects, most studies have focused on transient pain stimuli. To explore these mechanisms in the context of tonic pain, we conducted a study using a 15-minute tonic muscle pain induction procedure, where hypertonic saline was infused into the left masseter of healthy participants. We collected real-time Visual Analogue Scale (VAS) scores and functional magnetic resonance imaging (fMRI) data during the induction of placebo analgesia and nocebo hyperalgesia via conditioned learning. Our findings revealed that placebo analgesia was more pronounced and lasted longer than nocebo hyperalgesia. Real-time pain ratings correlated significantly with neural activity in several brain regions. Notably, the putamen was implicated in both effects, while the caudate and other regions were differentially involved in placebo and nocebo effects. These findings confirm that the tonic muscle pain paradigm can be used to investigate the mechanisms of placebo and nocebo effects and indicate that placebo analgesia and nocebo hyperalgesia may have more distinct than common neural bases.

Details DOI

NeurIPS Conference 2024 Conference Paper

In this paper, we propose a novel benchmark, named VastTrack, aiming to facilitate the development of general visual tracking via encompassing abundant classes and videos. VastTrack consists of a few attractive properties: (1) Vast Object Category. In particular, it covers targets from 2, 115 categories, significantly surpassing object classes of existing popular benchmarks (e. g. , GOT-10k with 563 classes and LaSOT with 70 categories). Through providing such vast object classes, we expect to learn more general object tracking. (2) Larger scale. Compared with current benchmarks, VastTrack provides 50, 610 videos with 4. 2 million frames, which makes it to date the largest dataset in term of the number of videos, and hence could benefit training even more powerful visual trackers in the deep learning era. (3) Rich Annotation. Besides conventional bounding box annotations, VastTrack also provides linguistic descriptions with more than 50K sentences for the videos. Such rich annotations of VastTrack enable the development of both vision-only and vision-language tracking. In order to ensure precise annotation, each frame in the videos is manually labeled with multi-stage of careful inspections and refinements. To understand performance of existing trackers and to provide baselines for future comparison, we extensively evaluate 25 representative trackers. The results, not surprisingly, display significant drops compared to those on current datasets due to lack of abundant categories and videos from diverse scenarios for training, and more efforts are urgently required to improve general visual tracking. Our VastTrack, the toolkit, and evaluation results are publicly available at https: //github. com/HengLan/VastTrack.

PDF Details DOI

AAMAS Conference 2023 Conference Paper

Adversarial Inverse Reinforcement Learning for Mean Field Games

Yang Chen
Libo Zhang
Jiamou Liu
Michael Witbrock

Goal-based agents respond to environments and adjust behaviour accordingly to reach objectives. Understanding incentives of interacting agents from observed behaviour is a core problem in multi-agent systems. Inverse reinforcement learning (IRL) solves this problem, which infers underlying reward functions by observing the behaviour of rational agents. Despite IRL being principled, it becomes intractable when the number of agents grows because of the curse of dimensionality and the explosion of agent interactions. The formalism of Mean field games (MFGs) has gained momentum as a mathematically tractable paradigm for studying large-scale multi-agent systems. By grounding IRL in MFGs, recent research attempts to push the limits of the agent number in IRL. However, the study of IRL for MFGs is far from being mature as existing methods assume strong rationality, while real-world agents often exhibit bounded rationality due to the limited cognitive or computational capacity. Towards a more general and practical IRL framework for MFGs, this paper proposes Mean-Field Adversarial IRL, a novel framework capable of tolerating bounded rationality. We build it upon the maximum entropy principle, adversarial learning, and a new equilibrium concept for MFGs. We evaluate our machinery on simulated tasks with imperfect demonstrations resulting from bounded rationality. Experimental results demonstrate the superiority of MF-AIRL over existing methods in reward recovery.

PDF

EAAI Journal 2023 Journal Article

CSCMOT: Multi-object tracking based on channel spatial cooperative attention mechanism

Fei Wang
Hao Yan
Libo Zhang
Ke Gao

Multi-object tracking has made good progress in recent years. Most mainstream methods use the fusion method of detection and Re-ID to complete the multi-target tracking technology. However, the current multi-tracking algorithm is slow and cannot meet the real-time requirements, which makes it difficult to implement in actual scenarios. In addition, the current mainstream multi-target tracking technology often has the problem of identity information jumping. Such frequent identity information hopping can lead to serious problems in some demanding practical applications, resulting in poor tracking performance. To solve these problems, we propose a simple framework CSCMOT. A non-parametric attention mechanism is adopted to focus on some feature points of the target without increasing the amount of computation, so as to reduce the amount of computation and improve the real-time performance of the algorithm. In addition, the jumping problem of identity information can be reduced by random simulation occlusion to improve tracking performance. Experiments show that the real-time performance of the proposed CSCMOT framework reaches 32. 5 FPS, which exceeds most of the mainstream methods. In addition, the ID-switch was reduced to 2493 on the MOT17 dataset. Made a great breakthrough, better to solve the problem of identity information jump. The tracking accuracy is also 71. 5, a competitive result that exceeds most of the mainstream methods. Effective data show that the framework improves the real-time performance of the algorithm, solves the problem of identity jump between targets, and is more conducive to experiment landing, which is easy to combine with the mobile robot platform.

Details DOI

AAMAS Conference 2023 Conference Paper

Learning Density-Based Correlated Equilibria for Markov Games

Libo Zhang
Yang Chen
Toru Takisaka
Bakh Khoussainov
Michael Witbrock
Jiamou Liu

Correlated Equilibrium (CE) is a well-established solution concept that captures coordination among agents and enjoys good algorithmic properties. In real-world multi-agent systems, in addition to being in equilibrium, agents’ policies are often expected to meet requirements with respect to safety, and fairness. Such additional requirements can often be expressed in terms of the state density which measures the state-visitation frequencies during the course of a game. However, existing CE notions or CE-finding approaches cannot explicitly specify a CE with particular properties concerning state density; they do so implicitly by either modifying reward functions or using value functions as the selection criteria. The resulting CE may thus not fully fulfil the state-density requirements. In this paper, we propose Density-Based Correlated Equilibria (DBCE), a new notion of CE that explicitly takes state density as a selection criterion. Concretely, we instantiate DBCE by specifying different state-density requirements motivated by real-world applications. To compute DBCE, we put forward the Density Based Correlated Policy Iteration algorithm for the underlying control problem. We perform experiments on various games where results demonstrate the advantage of our CE-finding approach over existing methods in scenarios with state-density concerns.

PDF

AAMAS Conference 2022 Conference Paper

Individual-Level Inverse Reinforcement Learning for Mean Field Games

Yang Chen
Libo Zhang
Jiamou Liu
Shuyue Hu

The recent mean field game (MFG) formalism has enabled the application of inverse reinforcement learning (IRL) methods in largescale multi-agent systems, with the goal of inferring reward signals that can explain demonstrated behaviours of large populations. The existing IRL methods for MFGs are built upon reducing an MFG to a Markov decision process (MDP) defined on the collective behaviours and average rewards of the population. However, this paper reveals that the reduction from MFG to MDP holds only for the fully cooperative setting. This limitation invalidates existing IRL methods on MFGs with non-cooperative environments. To measure more general behaviours in large populations, we study the use of individual behaviours to infer ground-truth reward functions for MFGs. We propose Mean Field IRL (MFIRL), the first dedicated IRL framework for MFGs that can handle both cooperative and non-cooperative environments. Based on this theoretically justified framework, we develop a practical algorithm effective for MFGs with unknown dynamics. We evaluate MFIRL on both cooperative and mixed cooperative-competitive scenarios with many agents. Results demonstrate that MFIRL excels in reward recovery, sample efficiency and robustness in the face of changing dynamics.

PDF

YNIMG Journal 2021 Journal Article

A novel method to simultaneously record spinal cord electrophysiology and electroencephalography signals

Feixue Wang
Libo Zhang
Lupeng Yue
Yuxuan Zeng
Qing Zhao
Qingjuan Gong
Jianbo Zhang
Dongyang Liu

The brain and the spinal cord together make up the central nervous system (CNS). The functions of the human brain have been the focus of neuroscience research for a long time. However, the spinal cord is largely ignored, and the functional interaction of these two parts of the CNS is only partly understood. This study developed a novel method to simultaneously record spinal cord electrophysiology (SCE) and electroencephalography (EEG) signals and validated its performance using a classical resting-state study design with two experimental conditions: eyes-closed (EC) and eyes-open (EO). We recruited nine postherpetic neuralgia patients implanted with a spinal cord stimulator, which was modified to record SCE signals simultaneously with EEG signals. For both EEG and SCE, similar differences were found in delta- and alpha-band oscillations between the EC and EO conditions, and the spectral power of these frequency bands was able to predict EC/EO behaviors. Moreover, causal connectivity analysis suggested a top-down regulation in delta-band oscillations from the brain to the spinal cord. Altogether, this study demonstrates the validity of simultaneous SCE-EEG recording and shows that the novel method is a valuable tool to investigate the brain-spinal interaction. With this method, we can better unite knowledge about the brain and the spinal cord for a deeper understanding of the functions of the whole CNS.

Details DOI

AIIM Journal 2021 Journal Article

Convolutional squeeze-and-excitation network for ECG arrhythmia detection

Rongjun Ge
Tengfei Shen
Ying Zhou
Chengyu Liu
Libo Zhang
Benqiang Yang
Ying Yan
Jean-Louis Coatrieux

Automatic detection of arrhythmia through an electrocardiogram (ECG) is of great significance for the prevention and treatment of cardiovascular diseases. In Convolutional neural network, the ECG signal is converted into multiple feature channels with equal weights through the convolution operation. Multiple feature channels can provide richer and more comprehensive information, but also contain redundant information, which will affect the diagnosis of arrhythmia, so feature channels that contain arrhythmia information should be paid attention to and given larger weight. In this paper, we introduced the Squeeze-and-Excitation (SE) block for the first time for the automatic detection of multiple types of arrhythmias with ECG. Our algorithm combines the residual convolutional module and the SE block to extract features from the original ECG signal. The SE block adaptively enhances the discriminative features and suppresses noise by explicitly modeling the interdependence between the channels, which can adaptively integrate information from different feature channels of ECG. The one-dimensional convolution operation over the time dimension is used to extract temporal information and the shortcut connection of the Se-Residual convolutional module in the proposed model makes the network easier to optimize. Thanks to the powerful feature extraction capabilities of the network, which can effectively extract discriminative arrhythmia features in multiple feature channels, so that no extra data preprocessing including denoising in other methods are need for our framework. It thus improves the working efficiency and keeps the collected biological information without loss. Experiments conducted with the 12-lead ECG dataset of the China Physiological Signal Challenge (CPSC) 2018 and the dataset of PhysioNet/Computing in Cardiology (CinC) Challenge 2017. The experiment results show that our model gains great performance and has great potential in clinical.

Details DOI

AAAI Conference 2021 Conference Paper

Rethinking Object Detection in Retail Stores

Yuanqiang Cai
Longyin Wen
Libo Zhang
Dawei Du
Weiqiang Wang

The conventional standard for object detection uses a bounding box to represent each individual object instance. However, it is not practical in the industry-relevant applications in the context of warehouses due to severe occlusions among groups of instances of the same categories. In this paper, we propose a new task, i. e. , simultaneously object localization and counting, abbreviated as Locount, which requires algorithms to localize groups of objects of interest with the number of instances. However, there does not exist a dataset or benchmark designed for such a task. To this end, we collect a large-scale object localization and counting dataset with rich annotations in retail stores, which consists of 50, 394 images with more than 1. 9 million object instances in 140 categories. Together with this dataset, we provide a new evaluation protocol and divide the training and testing subsets to fairly evaluate the performance of algorithms for Locount, developing a new benchmark for the Locount task. Moreover, we present a cascaded localization and counting network as a strong baseline, which gradually classifies and regresses the bounding boxes of objects with the predicted numbers of instances enclosed in the bounding boxes, trained in an end-toend manner. Extensive experiments are conducted on the proposed dataset to demonstrate its significance and the analysis is provided to indicate future directions. Dataset is available at https: //isrc. iscas. ac. cn/gitlab/research/locount-dataset.

PDF Details

AAAI Conference 2019 Conference Paper

Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently

Dan Liu
Dawei Du
Libo Zhang
Tiejian Luo
Yanjun Wu
Feiyue Huang
Siwei Lyu

Existing hand detection methods usually follow the pipeline of multiple stages with high computation cost, i. e. , feature extraction, region proposal, bounding box regression, and additional layers for rotated region detection. In this paper, we propose a new Scale Invariant Fully Convolutional Network (SIFCN) trained in an end-to-end fashion to detect hands efficiently. Specifically, we merge the feature maps from high to low layers in an iterative way, which handles different scales of hands better with less time overhead comparing to concatenating them simply. Moreover, we develop the Complementary Weighted Fusion (CWF) block to make full use of the distinctive features among multiple layers to achieve scale invariance. To deal with rotated hand detection, we present the rotation map to get rid of complex rotation and derotation layers. Besides, we design the multi-scale loss scheme to accelerate the training process significantly by adding supervision to the intermediate layers of the network. Compared with the state-of-the-art methods, our algorithm shows comparable accuracy and runs a 4. 23 times faster speed on the VIVA dataset and achieves better average precision on Oxford hand detection dataset at a speed of 62. 5 fps.

PDF Details

IJCAI Conference 2018 Conference Paper

Teaching Machines to Ask Questions

Kaichun Yao
Libo Zhang
Tiejian Luo
Lili Tao
Yanjun Wu

We propose a novel neural network model that aims to generate diverse and human-like natural language questions. Our model not only directly captures the variability in possible questions by using a latent variable, but also generates certain types of questions by introducing an additional observed variable. We deploy our model in the generative adversarial network (GAN) framework and modify the discriminator which not only allows evaluating the question authenticity, but predicts the question type. Our model is trained and evaluated on a question-answering dataset SQuAD, and the experimental results shown the proposed model is able to generate diverse and readable questions with the specific attribute.

PDF Details