Xinliang Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinliang Zhou has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Ziyu Jia
Institute of Automation, Chinese Academy of Science, Beijing, China
9 shared publications - Yi Ding
College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore
7 shared publications - Chenyu Liu
College of Computing and Data Science Nanyang Technological University Singapore
6 shared publications - Chenyu Liu
Nanyang technological university, Singapore, Singapore
5 shared publications - Yang Liu
Department of Obstetrics and Gynecology, The Second Affiliated Hospital of Kunming Medical University, China
5 shared publications - Jiaping Xiao
School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2423-2432
Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2423-2432
Open AccessFoundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding
- Open Access
- 20 July 2026
- Published by Elsevier in SSRN Electronic Journal
Adapting Single-modal EEG Foundation Models to Multimodal Affective Computing via Spectral Cross-modal Prompting
Despite the remarkable success of foundation models in single-modal EEG analysis, their extension to multimodal affective tasks remains constrained by pervasive modality gaps and the prohibitive computational overhead of conventional fine-tuning. This paper presents Frequency-domain Informed Prompt Tuning (FIPT), a parameter-efficient framework designed to adapt pre-trained EEG backbones (e.g., LaBraM, CBraMod) to multimodal emotion recognition. By freezing the backbone's core weights, we introduce a Spectral-Rhythmic Alignment Module (SRAM) that synchronizes heterogeneous physiological signals in a unified frequency space, effectively mitigating cross-modal discrepancies. To further bridge the representation gap, we employ a Knowledge-Augmented Hybrid Prompting strategy, which injects Power Spectral Density (PSD) priors to anchor the model’s attention on biologically significant oscillatory features.Extensive evaluations on four diverse public datasets demonstrate that FIPT consistently achieves state-of-the-art performance. Our sensitivity analysis reveals that the framework effectively leverages spectral priors for guided adaptation, providing a robust, interpretable, and scalable paradigm for multimodal affective computing.
- 20 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAdapting Single-modal EEG Foundation Models to Multimodal Affective Computing via Spectral Cross-modal Prompting
Despite the remarkable success of foundation models in single-modal EEG analysis, their extension to multimodal affective tasks remains constrained by pervasive modality gaps and the prohibitive computational overhead of conventional fine-tuning. This paper presents Frequency-domain Informed Prompt Tuning (FIPT), a parameter-efficient framework designed to adapt pre-trained EEG backbones (e.g., LaBraM, CBraMod) to multimodal emotion recognition. By freezing the backbone's core weights, we introduce a Spectral-Rhythmic Alignment Module (SRAM) that synchronizes heterogeneous physiological signals in a unified frequency space, effectively mitigating cross-modal discrepancies. To further bridge the representation gap, we employ a Knowledge-Augmented Hybrid Prompting strategy, which injects Power Spectral Density (PSD) priors to anchor the model’s attention on biologically significant oscillatory features.Extensive evaluations on four diverse public datasets demonstrate that FIPT consistently achieves state-of-the-art performance. Our sensitivity analysis reveals that the framework effectively leverages spectral priors for guided adaptation, providing a robust, interpretable, and scalable paradigm for multimodal affective computing.
- 20 May 2026
- Published by Elsevier in Information Fusion
- Vol. 135
Wavelet-informed pretraining and scenario-conditioned fusion for driving takeover performance prediction
- 20 May 2026
- Published by Elsevier in Information Fusion
- Vol. 135
Wavelet-informed pretraining and scenario-conditioned fusion for driving takeover performance prediction
- Open Access
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1203
Statistical Reward Shaping for Reinforcement Learning in Bipedal Locomotion
Achieving stable bipedal locomotion for humanoid robots remains a central challenge in reinforcement learning (RL), in which the design of reward functions is pivotal but non-trivial. This paper proposes a three-tier statistical reward shaping framework to optimize bipedal gait learning. First, training outcomes are diagnostically monitored using forward distance, fall rate, and posture score. Pearson correlation and regression analyses are then employed to identify trade-offs and isolate the direct effects of reward components. Finally, targeted parameter sweeps enable directionally guided optimization, substantially reducing heuristic parameter tuning while refining a reward function for the H1 robot in Isaac Lab. Experimental results demonstrate clear improvements over the baseline. The optimized policy reduces convergence time by 14% and increases forward distance by 186%. Stability is markedly enhanced, with fall rate decreasing from 75% to 2% and active locomotion efficiency nearly doubling (0.339 to 0.678). These results validate a reproducible, data-driven framework for reward design, highlighting the importance of principled statistical analysis in complex RL-based humanoid locomotion.
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1203
Open AccessStatistical Reward Shaping for Reinforcement Learning in Bipedal Locomotion
Achieving stable bipedal locomotion for humanoid robots remains a central challenge in reinforcement learning (RL), in which the design of reward functions is pivotal but non-trivial. This paper proposes a three-tier statistical reward shaping framework to optimize bipedal gait learning. First, training outcomes are diagnostically monitored using forward distance, fall rate, and posture score. Pearson correlation and regression analyses are then employed to identify trade-offs and isolate the direct effects of reward components. Finally, targeted parameter sweeps enable directionally guided optimization, substantially reducing heuristic parameter tuning while refining a reward function for the H1 robot in Isaac Lab. Experimental results demonstrate clear improvements over the baseline. The optimized policy reduces convergence time by 14% and increases forward distance by 186%. Stability is markedly enhanced, with fall rate decreasing from 75% to 2% and active locomotion efficiency nearly doubling (0.339 to 0.678). These results validate a reproducible, data-driven framework for reward design, highlighting the importance of principled statistical analysis in complex RL-based humanoid locomotion.
- 19 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Magazine
- Vol. 42 (5) , 22-35
Brain Foundation Models: A survey on advancements in neural signal processing and brain discovery
Brain foundation models (BFMs) represent a transformative paradigm in computational neuroscience that leverages large-scale pretraining on diverse neural signals to achieve robust generalization across tasks, modalities, and experimental contexts. This survey article establishes the first comprehensive definition and framework for BFMs, systematically examining their construction, core methodologies, and applications. We present key approaches for data processing and training strategies alongside diverse applications spanning brain decoding and scientific discovery. Through critical analysis of recent methodological innovations, we identify fundamental challenges that must be addressed to realize the full potential of BFMs, including advancing data quality and standardization, optimizing model architectures, improving training efficiency, and enhancing interpretability. By bridging the gap between neuroscience and artificial intelligence (AI), BFMs present unprecedented opportunities to revolutionize brain research, clinical diagnostics, and therapeutic interventions. This article serves as a foundational reference for researchers and practitioners seeking to understand and advance this emerging field.
- 19 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Magazine
- Vol. 42 (5) , 22-35
Brain Foundation Models: A survey on advancements in neural signal processing and brain discovery
Brain foundation models (BFMs) represent a transformative paradigm in computational neuroscience that leverages large-scale pretraining on diverse neural signals to achieve robust generalization across tasks, modalities, and experimental contexts. This survey article establishes the first comprehensive definition and framework for BFMs, systematically examining their construction, core methodologies, and applications. We present key approaches for data processing and training strategies alongside diverse applications spanning brain decoding and scientific discovery. Through critical analysis of recent methodological innovations, we identify fundamental challenges that must be addressed to realize the full potential of BFMs, including advancing data quality and standardization, optimizing model architectures, improving training efficiency, and enhancing interpretability. By bridging the gap between neuroscience and artificial intelligence (AI), BFMs present unprecedented opportunities to revolutionize brain research, clinical diagnostics, and therapeutic interventions. This article serves as a foundational reference for researchers and practitioners seeking to understand and advance this emerging field.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5509-5518
Sera: Separated Coarse-to-fine Representation Alignment for Cross-subject EEG-based Emotion Recognition
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5509-5518
Open AccessSera: Separated Coarse-to-fine Representation Alignment for Cross-subject EEG-based Emotion Recognition
- Open Access
Introducing Multimodal Paradigm for Learning Sleep Staging PSG via General-Purpose Model
Sleep staging is essential for diagnosing sleep disorders and assessing neurological health. Existing automatic methods typically extract features from complex polysomnography (PSG) signals and train domain-specific models, which often lack intuitiveness and require large, specialized datasets. To overcome these limitations, we introduce a new paradigm for sleep staging that leverages large multimodal general-purpose models to emulate clinical diagnostic practices. Specifically, we convert raw one-dimensional PSG time-series into intuitive two-dimensional waveform images and then fine-tune a multimodal large model to learn from these representations. Experiments on three public datasets (ISRUC, MASS, SHHS) demonstrate that our approach enables general-purpose models, without prior exposure to sleep data, to acquire robust staging capabilities. Moreover, explanation analysis reveals our model learned to mimic the visual diagnostic workflow of human experts for sleep staging by PSG images. The proposed method consistently outperforms state-of-the-art baselines in accuracy and robustness, highlighting its efficiency and practical value for medical applications. The code for the signal-to-image pipeline and the PSG image dataset will be released.
Open AccessIntroducing Multimodal Paradigm for Learning Sleep Staging PSG via General-Purpose Model
Sleep staging is essential for diagnosing sleep disorders and assessing neurological health. Existing automatic methods typically extract features from complex polysomnography (PSG) signals and train domain-specific models, which often lack intuitiveness and require large, specialized datasets. To overcome these limitations, we introduce a new paradigm for sleep staging that leverages large multimodal general-purpose models to emulate clinical diagnostic practices. Specifically, we convert raw one-dimensional PSG time-series into intuitive two-dimensional waveform images and then fine-tune a multimodal large model to learn from these representations. Experiments on three public datasets (ISRUC, MASS, SHHS) demonstrate that our approach enables general-purpose models, without prior exposure to sleep data, to acquire robust staging capabilities. Moreover, explanation analysis reveals our model learned to mimic the visual diagnostic workflow of human experts for sleep staging by PSG images. The proposed method consistently outperforms state-of-the-art baselines in accuracy and robustness, highlighting its efficiency and practical value for medical applications. The code for the signal-to-image pipeline and the PSG image dataset will be released.
- Open Access
ECHO: Toward Contextual Seq2Seq Paradigms in Large EEG Models
Electroencephalography (EEG), with its broad range of applications, necessitates models that can generalize effectively across various tasks and datasets. Large EEG Models (LEMs) address this by pretraining encoder-centric architectures on large-scale unlabeled data to extract universal representations. While effective, these models lack decoders of comparable capacity, limiting the full utilization of the learned features. To address this issue, we introduce ECHO, a novel decoder-centric LEM paradigm that reformulates EEG modeling as sequence-to-sequence learning. ECHO captures layered relationships among signals, labels, and tasks within sequence space, while incorporating discrete support samples to construct contextual cues. This design equips ECHO with in-context learning, enabling dynamic adaptation to heterogeneous tasks without parameter updates. Extensive experiments across multiple datasets demonstrate that, even with basic model components, ECHO consistently outperforms state-of-the-art single-task LEMs in multi-task settings, showing superior generalization and adaptability.
Open AccessECHO: Toward Contextual Seq2Seq Paradigms in Large EEG Models
Electroencephalography (EEG), with its broad range of applications, necessitates models that can generalize effectively across various tasks and datasets. Large EEG Models (LEMs) address this by pretraining encoder-centric architectures on large-scale unlabeled data to extract universal representations. While effective, these models lack decoders of comparable capacity, limiting the full utilization of the learned features. To address this issue, we introduce ECHO, a novel decoder-centric LEM paradigm that reformulates EEG modeling as sequence-to-sequence learning. ECHO captures layered relationships among signals, labels, and tasks within sequence space, while incorporating discrete support samples to construct contextual cues. This design equips ECHO with in-context learning, enabling dynamic adaptation to heterogeneous tasks without parameter updates. Extensive experiments across multiple datasets demonstrate that, even with basic model components, ECHO consistently outperforms state-of-the-art single-task LEMs in multi-task settings, showing superior generalization and adaptability.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 33 (12) , 4331-4344
Fuzzy Information Evolution With Three-Way Decision in Social Network Group Decision-Making
In group decision-making (GDM) scenarios, uncertainty, dynamic social structures, and vague information present challenges for traditional opinion dynamics models. To address these issues, this study proposes a novel social network group decision-making (SNGDM) framework that integrates three-way decision (3WD) theory, dynamic network reconstruction, and linguistic opinion representation. First, the 3WD mechanism is introduced to explicitly model hesitation and ambiguity in agent judgments, thereby preventing irrational decisions. Second, a connection adjustment rule based on opinion similarity is developed, enabling agents to adaptively update their communication links and better reflect the evolving nature of social relationships. Third, linguistic terms are used to describe agent opinions, allowing the model to handle vague and incomplete information more effectively. Finally, an integrated multi-agent decision-making framework is constructed, which simultaneously considers individual uncertainty, opinion evolution, and network dynamics. The proposed model is applied to a multi-UAV cooperative decision-making scenario, where simulation results and consensus analysis demonstrate its effectiveness. Experimental comparisons further verify the algorithm's advantages in enhancing system stability and representing realistic decision-making behaviors.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 33 (12) , 4331-4344
Fuzzy Information Evolution With Three-Way Decision in Social Network Group Decision-Making
In group decision-making (GDM) scenarios, uncertainty, dynamic social structures, and vague information present challenges for traditional opinion dynamics models. To address these issues, this study proposes a novel social network group decision-making (SNGDM) framework that integrates three-way decision (3WD) theory, dynamic network reconstruction, and linguistic opinion representation. First, the 3WD mechanism is introduced to explicitly model hesitation and ambiguity in agent judgments, thereby preventing irrational decisions. Second, a connection adjustment rule based on opinion similarity is developed, enabling agents to adaptively update their communication links and better reflect the evolving nature of social relationships. Third, linguistic terms are used to describe agent opinions, allowing the model to handle vague and incomplete information more effectively. Finally, an integrated multi-agent decision-making framework is constructed, which simultaneously considers individual uncertainty, opinion evolution, and network dynamics. The proposed model is applied to a multi-UAV cooperative decision-making scenario, where simulation results and consensus analysis demonstrate its effectiveness. Experimental comparisons further verify the algorithm's advantages in enhancing system stability and representing realistic decision-making behaviors.