Wei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wei Chen has a total of 259 co-authors. Here are the top co-authors by number of shared publications:
- Li Qiu
School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen), Shenzhen, China
23 shared publications - Dan Wang
School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden
9 shared publications - John Chi-Shing Lui
The Chinese University of Hong Kong (CUHK)
5 shared publications - Sei Zhen Khong
Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan
5 shared publications - Xiaoming Sun
Institute of Computing Technology
5 shared publications - Yajun Wang
Sunnyvale CA U.S.A
5 shared publications
Latest Publications
- Open Access
- 22 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 381-390
Continuous Semantic Caching for Low-Cost LLM Serving
- 22 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 381-390
Open AccessContinuous Semantic Caching for Low-Cost LLM Serving
- 12 November 2026
- Published by Elsevier in Journal of the Franklin Institute
A Phase Theory for Matrices and MIMO LTI Systems
- 12 November 2026
- Published by Elsevier in Journal of the Franklin Institute
A Phase Theory for Matrices and MIMO LTI Systems
- 27 February 2026
- Published by Elsevier in Artificial Intelligence
- Vol. 354
Exploring multi-layered networks through random walks: bridging offline optimization and online learning
- 27 February 2026
- Published by Elsevier in Artificial Intelligence
- Vol. 354
Exploring multi-layered networks through random walks: bridging offline optimization and online learning
- Open Access
Frequency Shaping Control for Oscillation Damping in Weakly-Connected Power Network: A Root Locus Method
Frequency control following a contingency event is of vital concern in power system operations. Leveraging inverter-based resources, it is not hard to shape the center of inertia (COI) frequency nicely. However, under weak grid conditions, it becomes insufficient to solely shape the COI frequency since this aggregate signal fails to reveal the inter-area oscillations. In this manuscript, we advocate for foolproof fine-tuning rules for \emph{frequency shaping control} (FS) based on a systematic analysis of damping ratio and decay rate of inter-area oscillations to simultaneously meet specified metrics for frequency security and oscillatory stability. To this end, building on a modal decomposition, we simplify the oscillation damping problem into a pole-placement task for a set of scalar subsystems, which can be efficiently solved by only investigating the root locus of a scalar subsystem associated with the main mode, while FS inherently guarantees a Nadir-less COI frequency response. Through our proposed root-locus-based oscillatory stability analysis, we derive closed-form expressions for the minimum damping ratio and decay rate among inter-area oscillations in terms of networked system and control parameters under FS. Moreover, we propose useful tuning guidelines for FS which need only simple calculations or visualized tuning to not only shape the COI frequency into a first-order response that converges to a steady-state value within the allowed range but also ensure a satisfactory damping ratio and decay rate of inter-area oscillations following disturbances. As for the common virtual inertia control (VI), although similar oscillatory stability analysis becomes intractable, one can still glean some insights via the root locus method. Numerical simulations validate the proposed tuning for FS as well as the superiority of FS over VI in exponential convergence rate.
Open AccessFrequency Shaping Control for Oscillation Damping in Weakly-Connected Power Network: A Root Locus Method
Frequency control following a contingency event is of vital concern in power system operations. Leveraging inverter-based resources, it is not hard to shape the center of inertia (COI) frequency nicely. However, under weak grid conditions, it becomes insufficient to solely shape the COI frequency since this aggregate signal fails to reveal the inter-area oscillations. In this manuscript, we advocate for foolproof fine-tuning rules for \emph{frequency shaping control} (FS) based on a systematic analysis of damping ratio and decay rate of inter-area oscillations to simultaneously meet specified metrics for frequency security and oscillatory stability. To this end, building on a modal decomposition, we simplify the oscillation damping problem into a pole-placement task for a set of scalar subsystems, which can be efficiently solved by only investigating the root locus of a scalar subsystem associated with the main mode, while FS inherently guarantees a Nadir-less COI frequency response. Through our proposed root-locus-based oscillatory stability analysis, we derive closed-form expressions for the minimum damping ratio and decay rate among inter-area oscillations in terms of networked system and control parameters under FS. Moreover, we propose useful tuning guidelines for FS which need only simple calculations or visualized tuning to not only shape the COI frequency into a first-order response that converges to a steady-state value within the allowed range but also ensure a satisfactory damping ratio and decay rate of inter-area oscillations following disturbances. As for the common virtual inertia control (VI), although similar oscillatory stability analysis becomes intractable, one can still glean some insights via the root locus method. Numerical simulations validate the proposed tuning for FS as well as the superiority of FS over VI in exponential convergence rate.
- 2 January 2026
- Published by Springer Nature
- p. 513-529
Convergence to Equilibrium of No-Regret Dynamics in Congestion Games
- 2 January 2026
- Published by Springer Nature
- p. 513-529
Convergence to Equilibrium of No-Regret Dynamics in Congestion Games
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (4) , 1-10
Exploiting Temporal Decay and Dual Network for Influence Maximization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (4) , 1-10
Exploiting Temporal Decay and Dual Network for Influence Maximization
- Open Access
Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms
The problem of combinatorial multi-armed bandits with probabilistically triggered arms (CMAB-T) has been extensively studied. Prior work primarily focuses on either the online setting where an agent learns about the unknown environment through iterative interactions, or the offline setting where a policy is learned solely from logged data. However, each of these paradigms has inherent limitations: online algorithms suffer from high interaction costs and slow adaptation, while offline methods are constrained by dataset quality and lack of exploration capabilities. To address these complementary weaknesses, we propose hybrid CMAB-T, a new framework that integrates offline data with online interaction in a principled manner. Our proposed hybrid CUCB algorithm leverages offline data to guide exploration and accelerate convergence, while strategically incorporating online interactions to mitigate the insufficient coverage or distributional bias of the offline dataset. We provide theoretical guarantees on the algorithm's regret, demonstrating that hybrid CUCB significantly outperforms purely online approaches when high-quality offline data is available, and effectively corrects the bias inherent in offline-only methods when the data is limited or misaligned. Empirical results further demonstrate the consistent advantage of our algorithm.
Open AccessHybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms
The problem of combinatorial multi-armed bandits with probabilistically triggered arms (CMAB-T) has been extensively studied. Prior work primarily focuses on either the online setting where an agent learns about the unknown environment through iterative interactions, or the offline setting where a policy is learned solely from logged data. However, each of these paradigms has inherent limitations: online algorithms suffer from high interaction costs and slow adaptation, while offline methods are constrained by dataset quality and lack of exploration capabilities. To address these complementary weaknesses, we propose hybrid CMAB-T, a new framework that integrates offline data with online interaction in a principled manner. Our proposed hybrid CUCB algorithm leverages offline data to guide exploration and accelerate convergence, while strategically incorporating online interactions to mitigate the insufficient coverage or distributional bias of the offline dataset. We provide theoretical guarantees on the algorithm's regret, demonstrating that hybrid CUCB significantly outperforms purely online approaches when high-quality offline data is available, and effectively corrects the bias inherent in offline-only methods when the data is limited or misaligned. Empirical results further demonstrate the consistent advantage of our algorithm.
- 8 December 2025
- Published by Elsevier in Systems & Control Letters
- Vol. 208
State feedback Φ ∞ synthesis of multivariable linear systems
- 8 December 2025
- Published by Elsevier in Systems & Control Letters
- Vol. 208
State feedback Φ ∞ synthesis of multivariable linear systems
- Open Access
Quadratic Truncated Random Return in Distributional LQR: Positive Definiteness, Density, and Log-Concavity
Distributional linear quadratic regulator (LQR) is a new framework that integrates the distributional reinforcement learning and classical LQR, which offers a new way to study the random return instead of the expected cost. Unlike iterative approximation using dynamic programming in the DRL, a closed-form expression for the random return can be exactly characterized in the distributional LQR, which is defined over infinitely many random variables. In recent work [1, 2], it has been shown that this random return can be well approximated by a finite number of random variables, which we call truncated random return. In this paper, we study the truncated random return in the distributional LQR. We show that the truncated random return can be naturally expressed in the quadratic form. We develop a sufficient condition for the positive definiteness of the block symmetric matrix in the quadratic form and provide the lower and upper bounds on the eigenvalues of this matrix. We further show that in this case, the truncated random return follows a positively weighted non-central chi-square distribution if the random disturbances admits Gaussian, and its cumulative distribution function is log-concave if the probability density function of the random disturbances is log-concave.
Open AccessQuadratic Truncated Random Return in Distributional LQR: Positive Definiteness, Density, and Log-Concavity
Distributional linear quadratic regulator (LQR) is a new framework that integrates the distributional reinforcement learning and classical LQR, which offers a new way to study the random return instead of the expected cost. Unlike iterative approximation using dynamic programming in the DRL, a closed-form expression for the random return can be exactly characterized in the distributional LQR, which is defined over infinitely many random variables. In recent work [1, 2], it has been shown that this random return can be well approximated by a finite number of random variables, which we call truncated random return. In this paper, we study the truncated random return in the distributional LQR. We show that the truncated random return can be naturally expressed in the quadratic form. We develop a sufficient condition for the positive definiteness of the block symmetric matrix in the quadratic form and provide the lower and upper bounds on the eigenvalues of this matrix. We further show that in this case, the truncated random return follows a positively weighted non-central chi-square distribution if the random disturbances admits Gaussian, and its cumulative distribution function is log-concave if the probability density function of the random disturbances is log-concave.
- Open Access
Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
Current autoregressive language models (ARMs) achieve high accuracy but require long token sequences, making them costly. Discrete diffusion language models (DDLMs) enable parallel and flexible generation within a fixed number of steps and have recently emerged for their strong performance in complex reasoning and long-term planning tasks. We present a study exploring hybrid architectures that couple DDLMs with ARMs to assess whether their collaboration can yield complementary benefits. We first examine collaboration in text space, where one model plans the reasoning process and another executes the final answer based on that plan. We then extend this setup to latent-space communication, introducing a learned projector that maps DDLM latents into the ARM's embedding space, potentially bypassing some of the text-generation limitations of diffusion models. We find that shifting DDLM --> ARM communication from text space to latent space yields significant accuracy gains, for example increasing from 27.0% to 54.0% on DART-5 and from 0.0% to 14.0% on AIME24. We also find that combining a DDLM planner with an ARM executor can provide substantial computational savings with little to no impact on accuracy. For example, the latent-space pipeline, using 64 tokens for planning and roughly 5 for execution, surpasses Qwen3.1-7B on DART-5 and AIME, despite Qwen using 44 times more tokens. Overall, our study offers new insights into reasoning with DDLMs and highlights their potential in hybrid architectures.
Open AccessPlanner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
Current autoregressive language models (ARMs) achieve high accuracy but require long token sequences, making them costly. Discrete diffusion language models (DDLMs) enable parallel and flexible generation within a fixed number of steps and have recently emerged for their strong performance in complex reasoning and long-term planning tasks. We present a study exploring hybrid architectures that couple DDLMs with ARMs to assess whether their collaboration can yield complementary benefits. We first examine collaboration in text space, where one model plans the reasoning process and another executes the final answer based on that plan. We then extend this setup to latent-space communication, introducing a learned projector that maps DDLM latents into the ARM's embedding space, potentially bypassing some of the text-generation limitations of diffusion models. We find that shifting DDLM --> ARM communication from text space to latent space yields significant accuracy gains, for example increasing from 27.0% to 54.0% on DART-5 and from 0.0% to 14.0% on AIME24. We also find that combining a DDLM planner with an ARM executor can provide substantial computational savings with little to no impact on accuracy. For example, the latent-space pipeline, using 64 tokens for planning and roughly 5 for execution, surpasses Qwen3.1-7B on DART-5 and AIME, despite Qwen using 44 times more tokens. Overall, our study offers new insights into reasoning with DDLMs and highlights their potential in hybrid architectures.