arXiv subjects

Wu Yue

Publications and source records attributed to Wu Yue.

5 recordsLinked to original sources

arXiv2026

Input-Side Variance Suppression under Non-Normal Transient Amplification in Continuous-Control Reinforcement Learning

Continuous-control reinforcement learning (RL) often exhibits large closed-loop variance, high-frequency control jitter, and sensitivity to disturbance injection. Existing explanations usually emphasize disturbance sources such as action noise, exploration perturbations, or policy nonsmoothness. This letter studies a complementary amplifier-side perspective: in nominally stable yet strongly non-normal closed loops, small input perturbations can undergo transient amplification and lead to disproportionately large state covariance. Motivated by this source--amplifier decomposition, we introduce an input-side variance suppression layer that operates between the learned policy and the plant input to reduce applied-input variance and step-to-step jitter. To separate mechanism from correlation, we use two control-theoretic interventions: one varies only eigenvector geometry under fixed eigenvalues and spectral radius, and the other varies only applied-input statistics under fixed strongly non-normal geometry. We then provide mechanism-consistent external validation on planar quadrotor tasks. Throughout, Koopman/ALE surrogates are used only as analysis and certification tools, not as direct performance paths. Taken together, the results support a narrower claim: in the studied settings, non-normal transient amplification is an important and under-emphasized contributor to execution-time closed-loop variance, and source-side suppression can reduce downstream covariance without changing the structural peak gain.

eess.SY↗

arXiv2025

DISC: Dynamic Decomposition Improves LLM Inference Scaling

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually designed based on domain knowledge. We propose dynamic decomposition, a method that adaptively and automatically partitions solution and reasoning traces into manageable steps during inference. By more effectively allocating compute -- particularly through subdividing challenging steps and prioritizing their sampling -- dynamic decomposition significantly improves inference efficiency. Experiments on benchmarks such as APPS, MATH, and LiveCodeBench demonstrate that dynamic decomposition outperforms static approaches, including token-level, sentence-level, and single-step decompositions, reducing the pass@10 error rate by 5.0%, 6.7%, and 10.5% respectively. These findings highlight the potential of dynamic decomposition to improve a wide range of inference scaling techniques.

cs.LG↗

arXiv2023

Evolutionary Multitasking with Solution Space Cutting for Point Cloud Registration

Point cloud registration (PCR) is a popular research topic in computer vision. Recently, the registration method in an evolutionary way has received continuous attention because of its robustness to the initial pose and flexibility in objective function design. However, most evolving registration methods cannot tackle the local optimum well and they have rarely investigated the success ratio, which implies the probability of not falling into local optima and is closely related to the practicality of the algorithm. Evolutionary multi-task optimization (EMTO) is a widely used paradigm, which can boost exploration capability through knowledge transfer among related tasks. Inspired by this concept, this study proposes a novel evolving registration algorithm via EMTO, where the multi-task configuration is based on the idea of solution space cutting. Concretely, one task searching in cut space assists another task with complex function landscape in escaping from local optima and enhancing successful registration ratio. To reduce unnecessary computational cost, a sparse-to-dense strategy is proposed. In addition, a novel fitness function robust to various overlap rates as well as a problem-specific metric of computational cost is introduced. Compared with 8 evolving approaches, 4 traditional approaches and 3 deep learning approaches on the object-scale and scene-scale registration datasets, experimental results demonstrate that the proposed method has superior performances in terms of precision and tackling local optima.

cs.CV↗

arXiv2020

Dielectrophoretic Equilibrium of Complex Particles

In contrast to the commonly used spherical Janus particles, here we used engineered Janus particles that are fabricated using photolithography technique for precise control over their geometry and coated regions. Specifically, we studied a lollipop-shaped complex particle where its head is coated with gold while its tail is left bare. Due to their distinct electrical properties (i.e. electrical polarizability) the particle exhibits force equilibrium where opposite dielectrophoretic forces acting on its head and tail exactly cancel each other to yield a stable equilibrium position. This was realized in a quadrupolar electrode array where the equilibrium position of the engineered particle could be tuned by the frequency. This stands in contrast to the standard dielectrophoretic behavior where the particle shifts positions from either the center of the quad to the very edge of the electrodes when shifting from a negative to positive dielectrophoretic response, respectively. This opens new opportunities for positioning control of such complex particles for self-assembly, biosensing, biomimetic spermatozoa and more.

cond-mat.soft↗

arXiv2016

The Moments of Lévy's area using a sticky shuffle Hopf algebra

Lévy's stochastic area for planar Brownian motion is the difference of two iterated integrals of second rank against its component one-dimen\-sional Brownian motions. Such iterated integrals can be multiplied using the sticky shuffle product determined by the underlying Itô algebra of stochastic differentials. We use combinatorial enumerations that arise from the distributive law in the corresponding Hopf algebra structure to evaluate the moments of Lévy's area. These Lévy moments are well known to be given essentially by the Euler numbers. This has recently been confirmed in a novel combinatorial approach by Levin and Wildon. Our combinatorial calculations considerably simplify their approach.

math.PR↗