arXiv subjects

Chenchen Wang

Publications and source records attributed to Chenchen Wang.

14 recordsLinked to original sources

arXiv2026

Deadline-Aware Adaptive Prefill Chunking for Efficient Large Language Model Serving

Continuous batching improves large language model (LLM) serving throughput, but long prompt prefills can delay decode iterations and violate inter-token latency objectives. Chunked prefill mitigates this interference, yet its chunk size is normally fixed: small chunks protect decode latency but repeatedly pay launch overhead, while large chunks improve prefill efficiency but create latency spikes. We introduce SLOWeave, an online scheduling method that selects the largest prefill chunk predicted to finish before the earliest active decode deadline. The decision requires no workload-specific chunk-size tuning and is computed by a logarithmic-time search over a monotone iteration-cost model. We prove that, whenever a decode-only iteration is feasible and the cost predictor is accurate, SLOWeave maximizes immediate prefill progress among decisions that preserve every active request's next-token deadline. We evaluate the method in a reproducible event-driven simulator and an iteration-level GPU runtime across chat, mixed-context, long-context, and bursty workloads. Under a 25ms time-per-output-token objective, SLOWeave improves goodput over the strongest fixed-chunk baseline by 39% on mixed requests and 38% on long-context requests. Under a stricter 10ms objective, the gains rise to 3.3$\times$ and 2.4$\times$, respectively. These results isolate adaptive chunk sizing as a useful serving primitive and provide an implementation-ready controller for integration with iteration-level LLM runtimes.

cs.CL↗

arXiv2026

Backstepping-Guided Reinforcement Learning for Wide-Range Saint-Venant Canal Regulation

Backstepping control provides local stability guarantees for nonlinear Saint-Venant systems, but its regulation performance may degrade when the system operates far from the nominal equilibrium. This letter proposes a backstepping-guided soft actor-critic (SAC) controller framework that incorporates model-based control knowledge into reinforcement learning (RL). The nominal backstepping control law is first learned by deep operator network (DeepONet) and embedded into the actor and critic networks as prior informed feature representations. The learned prior is further combined with the SAC policy to generate the final control input, while a transfer-learning strategy preserves the useful backstepping knowledge during adaptation to the nonlinear dynamics. Simulation results on the Sambre River model demonstrate that the proposed method improves learning efficiency and maintains effective regulation over larger initial deviations than backstepping control.

math.AP↗

arXiv2026

Avalanche Sensing via Kerr frequency comb in an Optical Microcavity

Sensors based on optical microcavities enhance light-matter interactions within an ultraconfined volume, enabling high-sensitivity detection across a wide range of sensing applications. In these systems, environmental perturbations modify the intrinsic resonance properties of the cavity, typically manifested as frequency shifts, linewidth broadening, or mode splitting. However, the minimum resolvable change in these spectral properties fundamentally limits the overall sensor sensitivity. Here, we propose a new avalanche sensing scheme enabled by Kerr nonlinearity. Instead of relying on the detection of frequency shifts, our approach exploits abrupt state transitions in a Kerr frequency comb to amplify weak perturbations. We provide a theoretical analysis of the underlying mechanism of this scheme and validate the concept through both coupled-mode theory (CMT) modeling and full-wave electromagnetic simulations.

physics.optics↗

arXiv2026

DogWeave: High-Fidelity 3D Canine Reconstruction from a Single Image via Normal Fusion and Conditional Inpainting

Monocular 3D animal reconstruction is challenging due to complex articulation, self-occlusion, and fine-scale details such as fur. Existing methods often produce distorted geometry and inconsistent textures due to the lack of articulated 3D supervision and limited availability of back-view images in 2D datasets, which makes reconstructing unobserved regions particularly difficult. To address these limitations, we propose DogWeave, a model-based framework for reconstructing high-fidelity 3D canine models from a single RGB image. DogWeave improves geometry by refining a coarsely-initiated parametric mesh into a detailed SDF representation through multi-view normal field optimization using diffusion-enhanced normals. It then generates view-consistent textures through conditional partial inpainting guided by structure and style cues, enabling realistic reconstruction of unobserved regions. Using only about 7,000 dog images processed via our 2D pipeline for training, DogWeave produces complete, realistic 3D models and outperforms state-of-the-art single image to 3d reconstruction methods in both shape accuracy and texture realism for canines.

cs.CV↗

arXiv2025

The Incompressible Navier-Stokes-Fourier Limits from Boltzmann-Fermi-Dirac Equation for Low Regularity Data

We consider the hydrodynamic limits of the quantum Boltzmann equation with Fermi-Dirac statistics for hard sphere and hard potentials in the whole space. By analyzing the spectrum of the linearized collision operator combined with the transport operator and its associated semigroup, the incompressible Navier-Stokes-Fourier limits from the BFD equation is verified rigorously. Compared to the results in [Jiang-Xiong-Zhou,J. Differ. Equ.,2022], this paper works with a lower regularity for the initial data. In addition, the fixed-point arguments together with a time iteration ensure us to obtain the lifespan of kinetic solution coincides with those of limiting fluid solution.

math.AP↗

arXiv2025

Soft Actor-Critic with Backstepping-Pretrained DeepONet for control of PDEs

This paper develops a reinforcement learning-based controller for the stabilization of partial differential equation (PDE) systems. Within the soft actor-critic (SAC) framework, we embed a DeepONet, a well-known neural operator (NO), which is pretrained using the backstepping controller. The pretrained DeepONet captures the essential features of the backstepping controller and serves as a feature extractor, replacing the convolutional neural networks (CNNs) layers in the original actor and critic networks, and directly connects to the fully connected layers of the SAC architecture. We apply this novel backstepping and reinforcement learning integrated method to stabilize an unstable ffrst-order hyperbolic PDE and an unstable reactiondiffusion PDE. Simulation results demonstrate that the proposed method outperforms the standard SAC, SAC with an untrained DeepONet, and the backstepping controller on both systems.

math.OC↗

arXiv2025

Uniform convergence to the equilibrium of the homogeneous Boltzmann-Fermi-Dirac Equation with moderately soft potential

We concern the long-time behavior of mild solutions to the spatially homogeneous Boltzmann--Fermi--Dirac equation with moderately soft potential. Based on the well-posedness results in [X-G. Lu, J. Stat. Phys., 105, (2001), 353-388], we prove that the mild solution decays algebraically to the Fermi--Dirac statistics with an explicit rate. Under the framework of the level set analysis by De Giorgi, we derive an $L^\infty$ estimate which is uniform with respect to the quantum parameter $\varepsilon$. All quantitative estimates are independent of $\varepsilon$, which implies that they also hold in the classical limit, i.e., the Boltzmann equation.

math.AP↗

arXiv2024

LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification

Lensless cameras, innovatively replacing traditional lenses for ultra-thin, flat optics, encode light directly onto sensors, producing images that are not immediately recognizable. This compact, lightweight, and cost-effective imaging solution offers inherent privacy advantages, making it attractive for privacy-sensitive applications like face verification. Typical lensless face verification adopts a two-stage process of reconstruction followed by verification, incurring privacy risks from reconstructed faces and high computational costs. This paper presents an end-to-end optimization approach for privacy-preserving face verification directly on encoded lensless captures, ensuring that the entire software pipeline remains encoded with no visible faces as intermediate results. To achieve this, we propose several techniques to address unique challenges from the lensless setup which precludes traditional face detection and alignment. Specifically, we propose a face center alignment scheme, an augmentation curriculum to build robustness against variations, and a knowledge distillation method to smooth optimization and enhance performance. Evaluations under both simulation and real environment demonstrate our method outperforms two-stage lensless verification while enhancing privacy and efficiency. Project website: \url{lenslessface.github.io}.

cs.CV↗

arXiv2024

DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes

Recent large vision-language models (LVLMs) for video understanding are primarily fine-tuned with various videos scraped from online platforms. Existing datasets, such as ActivityNet, require considerable human labor for structuring and annotation before effectively utilized for tuning LVLMs. While current LVLMs are primarily trained on existing datasets in broad, general-purpose settings, adapting them to specific downstream scenarios remains challenging, as collecting and annotating task-specific videos is highly labor-intensive and time-consuming. To address this issue, we propose a three-stage framework named DreamFrame for automatically generating style-consistent keyframes and corresponding question-answer (QA) pairs to support LVLM instruction tuning. DreamFrame generates datasets in a movie-like manner. First, we utilize an LLM to generate structured movie plots including movie prior information (like overview and style), frame descriptions and plot-related QA pairs, with a story expansion strategy to mitigate context length limitations.Then, to ensure visual consistency across generated frames, we design a Style Immobilization Process which maintains consistent style through an embedding learning strategy. Finally, frame descriptions and style embeddings are integrated to produce coherent keyframes. Using DreamFrame, we construct a dataset comprising approximately 1k stylized keyframe-like videos and 100k diverse QA pairs. Extensive fine-tuned experiments on various LVLM architectures demonstrate the effectiveness of the proposed dataset. Furthermore, based on the proposed dataset, we fine-tune a new LVLM named DreamFrame-7B, which significantly surpasses the previous similar-sized LVLMs across different benchmarks.

cs.CV↗

arXiv2023

Transverse spin selectivity in helical nanofibers prepared without any chiral molecule

In the last decade, chirality-induced spin selectivity (CISS) has been attracting extensive interest. However, there still exists a large gap between experiments and quantitative theoretical results, and the microscopic mechanism of CISS, especially transverse CISS where electrons are injected perpendicular to the helix axis of chiral molecules, remains elusive. Here, we address these issues by performing a combined experimental and theoretical study on conducting polyaniline helical nanofibers which are synthesized in the absence of any chiral species. Large spin polarization is measured in both left- and right-handed nanofibers for electrons injected perpendicular to their helix axis, which is comparable to the value of parallel electron injection in other chiral molecules, and it will be reversed by switching the handedness between two enantiomers. We develop a theoretical model with extremely weak spin-orbit coupling arising exclusively from electron propagation between neighboring polyanilines and the numerical results are quantitatively consistent with the experimental data. Our results demonstrate that the supramolecular handedness is sufficient for spin-selective electron transmission in chiral molecules assembled from achiral monomers and the mechanism of transverse CISS is revealed.

cond-mat.mes-hall↗

arXiv2023

Extremely Large-scale Array Systems: Near-Field Codebook Design and Performance Analysis

Extremely Large-scale Array (ELAA) promises to deliver ultra-high data rates with increased antenna elements. However, increasing antenna elements leads to a wider realm of near-field, which challenges the traditional design of codebooks. In this paper, we propose novel near-field codebook schemes based on the fitting formula of codewords' quantization performance. First, we analyze the quantization performance properties of uniform linear array (ULA) and uniform planar array (UPA) codewords. Our findings reveal an intriguing property: the correlation formula for ULA codewords can be represented by the elliptic formula, while the correlation formula for UPA codewords can be approximated using the ellipsoid formula. Building on this insight, we propose a ULA uniform codebook that maximizes the minimum correlation based on the derived formula. Moreover, we introduce a ULA dislocation codebook to further reduce quantization overhead. Continuing our exploration, we propose UPA uniform and dislocation codebook schemes. Our investigation demonstrates that oversampling in the angular domain offers distinct advantages, achieving heightened accuracy while minimizing overhead in quantifying near-field channels. Numerical results demonstrate the appealing advantages of the proposed codebook over existing methods in decreasing quantization overhead and increasing quantization accuracy.

cs.IT↗

arXiv2022

Uniqueness of global weak solutions to the frame hydrodynamics for biaxial nematic phases in $\mathbb{R}^2$

We consider the hydrodynamics for biaxial nematic phases described by a field of orthonormal frame, which can be derived from a molecular-theory-based tensor model. We prove the uniqueness of global weak solutions to the Cauchy problem of the frame hydrodynamics in dimensional two. The proof is mainly based on the suitable weaker energy estimates within the Littlewood--Paley analysis. We take full advantage of the estimates of nonlinear terms with rotational derivatives on $SO(3)$, together with cancellation relations and dissipative structures of the biaxial frame system.

math.AP↗

arXiv2022

Well-posedness of frame hydrodynamics for biaxial nematic liquid crystals

We consider the hydrodynamics for the biaxial nematic phase characterized by a field of orthonormal frame, which can be derived from a molecular-theory-based tensor model. In dimension two and three, we establish the local well-posedness and the blow-up criterion for smooth solutions to the frame hydrodynamic model. Furthermore, we prove the global existence of weak solutions in $\mathbb{R}^2$ which are nonsmooth at finitely many singular times.

math.AP↗

arXiv2015

Unraveling the luminescence signatures of chemical defects in polyethylene

Chemical defects in polyethylene (PE) can deleteriously downgrade its electrical properties and performance. Although these defects usually leave spectroscopic signatures in terms of characteristic luminescence peaks, it is nontrivial to make unambiguous assignments of the peaks to specific defect types. In this work, we go beyond traditional density functional theory calculations to determine defect-derived emission and absorption energies in PE. In particular, we characterize PE defect levels in terms of thermodynamic and adiabatic charge transition levels that involve total energy calculations of neutral and charged defects. Calculations are performed at several levels of theory including those involving (semi)local and hybrid electron exchange-correlation functionals, and many-body perturbation theory. With these critical elements, the calculated defect transition levels are in excellent correspondence to observed luminescence spectra of PE, thus clarifying and confirming the origins of the observed peaks. Based on this work, a prescription with a reasonable computational expense is proposed to accurately predict and assign spectroscopic signatures of defects in other organic polymers as well.

cond-mat.mtrl-sci↗