arXiv subjects

Chao Sun

Publications and source records attributed to Chao Sun.

At least 55 records · Page 3Linked to original sources

arXiv2025

PillarMamba: Learning Local-Global Context for Roadside Point Cloud via Hybrid State Space Model

Serving the Intelligent Transport System (ITS) and Vehicle-to-Everything (V2X) tasks, roadside perception has received increasing attention in recent years, as it can extend the perception range of connected vehicles and improve traffic safety. However, roadside point cloud oriented 3D object detection has not been effectively explored. To some extent, the key to the performance of a point cloud detector lies in the receptive field of the network and the ability to effectively utilize the scene context. The recent emergence of Mamba, based on State Space Model (SSM), has shaken up the traditional convolution and transformers that have long been the foundational building blocks, due to its efficient global receptive field. In this work, we introduce Mamba to pillar-based roadside point cloud perception and propose a framework based on Cross-stage State-space Group (CSG), called PillarMamba. It enhances the expressiveness of the network and achieves efficient computation through cross-stage feature fusion. However, due to the limitations of scan directions, state space model faces local connection disrupted and historical relationship forgotten. To address this, we propose the Hybrid State-space Block (HSB) to obtain the local-global context of roadside point cloud. Specifically, it enhances neighborhood connections through local convolution and preserves historical memory through residual attention. The proposed method outperforms the state-of-the-art methods on the popular large scale roadside benchmark: DAIR-V2X-I. The code will be released soon.

cs.CV↗

arXiv2025

Covariance-Intersection-based Distributed Kalman Filtering: Stability Problems Revisited

This paper studies the stability of covariance-intersection (CI)-based distributed Kalman filtering in time-varying systems. For the general time-varying case, a relationship between the error covariance and the observability Gramian is established. Utilizing this relationship, we demonstrate an intuition that the stability of a node is only related to the observability of those nodes that can reach it uniformly. For the periodic time-varying case, it is proved by a monotonicity analysis method that CI-based distributed Kalman filtering converges periodically for any initial condition. The convergent point is shown to be the unique positive definite solution to a Riccati-like equation. Additionally, by constructing an intermediate difference equation, the closed-loop transition matrix of the estimation error system is proved to be Schur stable. Notably, all theoretical results are obtained without requiring network connectivity assumptions. Finally, simulations verify the effectiveness of the stability results.

eess.SY↗

arXiv2025

Experimental study of velocity statistics in wall-bounded turbulent emulsions

Turbulent emulsions are ubiquitous in chemical engineering, food processing, pharmaceuticals, and other fields. However, our experimental understanding of this area remains limited due to the multi-scale nature of turbulent flow and the presence of extensive interfaces, which pose significant challenges to optical measurements. In this study, we address these challenges by precisely matching the refractive indices of the continuous and dispersed phases, enabling us to measure local velocity information at high volume fractions. The emulsion is generated in a turbulent Taylor-Couette flow, with velocity measured at two radial locations: near the inner cylinder (boundary layer) and in the middle gap (bulk region). Near the inner cylinder, the presence of droplets suppresses the emission of angular velocity plumes, which reduces the mean azimuthal velocity and its root mean squared fluctuation. The former effect leads to a higher angular velocity gradient in the boundary layer, resulting in greater global drag on the system. In the bulk region, although droplets suppress turbulence fluctuations, they enhance the cross-correlation between azimuthal and radial velocities, leaving the angular velocity flux contributed by the turbulent flow nearly unchanged. In both locations, droplets suppress turbulence at scales larger than the average droplet diameter and increase the intermittency of velocity increments. However, the effects of the droplets are more pronounced near the inner cylinder than in the bulk, likely because droplets fragment in the boundary layer but are less prone to breakup in the bulk. Our study provides experimental insights into how dispersed droplets modulate global drag, coherent structures, and the multi-scale characteristics of turbulent flow.

physics.flu-dyn↗

arXiv2025

Direct Preference Optimization for LLM-Enhanced Recommendation Systems

Large Language Models (LLMs) have exhibited remarkable performance across a wide range of domains, motivating research into their potential for recommendation systems. Early efforts have leveraged LLMs' rich knowledge and strong generalization capabilities via in-context learning, where recommendation tasks are framed as prompts. However, LLM performance in recommendation scenarios remains limited due to the mismatch between their pretraining objectives and recommendation tasks, as well as the lack of recommendation-specific data during pretraining. To address these challenges, we propose DPO4Rec, a novel framework that integrates Direct Preference Optimization (DPO) into LLM-enhanced recommendation systems. First, we prompt the LLM to infer user preferences from historical interactions, which are then used to augment traditional ID-based sequential recommendation models. Next, we train a reward model based on knowledge-augmented recommendation architectures to assess the quality of LLM-generated reasoning. Using this, we select the highest- and lowest-ranked responses from N samples to construct a dataset for LLM fine-tuning. Finally, we apply a structure alignment strategy via DPO to align the LLM's outputs with desirable recommendation behavior. Extensive experiments show that DPO4Rec significantly improves re-ranking performance over strong baselines, demonstrating enhanced instruction-following capabilities of LLMs in recommendation tasks.

cs.IR↗

arXiv2025

HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer

Roadside vision centric 3D object detection has received increasing attention in recent years. It expands the perception range of autonomous vehicles, enhances the road safety. Previous methods focused on predicting per-pixel height rather than depth, making significant gains in roadside visual perception. While it is limited by the perspective property of near-large and far-small on image features, making it difficult for network to understand real dimension of objects in the 3D world. BEV features and voxel features present the real distribution of objects in 3D world compared to the image features. However, BEV features tend to lose details due to the lack of explicit height information, and voxel features are computationally expensive. Inspired by this insight, an efficient framework learning height prediction in voxel features via transformer is proposed, dubbed HeightFormer. It groups the voxel features into local height sequences, and utilize attention mechanism to obtain height distribution prediction. Subsequently, the local height sequences are reassembled to generate accurate 3D features. The proposed method is applied to two large-scale roadside benchmarks, DAIR-V2X-I and Rope3D. Extensive experiments are performed and the HeightFormer outperforms the state-of-the-art methods in roadside vision centric 3D object detection task.

cs.CV↗

arXiv2025

Solving Online Resource-Constrained Scheduling for Follow-Up Observation in Astronomy: a Reinforcement Learning Approach

In the astronomical observation field, determining the allocation of observation resources of the telescope array and planning follow-up observations for targets of opportunity (ToOs) are indispensable components of astronomical scientific discovery. This problem is computationally challenging, given the online observation setting and the abundance of time-varying factors that can affect whether an observation can be conducted. This paper presents ROARS, a reinforcement learning approach for online astronomical resource-constrained scheduling. To capture the structure of the astronomical observation scheduling, we depict every schedule using a directed acyclic graph (DAG), illustrating the dependency of timing between different observation tasks within the schedule. Deep reinforcement learning is used to learn a policy that can improve the feasible solution by iteratively local rewriting until convergence. It can solve the challenge of obtaining a complete solution directly from scratch in astronomical observation scenarios, due to the high computational complexity resulting from numerous spatial and temporal constraints. A simulation environment is developed based on real-world scenarios for experiments, to evaluate the effectiveness of our proposed scheduling approach. The experimental results show that ROARS surpasses 5 popular heuristics, adapts to various observation scenarios and learns effective strategies with hindsight.

cs.AI↗

arXiv2025

Task Scheduling in Geo-Distributed Computing: A Survey

Geo-distributed computing, a paradigm that assigns computational tasks to globally distributed nodes, has emerged as a promising approach in cloud computing, edge computing, cloud-edge computing and supercomputer computing (HPC). It enables low-latency services, ensures data locality, and handles large-scale applications. As global computing capacity and task demands increase rapidly, scheduling tasks for efficient execution in geo-distributed computing systems has become an increasingly critical research challenge. It arises from the inherent characteristics of geographic distribution, including heterogeneous network conditions, region-specific resource pricing, and varying computational capabilities across locations. Researchers have developed diverse task scheduling methods tailored to geo-distributed scenarios, aiming to achieve objectives such as performance enhancement, fairness assurance, and fault-tolerance improvement. This survey provides a comprehensive and systematic review of task scheduling techniques across four major distributed computing environments, with an in-depth analysis of these approaches based on their core scheduling objectives. Through our analysis, we identify key research challenges and outline promising directions for advancing task scheduling in geo-distributed computing.

cs.DC↗

arXiv2025

Effects of rough walls on sheared annular centrifugal Rayleigh-Bénard convection

In this study, we investigate the coupling effects of roughness and wall shear in an annular centrifugal Rayleigh-Bénard convection (ACRBC) system, where two cylinders rotate with different angular velocities. Two-dimensional direct numerical simulations are conducted within a Rayleigh number range of $10^{6} \leq Ra \leq 10^{8}$, and the non-dimensional angular velocity difference ($\varOmega$), representing wall shear, varied from 0 to 1. The Prandtl number is fixed at $Pr = 4.3$, the inverse Rossby number at $Ro^{-1} = 20$, and the radius ratio at $η= 0.5$. The interaction between wall shear and roughness leads to distinct heat transfer behavior in different regimes. In the buoyancy-dominant regime, an increase in the non-dimensional angular velocity difference ($\varOmega$) significantly enhances heat transfer. However, as $\varOmega$ continues to rise, a sharp reduction in heat transfer is observed in the transitional regime. Beyond a critical value of $\varOmega$, the flow enters a shear-dominant regime, where heat transfer remains unchanged despite further increases in $\varOmega$.

physics.flu-dyn↗

arXiv2024

Global drag reduction and local flow statistics in Taylor-Couette turbulence with dilute polymer additives

We present an experimental study on the drag reduction by polymers in Taylor-Couette turbulence at Reynolds numbers ($Re$) ranging from $4\times 10^3$ to $2.5\times 10^4$. In this $Re$ regime, the Taylor vortex is present and accounts for more than 50\% of the total angular velocity flux. Polyacrylamide polymers with two different average molecular weights are used. It is found that the drag reduction rate increases with polymer concentration and approaches the maximum drag reduction (MDR) limit. At MDR, the friction factor follows the $-0.58$ scaling, i.e., $C_f \sim Re^{-0.58}$, similar to channel/pipe flows. However, the drag reduction rate is about $20\%$ at MDR, which is much lower than that in channel/pipe flows at comparable $Re$. We also find that the Reynolds shear stress does not vanish and the slope of the mean azimuthal velocity profile in the logarithmic layer remains unchanged at MDR. These behaviours are reminiscent of the low drag reduction regime reported in channel flow (Warholic et al., Exp. Fluids, vol. 27, issue 5, 1999, p. 461-472). We reveal that the lower drag reduction rate originates from the fact that polymers strongly suppress the turbulent flow while only slightly weaken the mean Taylor vortex. We further show that polymers steady the velocity boundary layer and suppress the small-scale Görtler vortices in the near-wall region. The former effect reduces the emission rate of both intense fast and slow plumes detached from the boundary layer, resulting in less flux transport from the inner cylinder to the outer one and reduces energy input into the bulk turbulent flow. Our results suggest that in turbulent flows, where secondary flow structures are statistically persistent and dominate the global transport properties of the system, the drag reduction efficiency of polymer additives is significantly diminished.

physics.flu-dyn↗

arXiv2024

Second harmonic generation with 48% conversion efficiency from cavity polygon modes in a monocrystalline lithium niobate microdisk resonator

Thin-film lithium niobate (TFLN) based optical microresonators offer large nonlinear coefficient d_33 and high light-wave confinement, allowing highly efficient second-order optical nonlinear frequency conversion. Here, we achieved ultra-efficiency second harmonic generation (SHG) from high-Q polygon modes by maximizing the utilization of the highest nonlinear coefficient d_33 in a monocrystalline X-cut TFLN microdisk resonator for the first time. The polygon modes are designed and formed with two parallel sides perpendicular to the optical axis of the lithium niobate crystal by introducing weak perturbations into the microdisk of a tapered fiber, which maximizes the utilization of d_33. The polygon modes exhibit ultrahigh intrinsic Q factors of ~3.86X10(7), due to the fact that polygon modes are located far from the relatively rough sidewall of the microdisk. Moreover, the pump and second harmonic polygon modes share high modal overlap factor of ~80%. Consequently, SHG from cavity polygon modes with absolute conversion efficiency as high as 48.08% was realized at an on-chip pump level of only 4.599 mW without fine domain structures, surpassing the best results (23% and 30%) reported in other two domain-inversion-free phase matching schemes and even approaching the record (52%) in PPLN microresonators.

physics.optics↗

arXiv2024

How interfacial tension enhances drag in turbulent Taylor-Couette flow with neutrally buoyant and equally viscous droplets

The presence of dispersed-phase droplets can result in a notable increase in the system's drag. However, our understanding of the mechanism underlying this phenomenon remains limited. In this study, we use three-dimensional direct numerical simulations with a modified multi-marker volume-of-fluid method to investigate liquid-liquid two-phase turbulence in a Taylor-Couette geometry. The dispersed phase has the same density and viscosity as the continuous phase. The Reynolds number $Re\equiv r_iω_i d/ν$ is fixed at 5200, the volume fraction of the dispersed phase is up to $40\%$, and the Weber number $We\equiv ρu^2_τd/σ$ is around 8. It is found that the increase in the system's drag originates from the contribution of interfacial tension. Specifically, droplets experience significant deformation and stretching in the streamwise direction due to shear near the inner cylinder. Consequently, the rear end of the droplets lags behind the fore head. This causes opposing interfacial tension effects on the fore head and rear end of the droplets. For the fore head of the droplets, the effect of interfacial tension appears to act against the flow direction. For the rear end, the effect appears to act in the flow direction. The increase in the system's drag is primarily attributed to the effect of interfacial tension on the fore head of the droplets which leads to the hindering effect of the droplets on the surrounding continuous phase. This hindering effect disrupts the formation of high-speed streaks, favoring the formation of low-speed ones, which are generally associated with higher viscous stress and drag of the system. This study provides new insights into the mechanism of drag enhancement reported in our previous experiments.

physics.flu-dyn↗

arXiv2024

Dynamic equilibrium of electrochemical bubbles growing on micro-electrodes

In gas evolving electrolysis, bubbles grow at electrodes due to a diffusive influx from oversaturation generated locally in the electrolyte by the electrode reaction. When considering electrodes of micrometer-size resembling catalytic islands, bubbles are found to approach dynamic equilibrium states at which they neither grow nor shrink. Such equilibrium states are found at low oversaturation for both, pinning and expanding wetting regimes of the bubbles and are based on the balance of local influx near the bubble foot and global outflux. Unlike the stability of pinned nano-bubbles studied earlier, the Laplace pressure plays a minor role only. We extend the analytical solution of Zhang & Lohse (2023) by taking into account the non-uniform distribution of dissolved gas around the bubble obtained from direct numerical simulation. This allows us to identify the parameter regions of bubble growth, dissolution and dynamic equilibrium as well as to analyze the stability of the equilibrium states. Finally, we draw conclusions on how to possibly enhance the efficiency of electrolysis.

physics.flu-dyn↗

arXiv2024

GRRIS: a real-time intra-site observation scheduling scheme for distributed survey telescope arrays

The distributed telescope array offers promise for conducting large-sky-area, high-frequency time domain surveys. Multiple telescopes can be deployed at each observation site, so intra-site observation task scheduling is crucial for enhancing observation efficiency and quality. Efficient use of observable time and rapid response to special situations are critical to maximize scientific discovery in time domain surveys. Besides, the competing scientific priorities, time-varying observation conditions, and capabilities of observation equipment, lead to a vast search space of the scheduling. So with the increasing number of telescopes and observation fields, balancing computational time with solution quality in observation scheduling poses a significant challenge. Informed by the seminal contributions of earlier studies on a multilevel scheduling model and global scheduler for time domain telescope array, this study is devoted to further exploring the site scheduler. Formulating the observation scheduling of multiple telescopes at the site as a cooperative decision-making problem, this paper proposes GRRIS, a real-time intra-site observation scheduling scheme for telescope array using graph and reinforcement learning. It employs a graph neural network to learn node features that can embed the spatial structure of the observation scheduling. An algorithm based on multi-agent reinforcement learning is designed to efficiently learn the optimum allocation policy of telescope agents to field nodes. Through numerical simulations with real-world scenarios, GRRIS can achieve up to a 22% solution improvement over the most competitive scheme. It offers better scalability and sub-second decision speed, meeting the needs of observation scheduling control for future distributed telescope arrays.

astro-ph.IM↗

arXiv2024

From Darcy flow to convective flow: pore-scale study of density-driven currents in porous media

We conducted a series of pore-scale numerical simulations on convective flow in porous media, with a fixed Schmidt number of 400 and a wide range of Rayleigh numbers. The porous media are modeled using regularly arranged square obstacles in a Rayleigh-Bénard (RB) system. As the Rayleigh number increases, the flow transitions from a Darcy-type regime to an RB-type regime, with the corresponding $Sh-Ra_D$ relationship shifting from sublinear scaling to the classical 0.3 scaling of RB convection. Here, $Sh$ and $Ra_D$ represent the Sherwood number and Rayleigh-Darcy number, respectively. For different porosities, the transition begins at approximately $Ra_D = 4000$, at which point the characteristic horizontal scale of the flow field is comparable to the size of a single obstacle unit. When the thickness of the concentration boundary layer is less than about one-sixth of the pore spacing, the flow finally enters the RB regime. In the Darcy regime, the scaling exponent of $Sh$ and $Ra_D$ decreases as porosity increases. Based on the Grossman-Lohse theory (J. Fluid Mech., vol. 407, 2000; Phys. Rev. Lett., vol. 86, 2001), we provide an explanation for the scaling laws in each regime and highlight the significant impact of mechanical dispersion effects within the boundary layer. Our findings provide some new insights into the validity range of the Darcy model.

physics.flu-dyn↗

arXiv2024

Turbulence modulation in liquid-liquid two-phase Taylor-Couette turbulence

We investigate the coupling effects of the two-phase interface, viscosity ratio, and density ratio of the dispersed phase to the continuous phase on the flow statistics in two-phase Taylor-Couette turbulence at a system Reynolds number of 6000 and a system Weber number of 10 using interface-resolved three-dimensional direct numerical simulations with the volume-of-fluid method. Our study focuses on four different scenarios: neutral droplets, low-viscosity droplets, light droplets, and low-viscosity light droplets. We find that neutral droplets and low-viscosity droplets primarily contribute to drag enhancement through the two-phase interface, while light droplets reduce the system's drag by explicitly reducing Reynolds stress due to the density dependence of Reynolds stress. Additionally, low-viscosity light droplets contribute to greater drag reduction by further reducing momentum transport near the inner cylinder and implicitly reducing Reynolds stress. While interfacial tension enhances turbulent kinetic energy (TKE) transport, drag enhancement is not strongly correlated with TKE transport for both neutral droplets and low-viscosity droplets. Light droplets primarily reduce the production term by diminishing Reynolds stress, whereas the density contrast between the phases boosts TKE transport near the inner wall. Therefore, the reduction in the dissipation rate is predominantly attributed to decreased turbulence production, causing drag reduction. For low-viscosity light droplets, the production term diminishes further, primarily due to their greater reduction in Reynolds stress, while reduced viscosity weakens the density difference's contribution to TKE transport near the inner cylinder, resulting in a more pronounced reduction in the dissipation rate and consequently stronger drag reduction. Our findings provide new insights into the turbulence modulation in two-phase flow.

physics.flu-dyn↗

arXiv2024

Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative Study

Objective: To explore and compare the performance of ChatGPT and other state-of-the-art LLMs on domain-specific NER tasks covering different entity types and domains in TCM against COVID-19 literature. Methods: We established a dataset of 389 articles on TCM against COVID-19, and manually annotated 48 of them with 6 types of entities belonging to 3 domains as the ground truth, against which the NER performance of LLMs can be assessed. We then performed NER tasks for the 6 entity types using ChatGPT (GPT-3.5 and GPT-4) and 4 state-of-the-art BERT-based question-answering (QA) models (RoBERTa, MiniLM, PubMedBERT and SciBERT) without prior training on the specific task. A domain fine-tuned model (GSAP-NER) was also applied for a comprehensive comparison. Results: The overall performance of LLMs varied significantly in exact match and fuzzy match. In the fuzzy match, ChatGPT surpassed BERT-based QA models in 5 out of 6 tasks, while in exact match, BERT-based QA models outperformed ChatGPT in 5 out of 6 tasks but with a smaller F-1 difference. GPT-4 showed a significant advantage over other models in fuzzy match, especially on the entity type of TCM formula and the Chinese patent drug (TFD) and ingredient (IG). Although GPT-4 outperformed BERT-based models on entity type of herb, target, and research method, none of the F-1 scores exceeded 0.5. GSAP-NER, outperformed GPT-4 in terms of F-1 by a slight margin on RM. ChatGPT achieved considerably higher recalls than precisions, particularly in the fuzzy match. Conclusions: The NER performance of LLMs is highly dependent on the entity type, and their performance varies across application scenarios. ChatGPT could be a good choice for scenarios where high recall is favored. However, for knowledge acquisition in rigorous scenarios, neither ChatGPT nor BERT-based QA models are off-the-shelf tools for professional practitioners.

cs.CL↗

arXiv2024

Leveraging Temporal Contexts to Enhance Vehicle-Infrastructure Cooperative Perception

Infrastructure sensors installed at elevated positions offer a broader perception range and encounter fewer occlusions. Integrating both infrastructure and ego-vehicle data through V2X communication, known as vehicle-infrastructure cooperation, has shown considerable advantages in enhancing perception capabilities and addressing corner cases encountered in single-vehicle autonomous driving. However, cooperative perception still faces numerous challenges, including limited communication bandwidth and practical communication interruptions. In this paper, we propose CTCE, a novel framework for cooperative 3D object detection. This framework transmits queries with temporal contexts enhancement, effectively balancing transmission efficiency and performance to accommodate real-world communication conditions. Additionally, we propose a temporal-guided fusion module to further improve performance. The roadside temporal enhancement and vehicle-side spatial-temporal fusion together constitute a multi-level temporal contexts integration mechanism, fully leveraging temporal information to enhance performance. Furthermore, a motion-aware reconstruction module is introduced to recover lost roadside queries due to communication interruptions. Experimental results on V2X-Seq and V2X-Sim datasets demonstrate that CTCE outperforms the baseline QUEST, achieving improvements of 3.8% and 1.3% in mAP, respectively. Experiments under communication interruption conditions validate CTCE's robustness to communication interruptions.

cs.RO↗

arXiv2024

Extended Spreading of Saline Droplets upon Impact on a Frosty Surface

Understanding the solidification dynamics of impacted water droplets is fundamental and crucial for applications, especially with the presence of frost and salt. Here, we experimentally investigate the spreading and freezing dynamics of saline droplets upon impact on a cold, frosty surface. Our findings demonstrate that the frost and salt can lead to an extended spreading of impacted droplets under specific conditions. In addition to the well-known 1/2 inertial spreading scaling law for droplets impact on a cold substrate, we observe a distinct transition to a 1/10 scaling law dominated by the capillary-viscous relation at low impacting velocities. We formulate the onset criterion for this extended spreading regime and derive a scaling dependence that captures the droplet's arrested diameter over various supercooling temperatures, by incorporating the effect of impact inertia, partial-wetting behavior and salinity. Based on the analysis, a unified model is proposed for predicting the droplet arrested diameter over a wide range of impact velocity and salinity.

physics.flu-dyn↗