arXiv subjects

Wenjie Chen

Publications and source records attributed to Wenjie Chen.

At least 19 recordsLinked to original sources

arXiv2026

Metasurface-integrated VCSEL designed for polarization control in optical Ising machines

The orthogonal polarization states of vertical-cavity surface-emitting lasers (VCSELs) can be used to describe candidate solutions to the Ising Hamiltonian, which is useful for solving quadratic unconstrained binary optimization problems. However, the natural anisotropy of VCSELs tends to overly favor one polarization state, which impedes the system from working as desired. In this work, we have designed and fabricated a metasurface, which may lead to a VCSEL with reduced undesired anisotropy. By changing the geometric size of nano-structures in the metasurface, the polarization state of the output light can be altered. Based on the injection-locking theory and spin-flip model, we numerically show that VCSELs with lowered anisotropy are more easily affected by the injection locking needed in Ising systems. Additionally, we numerically study the evolution of a 3-bit VCSEL-based Ising system and verify that the computational accuracy of the photonic Ising machine can be improved to more than twice that of its counterpart with higher anisotropy.

physics.optics↗

arXiv2026

Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses

LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state handling, and recovery logic. We study this setting as resource-bounded harness selection for fixed-model multi-turn tool agents, with the search surface scoped to prompts and tool-boundary middleware: edits are guarded intercepts at the tool boundary, not arbitrary rewriting of agent execution logic. Our optimizer-agnostic protocol reports mean held-out lift, worst-condition lift, repeatability, logged cost diagnostics, and RelLift95(B), a conservative estimate of the held-out gain of the harness selected under budget B. We instantiate the protocol with prompt-only and prompt-plus-middleware optimizers, including PRISM, which clusters failures and routes repairs to prompt, tool-boundary middleware, or joint edit surfaces within a Pareto search. On BFCL multi-round, tau2-Retail, and tau2-Telecom, PRISM obtains mean held-out lifts of 14.2, 14.9, and 10.1 percentage points and positive empirical RelLift95 on all three benchmarks, and a component ablation attributes the margin chiefly to failure-surface routing and the edit-pattern constraint. Across optimizers, the results show that some search procedures can occasionally find large gains but still choose brittle updates, so the reliability of the chosen harness should be reported alongside average held-out lift.

cs.AI↗

arXiv2026

Agentic ML Exploration (A-MLE) for Ads Ranking

Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteration - the cycles of research, implementation, training, debugging, evaluation, and launch required to surface a single statistically significant improvement. A typical ranking stack contains numerous differentiated models with heterogeneous data, architectures, and infrastructure constraints, and each cycle takes days to weeks of senior engineer attention per model. As a result, techniques that have proven effective on one model diffuse into others slowly and unevenly, leaving substantial recoverable signal unexplored. We present Agentic ML Exploration (A-MLE), an autonomous LLM-agent system that systematically explores ML techniques across a portfolio of ads ranking models. A-MLE decomposes ML iteration into five stages involving hypothesis generation, exploration strategy, experiment execution, result analysis and shared knowledge substrate which are orchestrated by a single agent that invokes domain-specific skills and agentic workflows against a sandboxed execution layer, with human-in-the-loop checkpoints at each stage boundary. We deploy A-MLE across a representative set of large-scale ads ranking models and evaluate it along a tiered capability framework (tool availability, autonomous workflow execution, and open-ended exploration). We further report a controlled cross-LLM study using a fixed agent loop, which surfaces qualitative differences in execution reliability and exploration aggressiveness across the Claude Sonnet, Gemini, and GPT families. We discuss failure modes and the design choices that govern reliability. Our findings suggest that agentic exploration is a practical force multiplier for ML engineers in industrial recommenders, especially for the long tail of models that rarely receive expert attention.

cs.AI↗

arXiv2026

Personalized Treatment Outcome Prediction from Scarce Data via Dual-Channel Knowledge Distillation and Adaptive Fusion

Personalized treatment outcome prediction based on trial data for small-sample and rare patient groups is a critical task in precision medicine. However, the high cost and scarcity of trial data limit the prediction performance. To address this issue, we propose a cross-fidelity knowledge distillation and adaptive fusion network (CFKD-AFN), which leverages abundant but low-fidelity simulation data to enhance the prediction on scarce but high-fidelity trial data. CFKD-AFN incorporates a dual-channel knowledge distillation module to extract complementary knowledge from the low-fidelity model, along with an attention-guided fusion module to adaptively integrate multi-source information. Experiments on chronic obstructive pulmonary disease show that CFKD-AFN reduces the mean squared error by 6.67% ~ 74.55% and the mean absolute percentage error by 1.43% ~ 51.54% compared to the evaluated competing methods and remains robust to varying high-fidelity dataset sizes. Furthermore, we extend the CFKD-AFN framework to an interpretable variant for exploratory analysis of feature-attribution patterns associated with treatment outcomes.

cs.LG↗

arXiv2026

MSR:Hybrid Field Modeling for CT-MRI Rigid-Deformable Registration of the Cervical Spine with an Annotated Dataset

Accurate CT-MRI registration of the cervical spine is essential for preoperative planning because this region is anatomically complex,highly variable,and vulnerable to injury of the vertebral arteries and spinal cord. However,cervical CT-MRI registration remains underexplored,particularly for rigid-deformable hybrid modeling,and the lack of high-quality annotated multimodal data further limits progress. To address these challenges, we construct and release a comprehensively annotated CT-MRI dataset, R-D-Reg, and propose MSR, a rigid-deformable hybrid registration framework for complex joint structures. Specifically, MSR includes a rigid registration module for independent local rigid alignment of individual vertebrae and a deformable registration module with an MSL block that combines Mamba-based global modeling and Swin Transformer-based local modeling through adaptive gating. The rigid and deformable deformation fields are then fused to generate a hybrid field that better preserves local anatomical consistency. The code and dataset are publicly available at https://github.com/ssc1230609-spec/MSR-registration.

cs.CV↗

arXiv2026

Multi-Objective Evolutionary Optimization of Chance-Constrained Multiple-Choice Knapsack Problems with Implicit Probability Distributions

The multiple-choice knapsack problem (MCKP) is a classic combinatorial optimization with wide practical applications. This paper investigates a significant yet underexplored extension of MCKP: the multi-objective chance-constrained MCKP (MO-CCMCKP) under implicit probability distributions. The goal of the problem is to simultaneously minimize the total cost and maximize the confidence level of satisfying the capacity constraint, capturing essential trade-offs in domains like 5G network configuration. To address the computational challenge of evaluating chance constraints under implicit distributions, we first propose an order-preserving efficient resource allocation Monte Carlo (OPERA-MC) method. This approach adaptively allocates sampling resources to preserve dominance relationships while reducing evaluation time significantly. Further, we develop NHILS, a hybrid evolutionary algorithm that integrates specialized initialization and local search into NSGA-II to navigate sparse feasible regions. Experiments on synthetic benchmarks and real-world 5G network configuration benchmarks demonstrate that NHILS consistently outperforms several state-of-the-art multi-objective optimizers in convergence, diversity, and feasibility. The benchmark instances and source code will be made publicly available to facilitate research in this area.

cs.NE↗

arXiv2026

Universal and Experiment-calibrated Prediction of XANES through Crystal Graph Neural Network and Transfer Learning Strategy

Theoretical simulation is helpful for accurate interpretation of experimental X-ray absorption near-edge structure (XANES) spectra that contain rich atomic and electronic structure information of materials. However, current simulation methods are usually too complex to give the needed accuracy and timeliness when a large amount of data need to be analyzed, such as for in-situ characterization of battery materials. To address these problems, artificial intelligence (AI) models have been developed for XANES prediction. However, instead of using experimental XANES data, the existing models are trained using simulated data, resulting in significant discrepancies between the predicted and experimental spectra. Also, the universality across different elements has not been well studied for such models. In this work, we firstly establish a crystal graph neural network, pre-trained on simulated XANES data covering 48 elements, to achieve universal XANES prediction with a low average relative square error of 0.020223; and then utilize transfer learning to calibrate the model using a small experimental XANES dataset. After calibration, the edge energy misalignment error of the predicted S, Ti and Fe K edge XANES is significantly reduced by about 80%. The method demonstrated in this work opens up a new way to achieve fast, universal, and experiment-calibrated XANES prediction.

cond-mat.mtrl-sci↗

arXiv2025

Memetic Search for Green Vehicle Routing Problem with Private Capacitated Refueling Stations

The green vehicle routing problem with private capacitated alternative fuel stations (GrVRP-PCAFS) extends the traditional green vehicle routing problem by considering capacitated refueling stations, where a limited number of vehicles can refuel simultaneously and additional vehicles must wait. This feature presents new challenges for route planning, as waiting times at stations must be managed while keeping route durations within limits and reducing total travel distance. This article presents METS, a novel memetic algorithm (MA) with separate constraint-based tour segmentation (SCTS) and a local search procedure tailored for solving GrVRP-PCAFS. METS balances exploration and exploitation through three key components. For exploration, the SCTS strategy splits giant tours to generate diverse solutions, and the search process is guided by a comprehensive fitness evaluation function to dynamically control feasibility and diversity to produce solutions that are both diverse and near-feasible. For exploitation, the local search procedure incorporates tailored move operators with constant-time evaluation mechanisms, enabling efficient examination of large solution neighborhoods. Experimental results demonstrate that METS discovers 31 new best-known solutions out of 40 instances in existing benchmark sets, achieving substantial improvements over current state-of-the-art methods. Additionally, a new large-scale benchmark set based on real-world logistics data is introduced to facilitate future research.

cs.NE↗

arXiv2025

Targeted-Subharmonic-Eliminating Pulse Density Modulation for Wireless Power Transfer Systems

This letter proposes a targeted-subharmonic-eliminating pulse density modulation (PDM) method for series-series (SS) compensated wireless power transfer (WPT) systems. The subharmonic frequency components which excite current abnormal oscillations in PDM controlled WPT systems are eliminated through a specially designed noise transfer function (NTF). The proposed method is simple to implement in both primary and secondary sides of WPT systems and exhibits a certain tolerance to deviations caused by inaccurate coupling coefficient identification in NTF design. Experimental results demonstrated the effectiveness and robustness of the proposed method in suppressing current abnormal oscillations and reducing the fluctuations in current amplitudes.

eess.SY↗

arXiv2025

Cascaded Large-Scale TSP Solving with Unified Neural Guidance: Bridging Local and Population-based Search

The traveling salesman problem (TSP) is a fundamental NP-hard optimization problem. Over the past decades, traditional heuristic methods have achieved substantial success in solving TSP, yet their performance, particularly for large-scale instances, remains to be further improved. The advancement of deep learning technologies over the past decade has driven a growing number of attempts to solve TSP by leveraging neural guidance. However, these efforts predominantly focus on small-scale TSP instances, with limited improvements in solving performance for large-scale instances, revealing persistent scalability challenges. This work presents UNiCS, a novel unified neural-guided cascaded solver for solving large-scale TSP instances. UNiCS comprises a local search (LS) phase and a population-based search (PBS) phase, both guided by a learning component called unified neural guidance (UNG). Specifically, UNG guides solution generation across both phases and determines appropriate phase transition timing to effectively combine the complementary strengths of LS and PBS. While trained only on simple distributions with relatively small-scale TSP instances, UNiCS generalizes effectively to challenging TSP benchmarks containing much larger instances (10,000-71,009 nodes) with diverse node distributions entirely unseen during training. Experimental results on the large-scale TSP instances demonstrate that UNiCS consistently outperforms state-of-the-art methods, with its advantage remaining consistent across various runtime budgets.

cs.NE↗

arXiv2025

GTool: Graph Enhanced Tool Planning with Large Language Model

Tool planning with large language models (LLMs), referring to selecting, organizing, and preparing the tools necessary to complete a user request, bridges the gap between natural language understanding and task execution. However, current works treat different tools as isolated components and fail to leverage the inherent dependencies of tools, leading to invalid planning results. Since tool dependencies are often incomplete, it becomes challenging for LLMs to accurately identify the appropriate tools required by a user request, especially when confronted with a large toolset. To solve this challenge, we propose \texttt{GTool}, which is the first work aiming to enhance the tool planning ability of LLMs under incomplete dependencies. \texttt{GTool} constructs a request-specific tool graph to select tools efficiently and generate the \texttt{ } which provides sufficient dependency information understandable by LLMs. Moreover, a missing dependency prediction task is designed to improve the reliability of \texttt{GTool} with incomplete dependencies. Without trimming LLMs, \texttt{GTool} can be seamlessly integrated with various LLM backbones without extensive retraining. Extensive experiments show that \texttt{GTool} achieves more than 29.6\% performance improvements compared with the state-of-the-art (SOTA) baselines with a light-weight (7B) LLM backbone.

cs.AI↗

arXiv2025

Knowledge-Guided Memetic Algorithm for Capacitated Arc Routing Problems with Time-Dependent Service Costs

The capacitated arc routing problem with time-dependent service costs (CARPTDSC) is a challenging combinatorial optimization problem that arises from winter gritting applications. CARPTDSC has two main challenges about time consumption. First, it is an NP-hard problem. Second, the time-dependent service costs of tasks require frequent evaluations during the search process, significantly increasing computational effort. These challenges make it difficult for existing algorithms to perform efficient searches, often resulting in limited efficiency. To address these issues, this paper proposes a knowledge-guided memetic algorithm with golden section search and negatively correlated search (KGMA-GN), where two knowledge-guided strategies are introduced to improve search efficiency. First, a knowledge-guided initialization strategy (KGIS) is proposed to generate high-quality initial solutions to speed up convergence. Second, a knowledge-guided small-step-size local search strategy (KGSLSS) is proposed to filter out invalid moves, thereby reducing unnecessary evaluations and saving the computation time. Experimental results on five benchmark test sets, including both small- and larger-scale instances, demonstrate that KGMA-GN achieves higher search efficiency than the state-of-the-art methods. Moreover, the ablation study further confirms that the knowledge-guided local search operators in KGSLSS can significantly reduce runtime compared to traditional operators, especially for the knowledge-guided swap operator, which achieves more than a tenfold improvement in speed.

cs.NE↗

arXiv2025

In-Context Meta LoRA Generation

Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms of storage and inference. Moreover, existing parameter generation methods fail to capture the correlations among these tasks, making multi-task LoRA parameter generation challenging. To address these limitations, we propose In-Context Meta LoRA (ICM-LoRA), a novel approach that efficiently achieves task-specific customization of large language models (LLMs). Specifically, we use training data from all tasks to train a tailored generator, Conditional Variational Autoencoder (CVAE). CVAE takes task descriptions as inputs and produces task-aware LoRA weights as outputs. These LoRA weights are then merged with LLMs to create task-specialized models without the need for additional fine-tuning. Furthermore, we utilize in-context meta-learning for knowledge enhancement and task mapping, to capture the relationship between tasks and parameter distributions. As a result, our method achieves more accurate LoRA parameter generation for diverse tasks using CVAE. ICM-LoRA enables more accurate LoRA parameter reconstruction than current parameter reconstruction methods and is useful for implementing task-specific enhancements of LoRA parameters. At the same time, our method occupies 283MB, only 1\% storage compared with the original LoRA.

cs.CL↗

arXiv2025

Neural Influence Estimator: Towards Real-time Solutions to Influence Blocking Maximization

Real-time solutions to the influence blocking maximization (IBM) problems are crucial for promptly containing the spread of misinformation. However, achieving this goal is non-trivial, mainly because assessing the blocked influence of an IBM problem solution typically requires plenty of expensive Monte Carlo simulations (MCSs). This work presents a novel approach that enables solving IBM problems with hundreds of thousands of nodes and edges in seconds. The key idea is to construct a fast-to-evaluate surrogate model called neural influence estimator (NIE) offline as a substitute for the time-intensive MCSs, and then combine it with optimization algorithms to address IBM problems online. To this end, a learning problem is formulated to build the NIE that takes the false-and-true information instance as input, extracts features describing the topology and inter-relationship between two seed sets, and predicts the blocked influence. A well-trained NIE can generalize across different IBM problems given a social network, and can be readily combined with existing IBM optimization algorithms. The experiments on 25 IBM problems with up to millions of edges show that the NIE-based optimization method can be up to four orders of magnitude faster than MCSs-based optimization method to achieve the same optimization quality. Moreover, given a one-minute limit, the NIE-based method can solve IBM problems with up to hundreds of thousands of nodes, which is at least one order of magnitude larger than what can be solved by existing methods.

cs.NE↗

arXiv2024

AI-Driven Accelerated Discovery of Intercalation-type Cathode Materials for Magnesium Batteries

Magnesium-ion batteries hold promise as future energy storage solution, yet current Mg cathodes are challenged by low voltage and specific capacity. Herein, we present an AI-driven workflow for discovering high-performance Mg cathode materials. Utilizing the common characteristics of various ionic intercalation-type electrodes, we design and train a Crystal Graph Convolutional Neural Network model that can accurately predicts electrode voltages for various ions with mean absolute errors (MAE) between 0.25 and 0.33 V. By deploying the trained model to stable Mg compounds from Materials Project and GNoME AI dataset, we identify 160 high voltage structures out of 15,308 candidates with voltages above 3.0 V and volumetric capacity over 800 Ah/L. We further train a precise NequIP model to facilitate accurate and rapid simulations of Mg ionic conductivity. From the 160 high voltage structures, the machine learning molecular dynamics simulations have selected 23 cathode materials with both high energy density and high ionic conductivity. This AI-driven workflow dramatically boosts the efficiency and precision of material discovery for multivalent ion batteries, paving the way for advanced Mg battery development.

cond-mat.mtrl-sci↗

arXiv2024

Topological temporal boundary states in a non-Hermitian spatial crystal

Periodic modulation of the material index in time opens momentum gaps. Such systems are regarded as the temporal analogue of common spatial crystals, wherein the bandgaps open in the frequency space. Recent studies have also led to the theoretical prediction of topological temporal boundary states (TTBSs) in such momentum gaps. In this work, we report the discovery and experimental realization of a new type of TTBS, appearing in a non-Hermitian spatial crystal with spatially periodic loss and gain, wherein the emergence of Bloch momentum gap is associated with a parity-time broken phase, instead of relying on periodic temporal modulation. By inducing a sudden flip of signs of the loss and gain profile, a mode emerges in the middle of the Bloch momentum gap and peaks at the flipping instant, which is regarded as a temporal boundary. Remarkably, we found that the temporal flip induces a topological transition in time, and the said mode is a TTBS that is a temporal analogue of the Jackiw-Rebbi state. The TTBS is experimentally observed in a 1D active mechanical lattice, and it can generically emerge in a wide range of non-Hermitian systems. By linking non-Hermitian physics with spatiotemporal topological systems, our results not only deepen the understanding of temporal topological phases but also open new grounds for controlling transient waves by topological means.

physics.optics↗

arXiv2024

GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning

Robotic object packing has broad practical applications in the logistics and automation industry, often formulated by researchers as the online 3D Bin Packing Problem (3D-BPP). However, existing DRL-based methods primarily focus on enhancing performance in limited packing environments while neglecting the ability to generalize across multiple environments characterized by different bin dimensions. To this end, we propose GOPT, a generalizable online 3D Bin Packing approach via Transformer-based deep reinforcement learning (DRL). First, we design a Placement Generator module to yield finite subspaces as placement candidates and the representation of the bin. Second, we propose a Packing Transformer, which fuses the features of the items and bin, to identify the spatial correlation between the item to be packed and available sub-spaces within the bin. Coupling these two components enables GOPT's ability to perform inference on bins of varying dimensions. We conduct extensive experiments and demonstrate that GOPT not only achieves superior performance against the baselines, but also exhibits excellent generalization capabilities. Furthermore, the deployment with a robot showcases the practical applicability of our method in the real world. The source code will be publicly available at https://github.com/Xiong5Heng/GOPT.

cs.RO↗

arXiv2024

Study of a Novel Capacitive Pressure Sensor Using Spiral Comb Electrodes

For traditional capacitive pressure sensors, high nonlinearity and poor sensitivity greatly limited their sensing applications. Hence, an innovative design of capacitors based on spiral comb electrodes is proposed for high-sensitivity pressure detection in this work. Compared to traditional capacitive pressure sensors with straight plate electrodes, the proposed sensor with the spiral electrodes increases the overlap areas of electrodes sufficiently, the pressure sensitivity can thus be greatly improved. Moreover, the capacitance variation of the proposed sensor is dominated by the change of the overlap area of the electrodes rather than the electrode's distance, the linearity can also thus be improved to higher than 0.99. Theoretical analysis and COMSOL-based finite element simulation have been implemented for principle verification and performance optimization. Simulation results show that the proposed design has a mechanical sensitivity of 1.5x10-4 m/Pa, capacitive sensitivity of 1.10 aF/Pa, and nonlinear error of 3.63%, respectively, at the pressure range from 0 to 30 kPa. An equivalent experiment has been further carried out for verification. Experimental results also show that both the sensitivity and linearity of capacitive pressure sensors with spiral electrodes are higher than those with straight electrodes. This work not only provides a new avenue for capacitor design, but also can be applied to high-sensitivity pressure detection.

physics.app-ph↗