arXiv subjects

Mengjie Zhang

Publications and source records attributed to Mengjie Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

HeatACO: A Heatmap-Guided Max--Min Ant System for Large-Scale Travelling Salesman Problems

Non-autoregressive neural solvers predict an edge-confidence heatmap for the Travelling Salesman Problem (TSP) in one forward pass, but a decoder must still produce a feasible Hamiltonian cycle. As instance size grows, this stage must reconcile a quadratic number of edge scores with global tour constraints. Greedy edge merging is fast and deterministic but produces low-quality tours, whereas Monte Carlo Tree Search (MCTS) over k-opt moves recovers better tours at high computational cost and requires predictor-specific tuning. We propose HeatACO, a predictor-agnostic heatmap-to-tour decoder. Its key is a capped, degree-aware evidence factor that integrates a fixed heatmap into a Max--Min Ant System (MMAS). The factor rewards only edge confidence beyond a node's tour-degree capacity, and its strength is scaled automatically from the pheromone dynamic range, allowing one configuration to decode heatmaps from different predictors without retraining or per-predictor tuning. Across four heatmap sources, HeatACO produces higher-quality solutions in less decoding time than the MCTS baseline on TSP500, TSP1K and TSP10K. Against matched standard MMAS baselines with the same search budget, heatmap guidance improves construction for all four predictors at both scales and remains beneficial with local search. HeatACO also transfers competitively to several distribution shifts and the asymmetric TSP (ATSP). Our post-hoc analysis identifies measurable heatmap properties associated with the observed performance variation.

cs.NE↗

arXiv2026

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models

On-Policy Self-Distillation (OPSD) uses privileged information available only to the teacher to provide dense token-level supervision on trajectories generated by the student. However, existing methods often rely on verified solution traces, explanations generated by external models, or manually localized visual evidence, which limits their scalable application to multimodal large language models. To address this issue, we exploit the information gap between high- and low-resolution views of the same image and propose RP-OPSD (Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models). During training, the student policy generates on-policy trajectories from images at one-quarter of the original resolution, while the teacher policy provides supervision using the original-resolution images. By minimizing the divergence between their output distributions along the student trajectories, the student learns the predictive behavior of the teacher under high-resolution inputs, thereby strengthening its low-resolution capability and transferring the learned improvement to original-resolution inference. RP-OPSD requires neither additional human annotations nor external models to generate solution traces but only image--question pairs. Experiments on Qwen3.5-9B show that RP-OPSD achieves a 5.45\% relative improvement in average performance at the original resolution and a $1.78\times$ training speedup over OPSD. These results demonstrate that resolution differences can serve as a simple and scalable source of privileged information, providing an effective and efficient approach to on-policy self-distillation for multimodal large language models.

cs.CV↗

arXiv2026

Benchmarking Zero-Shot LLM-Generated Parent Selection in Genetic Programming for Symbolic Regression

Parent selection significantly affects exploration, exploitation, and complexity control in genetic programming (GP) for symbolic regression. It is unclear whether large language models (LLMs) can synthesize effective operators in a zero-shot setting without iterative meta-evolution. Here, zero-shot means that the model receives only the task description, with no reference operators or iterative feedback. In this work, we benchmark zero-shot synthesis of parent-selection operators across eight LLMs within a standard GP framework for symbolic regression. Each model receives the same natural-language prompt to generate a parent-selection operator, which is then evaluated in a standard GP framework with only the parent-selection operator replaced, while all other components and the evolutionary-search budget are held constant. For each LLM, ten independent zero-shot operators are evaluated on twelve OpenML regression benchmarks and compared against automatic lexicase and tournament selection baselines. Claude Sonnet~4.6 and Gemini~3.1 Pro stand out for consistently strong performance on both training and held-out test $R^2$. The strongest operator in our benchmark---a Kimi~K2.5 zero-shot synthesis---surpasses the automatic lexicase and tournament baselines in search effectiveness. These results suggest that zero-shot LLM synthesis is a viable approach to generating competitive GP selection operators. Analysis shows that many generated operators use semantics to guide selection, suggesting that LLMs can produce non-trivial search heuristics from the task description alone. We also examine the relationship between public LLM leaderboard rankings and GP performance. Widely used benchmarks, such as Humanity's Last Exam and SWE-bench Verified, strongly correlate with training $R^2$, while their relationship to held-out test $R^2$ is weaker and less clear.

cs.NE↗

arXiv2026

Search Hardness-Aware LLM-Based Problem Formulation for Expensive Simulation-Driven Design

Expensive simulation-driven design is widely used in engineering to identify requirement-satisfying designs with as few high-fidelity simulations as possible. Most existing efforts address this challenge by improving optimization algorithms under fixed formulations, yet the formulation itself shapes the search landscape by defining the objectives and constraints optimized by the solver. Recent LLM-based automatic problem formulation methods generate formulations from natural-language requirements, but they mainly focus on design-intent alignment and overlook whether the formulation induces an efficient search process. To address this limitation, we propose SHA-PF, a search hardness-aware LLM-based problem formulation framework. We find that a formulation is more likely to guide efficient search when it prioritizes rare samples with greater progress potential. Based on this finding, SHA-PF defines a formulation search objective guided by search hardness, scoring each candidate formulation according to the priority. SHA-PF then searches the formulation space under this objective through LLM-based generation, repair, and evolutionary refinement. Experiments on the real-world multi-objective benchmark and five expensive antenna design benchmarks show that the formulations discovered by SHA-PF require significantly fewer evaluations to reach the design requirements than other baselines.

cs.NE↗

arXiv2026

Neural Architecture Distributions: A New Paradigm for Stochastic Segmentation

Stochastic segmentation seeks to represent multiple plausible masks for a single image, which is essential in safety- and quality-critical applications such as medical imaging or building defect inspection. Most existing methods introduce stochasticity by injecting continuous latent variables or by iterative denoising trajectories, whose stochastic sources are difficult to search or audit directly. We propose architecture distributions as a new stochastic source for segmentation: instead of sampling a latent variable or noise, we sample a discrete architecture from a learned distribution over operator choices at multiple searchable positions in a segmentation backbone. Each sampled architecture yields one mask through the selected active path, so inference depends on the executed subnet rather than the complete candidate bank. This approach also supports architectural provenance, since each output corresponds to a specific architecture configuration. To reduce collapse toward averaged masks, we train with set-level supervision by matching a set of architecture-sampled predictions to the annotation set using an IoU-based energy-distance surrogate. We further construct the candidate bank with evolutionary search, making the support of the stochastic source optimizable before distribution learning. The proposed method achieves state-of-the-art distribution matching and hypothesis coverage on LIDC-IDRI, and remains effective on two extension tasks. To the best of our knowledge, this is the first work to formulate stochastic segmentation as learning an architecture distribution and realizing output diversity through architecture sampling.

cs.CV↗

arXiv2026

Machine Learning-based Two-Stage Graph Sparsification for the Travelling Salesman Problem

High-performance TSP solvers such as Lin-Kernighan-Helsgaun (LKH) search within a \emph{candidate graph} -- a small subset of edges pre-selected for the solver -- rather than over the complete graph. The two leading sparsification heuristics, $α$-Nearest and POPMUSIC, each fall short of the density-coverage balance: $α$-Nearest is dense with stable recall, while POPMUSIC is sparser but its recall degrades with scale. Their union closes the recall gap while remaining far below the complete graph in density, leaving room for further reduction. Existing learning-based sparsifiers score edges on the complete graph, an approach that is expensive and largely limited to Euclidean instances. We propose a two-stage method that inverts this logic. Stage~1 takes the union of $α$-Nearest and POPMUSIC, achieving near-perfect recall at ${\sim}6N$ edges. Crucially, the union annotates each edge with its \emph{source provenance} -- whether it was endorsed by $α$-Nearest, POPMUSIC, or both. Stage~2 trains a lightweight classifier on these annotated edges and prunes the lowest-scoring ones. Because dual-source edges are almost always optimal, the learning problem reduces to filtering the single-source subset -- a substantially easier task than classifying all $O(N^2)$ edges from scratch. Across four distance types, five spatial distributions, and problem sizes from 50 to 500, the pipeline reduces candidate-graph density by $37$-$47\%$ while retaining ${\geq}99.69\%$ of optimal-tour edges, and matches or exceeds the coverage of recent Euclidean-only neural sparsifiers at lower density at TSP500.

cs.LG↗

arXiv2026

Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts

Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources. However, existing deep reinforcement learning (DRL) schedulers remain limited by rigid, single-path inference architectures that struggle to handle diverse scheduling scenarios. We introduce $\textbf{DEFT}$ ($\textbf{D}$eadline-p$\textbf{E}$rceptive Mixture-o$\textbf{F}$-Exper$\textbf{t}$s), an innovative DRL policy architecture that leverages a specialized mixture of experts, each trained to manage different levels of deadline tightness. To our knowledge, DEFT is the first to introduce and validate a Mixture-of-Experts architecture for dynamic cloud workflow scheduling. By adaptively routing decisions through the most appropriate experts, DEFT is capable of meeting a broad spectrum of deadline requirements that no single expert can achieve. Central to DEFT is a $\textbf{graph-adaptive}$ gating mechanism that encodes workflow DAGs, task states, and VM conditions, using cross-attention to guide expert activation in a fine-grained, deadline-sensitive manner. Experiments on dynamic cloud workflow benchmarks demonstrate that DEFT significantly reduces execution cost and deadline violations, outperforming multiple state-of-the-art DRL baselines.

cs.AI↗

arXiv2026

AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization

Expensive optimization tasks are ubiquitous in real-world applications, demanding highly specialized solvers. While LLM-driven automated solver generation shows promise, current paradigms face three critical issues when tackling expensive optimization: factual hallucinations due to deficient domain knowledge, the frequent dismantling of previously established locally optimal structures during refinement, and the prohibitive evaluation costs alongside restricted generalization caused by executing on training instances. To address these issues, we introduce AutoSG, a fully automated workflow directly translating natural language prompts into executable customized solvers. AutoSG features three core innovations: a retrieval-augmented solver generation module strictly grounding code in verified literature; a one-step self-refinement operator introducing task-specific improvements while preserving critical structural components; and an instance-free Elo-based LLM-as-a-Judge evaluation mechanism rapidly establishing global rankings. Extensive evaluations across diverse expensive optimization tasks confirm AutoSG significantly outperforms human-designed state-of-the-art frameworks and existing LLM-generated solvers.

cs.CL↗

arXiv2026

Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks

Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficient training on each task. Both settings overlook a common real-world property: problem patterns may drift continually over time, yielding massive tasks sequentially arising, each with only limited training resources. In this paper, we propose a novel lifelong learning paradigm for neural VRP solvers under continual task drift over time, where each task is locally stationary at one learning time step but receives only insufficient training resources. We empirically demonstrate that such continual drift arises in practice using a real-world logistics dataset. We then propose Dual Replay with Experience Enhancement (DREE), a general framework to improve learning efficiency and mitigate catastrophic forgetting under such drift. Extensive experiments based on both the real-world logistics dataset and commonly used synthetic dataset show that, under such continual drift, DREE effectively learns new tasks, preserves prior knowledge, improves generalization to unseen tasks, and can be applied to various existing neural solvers.

cs.LG↗

arXiv2026

Low-Cost Stereo Vision for Robust 3D Positioning of Thin Radiata Pine Branches in Autonomous Drone Pruning

Manual pruning of radiata pine, a species of major economic importance to New Zealand forestry, is hazardous, labour-intensive, and increasingly constrained by workforce shortages. Existing autonomous pruning platforms typically rely on expensive sensors such as LiDAR and are limited to thick branches, which restricts their wider adoption. This paper investigates whether a single low-cost stereo camera mounted on a drone can provide sufficiently accurate branch detection and three-dimensional positioning to support autonomous pruning of branches as thin as 10 mm, thereby removing the need for auxiliary depth sensors. The proposed pipeline comprises two stages: branch segmentation and depth estimation. For segmentation, Mask R-CNN variants and the YOLOv8 and YOLOv9 families are compared on a custom dataset of 71 stereo image pairs captured with a ZED Mini camera; YOLOv8 and YOLOv9 are selected as representative state-of-the-art real-time segmentors at the time of data collection, and the framework is designed to remain compatible with newer YOLO releases. For depth estimation, a traditional method (SGBM with WLS filtering) and deep-learning-based methods (PSMNet, ACVNet, GWCNet, MobileStereoNet, RAFT-Stereo, and NeRF-Supervised Deep Stereo) are evaluated, including cross-dataset fine-tuning experiments that expose the domain gap between urban driving benchmarks and natural forestry scenes. The main novelty of this work lies in coupling stereo segmentation with a centroid-based triangulation algorithm and Median-Absolute-Deviation outlier rejection that converts a segmentation mask and disparity map into a single robust branch-to-camera distance, addressing the challenges of sparse texture, thin structures, and noisy disparity values typical of forest scenes. Qualitative evaluations at distances of 1-2 m show that the learning-based stereo methods produce more coherent depth es...

cs.CV↗

arXiv2026

Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design

In the high-cost simulation-driven design domain, translating ambiguous design requirements into a mathematical optimization formulation is a bottleneck for optimizing product performance. This process is time-consuming and heavily reliant on expert knowledge. While large language models (LLMs) offer potential for automating this task, existing approaches either suffer from poor formalization that fails to accurately align with the design intent or rely on solver feedback for data filtering, which is unavailable due to the high simulation costs. To address this challenge, we propose APF, a framework for solver-independent, automated problem formulation via LLMs designed to automatically convert engineers' natural language requirements into executable optimization models. The core of this framework is an innovative pipeline for automatically generating high-quality data, which overcomes the difficulty of constructing suitable fine-tuning datasets in the absence of high-cost solver feedback with the help of data generation and test instance annotation. The generated high-quality dataset is used to perform supervised fine-tuning on LLMs, significantly enhancing their ability to generate accurate and executable optimization problem formulations. Experimental results on antenna design demonstrate that APF significantly outperforms the existing methods in both the accuracy of requirement formalization and the quality of resulting radiation efficiency curves in meeting the design goals.

cs.CL↗

arXiv2026

Positioning radiata pine branches requiring pruning by drone stereo vision

This paper presents a stereo-vision-based system mounted on a drone for detecting and localising radiata pine branches to support autonomous pruning. The proposed pipeline comprises two stages: branch segmentation and depth estimation. For segmentation, YOLOv8, YOLOv9, and Mask R-CNN variants are compared on a custom dataset of 71 stereo image pairs captured with a ZED Mini camera. For depth estimation, both a traditional method (SGBM with WLS filtering) and deep-learning-based methods (PSMNet, ACVNet, GWCNet, MobileStereoNet, RAFT-Stereo, and NeRF-Supervised Deep Stereo) are evaluated. A centroid-based triangulation algorithm with MAD outlier rejection is proposed to compute branch distance from the segmentation mask and disparity map. Qualitative evaluation at distances of 1-2 m indicates that the deep learning-based disparity maps produce more coherent depth estimates than SGBM, demonstrating the feasibility of low-cost stereo vision for automated branch positioning in forestry.

cs.CV↗

arXiv2026

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models

In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time or resource-constrained applications. Visual token pruning is a promising strategy for reducing the cost of MLLM inference by removing redundant visual tokens. Existing research usually assumes that all attention heads contribute equally to the visual interpretation. However, our study reveals that different heads may capture distinct visual semantics and inherently play distinct roles in visual processing. In light of this observation, we propose HAWK, a head importance-aware visual token pruning method that perceives the varying importance of attention heads in visual tasks to maximize the retention of crucial tokens. By leveraging head importance weights and text-guided attention to assess visual token significance, HAWK effectively retains task-relevant visual tokens while removing redundant ones. The proposed HAWK is entirely training-free and can be seamlessly applied to various MLLMs. Extensive experiments on multiple mainstream vision-language benchmarks demonstrate that HAWK achieves state-of-the-art accuracy. When applied to Qwen2.5-VL, HAWK retains 96.0% of the original accuracy after pruning 80.2% of the visual tokens. Additionally, it reduces end-to-end latency to 74.4% of the original and further decreases GPU memory usage across the tested models. The code is available at https://github.com/peppery77/HAWK.git.

cs.CV↗

arXiv2026

LLM-Meta-SR: In-Context Learning for Evolving Selection Operators in Symbolic Regression

Large language models (LLMs) have revolutionized algorithm development, yet their application in symbolic regression, where algorithms automatically discover symbolic expressions from data, remains limited. In this paper, we propose a meta-learning framework that enables LLMs to automatically design selection operators for evolutionary symbolic regression algorithms. We first identify two key limitations in existing LLM-based algorithm evolution techniques: lack of semantic guidance and code bloat. The absence of semantic awareness can lead to ineffective exchange of useful code components, while bloat results in unnecessarily complex components; both can hinder evolutionary learning progress or reduce the interpretability of the designed algorithm. To address these issues, we enhance the LLM-based evolution framework for meta-symbolic regression with two key innovations: a complementary, semantics-aware selection operator and bloat control. Additionally, we embed domain knowledge into the prompt, enabling the LLM to generate more effective and contextually relevant selection operators. Our experimental results on symbolic regression benchmarks show that LLMs can devise selection operators that outperform nine expert-designed baselines, achieving state-of-the-art performance. Moreover, the evolved operator can further improve a state-of-the-art symbolic regression algorithm, achieving the best performance among 28 symbolic regression and other machine learning algorithms across 116 regression datasets. This demonstrates that LLMs can exceed expert-level algorithm design for symbolic regression.

cs.NE↗

arXiv2026

UE5-Forest: A Photorealistic Synthetic Stereo Dataset for UAV Forestry Depth Estimation

Dense ground-truth disparity maps are practically unobtainable in forestry environments, where thin overlapping branches and complex canopy geometry defeat conventional depth sensors -- a critical bottleneck for training supervised stereo matching networks for autonomous UAV-based pruning. We present UE5-Forest, a photorealistic synthetic stereo dataset built entirely in Unreal Engine 5 (UE5). One hundred and fifteen photogrammetry-scanned trees from the Quixel Megascans library are placed in virtual scenes and captured by a simulated stereo rig whose intrinsics -- 63 mm baseline, 2.8 mm focal length, 3.84 mm sensor width -- replicate the ZED Mini camera mounted on our drone. Orbiting each tree at up to 2 m across three elevation bands (horizontal, +45 degrees, -45 degrees) yields 5,520 rectified 1920 x 1080 stereo pairs with pixel-perfect disparity labels. We provide a statistical characterisation of the dataset -- covering disparity distributions, scene diversity, and visual fidelity -- and a qualitative comparison with real-world Canterbury Tree Branches imagery that confirms the photorealistic quality and geometric plausibility of the rendered data. The dataset will be publicly released to provide the community with a ready-to-use benchmark and training resource for stereo-based forestry depth estimation.

cs.CV↗

arXiv2026

Real-Time Branch-to-Tool Distance Estimation for Autonomous UAV Pruning: Benchmarking Five DEFOM-Stereo Variants from Simulation to Jetson Deployment

Autonomous tree pruning with unmanned aerial vehicles (UAVs) is a safety-critical real-world task: the onboard perception system must estimate the metric distance from a cutting tool to thin tree branches in real time so that the UAV can approach, align, and actuate the pruner without collision. We address this problem by training five variants of DEFOM-Stereo - a recent foundation-model-based stereo matcher - on a task-specific synthetic dataset and deploying the checkpoints on an NVIDIA Jetson Orin Super 16 GB. The training corpus is built in Unreal Engine 5 with a simulated ZED Mini stereo camera capturing 5,520 stereo pairs across 115 tree instances from three viewpoints at 2m distance; dense EXR depth maps provide exact, spatially complete supervision for thin branches. On the synthetic test set, DEFOM-Stereo ViT-S achieves the best depth-domain accuracy (EPE 1.74 px, D1-all 5.81%, delta-1 95.90%, depth MAE 23.40 cm) but its Jetson inference speed of ~2.2 FPS (~450 ms per frame) remains too slow for responsive closed-loop tool control. A newly introduced balanced variant, DEFOM-PrunePlus (~21M backbone, ~3.3 FPS on Jetson), offers the best deployable accuracy-speed trade-off (EPE 5.87 px, depth MAE 64.26 cm, delta-1 87.59%): its frame rate is sufficient for real-time guidance and its depth accuracy supports safe branch approach planning at the 2m operating range. The lightweight DEFOM-PruneStereo (~6.9 FPS) and DEFOM-PruneNano (~8.5 FPS) run fast but sacrifice substantial accuracy (depth MAE > 57 cm), making estimates too unreliable for safe actuation. Zero-shot inference on real photographs confirms that full-capacity models preserve branch geometry, validating the sim-to-real transfer. We conclude that DEFOM-PrunePlus provides the most practical accuracy-latency balance for onboard distance estimation, while ViT-S serves as the reference for future hardware.

cs.CV↗

arXiv2026

Surrogate-Assisted Genetic Programming with Rank-Based Phenotypic Characterisation for Dynamic Multi-Mode Project Scheduling

The dynamic multi-mode resource-constrained project scheduling problem (DMRCPSP) is of practical importance, as it requires making real-time decisions under changing project states and resource availability. Genetic Programming (GP) has been shown to effectively evolve heuristic rules for such decision-making tasks; however, the evolutionary process typically relies on a large number of simulation-based fitness evaluations, resulting in high computational cost. Surrogate models offer a promising solution to reduce evaluation cost, but their application to GP requires problem-specific phenotypic characterisation (PC) schemes of heuristic rules. There is currently a lack of suitable PC schemes for GP applied to DMRCPSP. This paper proposes a rank-based PC scheme derived from heuristic-driven ordering of eligible activity-mode pairs and activity groups in decision situations. The resulting PC vectors enable a surrogate model to estimate the fitness of unevaluated GP individuals. Based on this scheme, a surrogate-assisted GP algorithm is developed. Experimental results demonstrate that the proposed surrogate-assisted GP can identify high-quality heuristic rules consistently earlier than the state-of-the-art GP approach for DMRCPSP, while introducing only marginal computational overhead. Further analyses demonstrate that the surrogate model provides useful guidance for offspring selection, leading to improved evolutionary efficiency.

cs.NE↗

arXiv2026

Progressive Per-Branch Depth Optimization for DEFOM-Stereo and SAM3 Joint Analysis in UAV Forestry Applications

Accurate per-branch 3D reconstruction is a prerequisite for autonomous UAV-based tree pruning; however, dense disparity maps from modern stereo matchers often remain too noisy for individual branch analysis in complex forest canopies. This paper introduces a progressive pipeline integrating DEFOM-Stereo foundation-model disparity estimation, SAM3 instance segmentation, and multi-stage depth optimization to deliver robust per-branch point clouds. Starting from a naive baseline, we systematically identify and resolve three error families through successive refinements. Mask boundary contamination is first addressed through morphological erosion and subsequently refined via a skeleton-preserving variant to safeguard thin-branch topology. Segmentation inaccuracy is then mitigated using LAB-space Mahalanobis color validation coupled with cross-branch overlap arbitration. Finally, depth noise - the most persistent error source - is initially reduced by outlier removal and median filtering, before being superseded by a robust five-stage scheme comprising MAD global detection, spatial density consensus, local MAD filtering, RGB-guided filtering, and adaptive bilateral filtering. Evaluated on 1920x1080 stereo imagery of Radiata pine (Pinus radiata) acquired with a ZED Mini camera (63 mm baseline) from a UAV in Canterbury, New Zealand, the proposed pipeline reduces the average per-branch depth standard deviation by 82% while retaining edge fidelity. The result is geometrically coherent 3D point clouds suitable for autonomous pruning tool positioning. All code and processed data are publicly released to facilitate further UAV forestry research.

eess.IV↗