arXiv subjects

Zhibin Wu

Publications and source records attributed to Zhibin Wu.

8 recordsLinked to original sources

arXiv2026

DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning

Few-shot learning (FSL) aims to generalize to novel categories with only a few samples. Recent approaches incorporate large language models (LLMs) to enrich visual representations with semantic embeddings derived from class names. However, they overlook progressive and adaptive alignment between vision and language from low-level to high-level semantics, resulting in limited semantic gains. To address these challenges, we propose Dual-level Vision-Language Alignment with Reinforcement Learning gating (DVLA-RL), which consists of Dual-level Semantic Construction (DSC) and RL-gated Attention (RLA). Specifically, DSC conditions LLMs on both class names and support samples to generate discriminative attributes, progressively selects the most relevant ones, and then synthesizes them into coherent class descriptions. This process provides complementary low-level attributes and high-level descriptions, enabling both fine-grained grounding and holistic class understanding. To dynamically integrate dual-level semantics along with the visual network layers, RLA formulates cross-modal fusion as a sequential decision process. A lightweight policy trained with episodic REINFORCE adaptively adjusts the contributions of self-attention and cross-attention to integrate textual and visual tokens. As a result, shallow layers refine local attributes and deep layers emphasize global semantics, enabling more precise cross-modal alignment. This achieves class-specific discrimination and generalized representations with merely a few support samples. DVLA-RL achieves new state-of-the-art performance across nine benchmarks in three diverse FSL scenarios.

cs.CV↗

arXiv2026

Generalized Optimal Classification Trees: A Mixed-Integer Programming Approach

Global optimization of decision trees is a long-standing challenge in combinatorial optimization, yet such models play an important role in interpretable machine learning. Although the problem has been investigated for several decades, only recent advances in discrete optimization have enabled practical algorithms for solving optimal classification tree problems on real-world datasets. Mixed-integer programming (MIP) offers a high degree of modeling flexibility, and we therefore propose a MIP-based framework for learning optimal classification trees under nonlinear performance metrics, such as the F1-score, that explicitly addresses class imbalance. To improve scalability, we develop problem-specific acceleration techniques, including a tailored branch-and-cut algorithm, an instance-reduction scheme, and warm-start strategies. We evaluate the proposed approach on 50 benchmark datasets. The computational results show that the framework can efficiently optimize nonlinear metrics while achieving strong predictive performance and reduced solution times compared with existing methods.

cs.LG↗

arXiv2026

The Dynamic Team Orienteering Problem in Spatial Crowdsourcing: A Scenario Sampling Approach

In services such as retail audits and urban infrastructure monitoring, a platform dispatches rewarded, location-based micro-tasks to mobile workers traveling along personal origin-destination (OD) trips under hard time budgets. As requests with time constraints arrive online over a finite horizon, the platform must decide which requests to accept and how to route workers to maximize collected profit. We model this setting as the Dynamic Team Orienteering Problem in Spatial Crowdsourcing (DTOP-SC). To solve this problem, we propose a scenario-sampling rolling-horizon framework that mitigates myopic bias by augmenting each planning epoch with sampled virtual tasks. At each epoch, the augmented task set defines a deterministic static subproblem solved via an adaptive large neighborhood search (ALNS). We also formulate a mixed-integer programming model to provide offline reference solutions. Computational experiments are conducted on synthetic DTOP-SC instances generated from real-world road-map coordinates and on a dynamic team orienteering (DTOP) benchmark. On the map-based instances, the proposed policy exhibits stable gaps with respect to time-limited MIP solutions across the tested scales, while maintaining smooth computational scalability as the problem size increases. On the DTOP benchmark, the policy achieves an average decision time of 0.14s per instance, with 192-198s reported for multiple plan approach as an indicative reference, while maintaining competitive profit.

math.OC↗

arXiv2025

A survey of the orienteering problem: model evolution, algorithmic advances, and future directions

The orienteering problem (OP) is a combinatorial optimization problem that seeks a path visiting a subset of locations to maximize collected rewards under a limited resource budget. This article presents a systematic PRISMA-based review of OP research published between 2017 and 2025, with a focus on models and methods that have shaped subsequent developments in the field. We introduce a component-based taxonomy that decomposes OP variants into time-, path-, node-, structure-, and information-based extensions. This framework unifies classical and emerging variants -- including stochastic, time-dependent, Dubins, Set, and multi-period OPs -- within a single structural perspective. We further categorize solution approaches into exact algorithms, heuristics and metaheuristics, and learning-based methods, with particular emphasis on matheuristics and recent advances in artificial intelligence, especially reinforcement learning and neural networks, which enhance scalability in large-scale and information-rich settings. Building on this unified view, we discuss how different components affect computational complexity and polyhedral properties and identify open challenges related to robustness, sustainability, and AI integration. The survey thus provides both a consolidated reference for existing OP research and a structured agenda for future theoretical and applied work.

math.OC↗

arXiv2025

VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning

Few-shot learning (FSL) aims to recognize novel concepts from only a few labeled support samples. Recent studies enhance support features by incorporating additional semantic information or designing complex semantic fusion modules. However, they still suffer from hallucinating semantics that contradict the visual evidence due to the lack of grounding in actual instances, resulting in noisy guidance and costly corrections. To address these issues, we propose a novel framework, bridging Vision and Text with LLMs for Few-Shot Learning (VT-FSL), which constructs precise cross-modal prompts conditioned on Large Language Models (LLMs) and support images, seamlessly integrating them through a geometry-aware alignment. It mainly consists of Cross-modal Iterative Prompting (CIP) and Cross-modal Geometric Alignment (CGA). Specifically, the CIP conditions an LLM on both class names and support images to generate precise class descriptions iteratively in a single structured reasoning pass. These descriptions not only enrich the semantic understanding of novel classes but also enable the zero-shot synthesis of semantically consistent images. The descriptions and synthetic images act respectively as complementary textual and visual prompts, providing high-level class semantics and low-level intra-class diversity to compensate for limited support data. Furthermore, the CGA jointly aligns the fused textual, support, and synthetic visual representations by minimizing the kernelized volume of the 3-dimensional parallelotope they span. It captures global and nonlinear relationships among all representations, enabling structured and consistent multimodal integration. The proposed VT-FSL method establishes new state-of-the-art performance across ten diverse benchmarks, including standard, cross-domain, and fine-grained few-shot learning scenarios. Code is available at https://github.com/peacelwh/VT-FSL.

cs.CV↗

arXiv2025

A Survey on Progress in LLM Alignment from the Perspective of Reward Design

Reward design plays a pivotal role in aligning large language models (LLMs) with human values, serving as the bridge between feedback signals and model optimization. This survey provides a structured organization of reward modeling and addresses three key aspects: mathematical formulation, construction practices, and interaction with optimization paradigms. Building on this, it develops a macro-level taxonomy that characterizes reward mechanisms along complementary dimensions, thereby offering both conceptual clarity and practical guidance for alignment research. The progression of LLM alignment can be understood as a continuous refinement of reward design strategies, with recent developments highlighting paradigm shifts from reinforcement learning (RL)-based to RL-free optimization and from single-task to multi-objective and complex settings.

cs.CL↗

arXiv2024

BooleanOCT: Optimal Classification Trees based on multivariate Boolean Rules

The global optimization of classification trees has demonstrated considerable promise, notably in enhancing accuracy, optimizing size, and thereby improving human comprehensibility. While existing optimal classification trees substantially enhance accuracy over greedy-based tree models like CART, they still fall short when compared to the more complex black-box models, such as random forests. To bridge this gap, we introduce a new mixed-integer programming (MIP) formulation, grounded in multivariate Boolean rules, to derive the optimal classification tree. Our methodology integrates both linear metrics, including accuracy, balanced accuracy, and cost-sensitive cost, as well as nonlinear metrics such as the F1-score. The approach is implemented in an open-source Python package named BooleanOCT. We comprehensively benchmark these methods on the 36 datasets from the UCI machine learning repository. The proposed models demonstrate practical solvability on real-world datasets, effectively handling sizes in the tens of thousands. Aiming to maximize accuracy, this model achieves an average absolute improvement of 3.1\% and 1.5\% over random forests in small-scale and medium-sized datasets, respectively. Experiments targeting various objectives, including balanced accuracy, cost-sensitive cost, and F1-score, demonstrate the framework's wide applicability and its superiority over contemporary state-of-the-art optimal classification tree methods in small to medium-scale datasets.

cs.LG↗

arXiv2019

Privacy protection of occupant behavior data and using blockchain for securely transferring temperature records in HVAC systems

The proportion of Energy consumption in the building industry is great, as well as the amount of cooling and heating system. Scholars have been working on energy conservation of Heating, ventilation, and air-conditioning and other systems in buildings. The application of occupant behavior data for building energy optimization has started gaining attention from scholars. However, occupant behavior data concerns many aspects of occupants' privacy. Different types of occupant behavior data contain occupants' private information to different levels. It is crucial to conduct privacy protection of occupant behavior data when using occupant behavior for energy conservation. This paper presents the aspects of privacy issue when using occupant behavior data, and methods to protect data privacy with blockchain technology. Both two options of using blockchain for privacy protection, sending data records as transactions and storing files on the blockchain, are explained and evaluated with temperature records from an open access paper. Sending data as transactions can be used between sensors and local building management system. While storing files on blockchain can be used for collaboration of different building management systems. Advantages, drawbacks, and potentials of using blockchain for data and file transfer are discussed. The results should be helpful for using occupant behavior data for building energy optimization.

cs.CR↗