arXiv subjects

Yi Zhang

Publications and source records attributed to Yi Zhang.

At least 505 records · Page 28Linked to original sources

arXiv2025

Joint Optimization of Service Routing and Scheduling in Home Health Care

The growing aging population has significantly increased demand for efficient home health care (HHC) services. This study introduces a Vehicle Routing and Appointment Scheduling Problem (VRASP) to simultaneously optimize caregiver routes and appointment times, minimizing costs while improving service quality. We first develop a deterministic VRASP model and then extend it to a stochastic version using sample average approximation to account for travel and service time uncertainty. A tailored Variable Neighborhood Search (VNS) heuristic is proposed, combining regret-based insertion and Tabu Search to efficiently solve both problem variants. Computational experiments show that the stochastic model outperforms the deterministic approach, while VNS achieves near-optimal solutions for small instances and demonstrates superior scalability for larger problems compared to CPLEX. This work provides HHC providers with a practical decision-making tool to enhance operational efficiency under uncertainty.

math.OC↗

arXiv2025

RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs

The rapid advancement of native multi-modal models and omni-models, exemplified by GPT-4o, Gemini, and o3, with their capability to process and generate content across modalities such as text and images, marks a significant milestone in the evolution of intelligence. Systematic evaluation of their multi-modal output capabilities in visual thinking processes (also known as multi-modal chain of thought, M-CoT) becomes critically important. However, existing benchmarks for evaluating multi-modal models primarily focus on assessing multi-modal inputs and text-only reasoning while neglecting the importance of reasoning through multi-modal outputs. In this paper, we present a benchmark, dubbed RBench-V, designed to assess models' vision-indispensable reasoning abilities. To construct RBench-V, we carefully hand-pick 803 questions covering math, physics, counting, and games. Unlike previous benchmarks that typically specify certain input modalities, RBench-V presents problems centered on multi-modal outputs, which require image manipulation such as generating novel images and constructing auxiliary lines to support the reasoning process. We evaluate numerous open- and closed-source models on RBench-V, including o3, Gemini 2.5 Pro, Qwen2.5-VL, etc. Even the best-performing model, o3, achieves only 25.8% accuracy on RBench-V, far below the human score of 82.3%, highlighting that current models struggle to leverage multi-modal reasoning. Data and code are available at https://evalmodels.github.io/rbenchv

cs.CV↗

arXiv2025

Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression Recognition

In this paper, we proposed a Multi-modal Collaborative Optimization and Expansion Network (MCO-E Net), to use event modalities to resist challenges such as low light, high exposure, and high dynamic range in single-eye expression recognition tasks. The MCO-E Net introduces two innovative designs: Multi-modal Collaborative Optimization Mamba (MCO-Mamba) and Heterogeneous Collaborative and Expansion Mixture-of-Experts (HCE-MoE). MCO-Mamba, building upon Mamba, leverages dual-modal information to jointly optimize the model, facilitating collaborative interaction and fusion of modal semantics. This approach encourages the model to balance the learning of both modalities and harness their respective strengths. HCE-MoE, on the other hand, employs a dynamic routing mechanism to distribute structurally varied experts (deep, attention, and focal), fostering collaborative learning of complementary semantics. This heterogeneous architecture systematically integrates diverse feature extraction paradigms to comprehensively capture expression semantics. Extensive experiments demonstrate that our proposed network achieves competitive performance in the task of single-eye expression recognition, especially under poor lighting conditions.

cs.CV↗

arXiv2025

Distributionally enhanced marginal sensitivity model and bounds

For sensitivity analysis against unmeasured confounding, we build on the marginal sensitivity model (MSM) and propose a new model, deMSM, by incorporating a second constraint on the shift of potential outcome distributions caused by unmeasured confounders in addition to the constraint on the shift of treatment probabilities. We show that deMSM leads to interpretable sharp bounds of common causal parameters and tightens the corresponding MSM bounds. Moreover, the sharp bounds are symmetric in the two deMSM constraints, which facilitates practical applications. Lastly, we compare deMSM with other MSM-related models in both model constraints and sharp bounds, and reveal new interpretations for later models.

stat.ME↗

arXiv2025

Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation

While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks and apply them in future contexts. To address this limitation, we propose a novel framework, log-augmented generation (LAG) that directly reuses prior computation and reasoning from past logs at test time to enhance model's ability to learn from previous tasks and perform better on new, unseen challenges, all while keeping the system efficient and scalable. Specifically, our system represents task logs using key-value (KV) caches, encoding the full reasoning context of prior tasks while storing KV caches for only a selected subset of tokens. When a new task arises, LAG retrieves the KV values from relevant logs to augment generation. Our approach differs from reflection-based memory mechanisms by directly reusing prior reasoning and computations without requiring additional steps for knowledge extraction or distillation. Our method also goes beyond existing KV caching techniques, which primarily target efficiency gains rather than improving accuracy. Experiments on knowledge- and reasoning-intensive datasets demonstrate that our method significantly outperforms standard agentic systems that do not utilize logs, as well as existing solutions based on reflection and KV cache techniques.

cs.CL↗

arXiv2025

Decoupled structure-preserving discretization of incompressible MHD equations with general boundary conditions

In the framework of a mixed finite element method, a structure-preserving formulation for incompressible magnetohydrodynamic (MHD) equations with general boundary conditions is proposed. A leapfrog-type temporal scheme fully decouples the fluid part from the Maxwell part by means of staggered discrete time sequences and, in doing so, partially linearizes the system. Conservation and dissipation properties of the formulation before and after the decoupling are analyzed. We demonstrate optimal spatial and second-order temporal accuracy, as well as conservation and dissipation properties, of the proposed method using manufactured solutions, and apply it to the benchmark Orszag-Tang and lid-driven cavity cases.

math.NA↗

arXiv2025

Josephson diodes induced by the loop current states

We study the diode effect of the supercurrent in the Josephson junctions with the loop current states as the tunneling barrier. The loop current states are realized by the Haldane model which preserves the inversion symmetry and thus forbids the diode effect. We demonstrate how the inversion symmetry can be broken in the monolayer and bilayer systems. In the monolayer system, inversion symmetry can be broken by either introducing a sublattice staggered potential for the Haldane model or introducing a modified Haldane model, and in the bilayer system, it can be broken by either staking the two layers with opposite current directions or by directly applying an electric field perpendicular to the layers. We further show that the diode efficiency can be tuned by the interlayer coupling and the strength of the electric field or interlayer voltage. Our results provide another route to realize the Josephson diode effect by breaking the time-reversal symmetry through the loop-current states.

cond-mat.supr-con↗

arXiv2025

A super-resolution reconstruction method for lightweight building images based on an expanding feature modulation network

This study proposes a lightweight method for building image super-resolution using a Dilated Contextual Feature Modulation Network (DCFMN). The process includes obtaining high-resolution images, down-sampling them to low-resolution, enhancing the low-resolution images, constructing and training a lightweight network model, and generating super-resolution outputs. To address challenges such as regular textures and long-range dependencies in building images, the DCFMN integrates an expansion separable modulation unit and a local feature enhancement module. The former employs multiple expansion convolutions equivalent to a large kernel to efficiently aggregate multi-scale features while leveraging a simple attention mechanism for adaptivity. The latter encodes local features, mixes channel information, and ensures no additional computational burden during inference through reparameterization. This approach effectively resolves the limitations of existing lightweight super-resolution networks in modeling long-range dependencies, achieving accurate and efficient global feature modeling without increasing computational costs, and significantly improving both reconstruction quality and lightweight efficiency for building image super-resolution models.

cs.CV↗

arXiv2025

DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward

Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world models. However, the reward functions in these world models, trained on sparse offline logs, often suffer from inaccuracies. Specifically, existing methods face two major limitations in addressing this challenge: (1) deterministic use of reward functions as static look-up tables, which propagates inaccuracies during policy learning, and (2) static uncertainty designs that fail to effectively capture decision risks and mitigate the impact of these inaccuracies. In this work, a dual-agent framework, DARLR, is proposed to dynamically update world models to enhance recommendation policies. To achieve this, a \textbf{\textit{selector}} is introduced to identify reference users by balancing similarity and diversity so that the \textbf{\textit{recommender}} can aggregate information from these users and iteratively refine reward estimations for dynamic reward shaping. Further, the statistical features of the selected users guide the dynamic adaptation of an uncertainty penalty to better align with evolving recommendation requirements. Extensive experiments on four benchmark datasets demonstrate the superior performance of DARLR, validating its effectiveness. The code is available at https://github.com/ArronDZhang/DARLR.

cs.IR↗

arXiv2025

ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems

Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on model-based RL through learning a world model from offline data and building the recommendation policy by interacting with this model. Although these methods have made progress in the recommendation performance, the effectiveness of model-based offline RL methods is often constrained by the accuracy of the estimation of the reward model and the model uncertainties, primarily due to the extreme discrepancy between offline logged data and real-world data in user interactions with online platforms. To fill this gap, a more accurate reward model and uncertainty estimation are needed for the model-based RL methods. In this paper, a novel model-based Reward Shaping in Offline Reinforcement Learning for Recommender Systems, ROLeR, is proposed for reward and uncertainty estimation in recommendation systems. Specifically, a non-parametric reward shaping method is designed to refine the reward model. In addition, a flexible and more representative uncertainty penalty is designed to fit the needs of recommendation systems. Extensive experiments conducted on four benchmark datasets showcase that ROLeR achieves state-of-the-art performance compared with existing baselines. The source code can be downloaded at https://github.com/ArronDZhang/ROLeR.

cs.IR↗

arXiv2025

Generative-Contrastive Heterogeneous Graph Neural Network

Heterogeneous Graphs (HGs) effectively model complex relationships in the real world through multi-type nodes and edges. In recent years, inspired by self-supervised learning (SSL), contrastive learning (CL)-based Heterogeneous Graphs Neural Networks (HGNNs) have shown great potential in utilizing data augmentation and contrastive discriminators for downstream tasks. However, data augmentation remains limited due to the graph data's integrity. Furthermore, the contrastive discriminators suffer from sampling bias and lack local heterogeneous information. To tackle the above limitations, we propose a novel Generative-Contrastive Heterogeneous Graph Neural Network (GC-HGNN). Specifically, we propose a heterogeneous graph generative learning method that enhances CL-based paradigm. This paradigm includes: 1) A contrastive view augmentation strategy using a masked autoencoder. 2) Position-aware and semantics-aware positive sample sampling strategy for generating hard negative samples. 3) A hierarchical contrastive learning strategy aimed at capturing local and global information. Furthermore, the hierarchical contrastive learning and sampling strategies aim to constitute an enhanced contrastive discriminator under the generative-contrastive perspective. Finally, we compare our model with seventeen baselines on eight real-world datasets. Our model outperforms the latest baselines on node classification and link prediction tasks.

cs.LG↗

arXiv2025

R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation

Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmarks often fail to rigorously evaluate the nuanced reasoning capabilities required for complex, real-world problemsolving, particularly in multi-disciplinary and multimodal contexts. In this paper, we introduce a graduate-level, multi-disciplinary, EnglishChinese benchmark, dubbed as Reasoning Bench (R-Bench), for assessing the reasoning capability of both language and multimodal models. RBench spans 1,094 questions across 108 subjects for language model evaluation and 665 questions across 83 subjects for multimodal model testing in both English and Chinese. These questions are meticulously curated to ensure rigorous difficulty calibration, subject balance, and crosslinguistic alignment, enabling the assessment to be an Olympiad-level multi-disciplinary benchmark. We evaluate widely used models, including OpenAI o1, GPT-4o, DeepSeek-R1, etc. Experimental results indicate that advanced models perform poorly on complex reasoning, especially multimodal reasoning. Even the top-performing model OpenAI o1 achieves only 53.2% accuracy on our multimodal evaluation. Data and code are made publicly available at here.

cs.CV↗

arXiv2025

The electronic structure and disorder effect of La$_3$Ni$_2$O$_{7}$ superconductor

Determining the electronic structure of La$_3$Ni$_2$O$_7$ is an essential step towards uncovering their superconducting mechanism. It is widely believed that the bilayer apical oxygens play an important role in the bilayer La$_3$Ni$_2$O$_7$ electronic structure. Applying the hybrid exchange-correlation functionals, we obtain a more accurate electronic structure of La$_3$Ni$_2$O$_7$ at its high-pressure phase, where the binding $d_{z^2}$ band is below the Fermi level owing to apical oxygen. The symmetry properties of this electronic structure and its corresponding tight-binding model are further analyzed. We find the antisymmetric part is highly entangled leading to a minimal nearly degenerate two-orbital model. Then, the apical oxygen vacancies effect is studied using the dynamical cluster approximation. This disorder effect strongly destroys the antisymmetric $β$ Fermi surface leading to the possible disappearance of superconductivity.

cond-mat.supr-con↗

arXiv2025

Open Domain Question Answering with Conflicting Contexts

Open domain question answering systems frequently rely on information retrieved from large collections of text (such as the Web) to answer questions. However, such collections of text often contain conflicting information, and indiscriminately depending on this information may result in untruthful and inaccurate answers. To understand the gravity of this problem, we collect a human-annotated dataset, Question Answering with Conflicting Contexts (QACC), and find that as much as 25% of unambiguous, open domain questions can lead to conflicting contexts when retrieved using Google Search. We evaluate and benchmark three powerful Large Language Models (LLMs) with our dataset QACC and demonstrate their limitations in effectively addressing questions with conflicting information. To explore how humans reason through conflicting contexts, we request our annotators to provide explanations for their selections of correct answers. We demonstrate that by finetuning LLMs to explain their answers, we can introduce richer information into their training that guide them through the process of reasoning with conflicting contexts.

cs.CL↗

arXiv2025

Quadratic Interest Network for Multimodal Click-Through Rate Prediction

Multimodal click-through rate (CTR) prediction is a key technique in industrial recommender systems. It leverages heterogeneous modalities such as text, images, and behavioral logs to capture high-order feature interactions between users and items, thereby enhancing the system's understanding of user interests and its ability to predict click behavior. The primary challenge in this field lies in effectively utilizing the rich semantic information from multiple modalities while satisfying the low-latency requirements of online inference in real-world applications. To foster progress in this area, the Multimodal CTR Prediction Challenge Track of the WWW 2025 EReL@MIR Workshop formulates the problem into two tasks: (1) Task 1 of Multimodal Item Embedding: this task aims to explore multimodal information extraction and item representation learning methods that enhance recommendation tasks; and (2) Task 2 of Multimodal CTR Prediction: this task aims to explore what multimodal recommendation model can effectively leverage multimodal embedding features and achieve better performance. In this paper, we propose a novel model for Task 2, named Quadratic Interest Network (QIN) for Multimodal CTR Prediction. Specifically, QIN employs adaptive sparse target attention to extract multimodal user behavior features, and leverages Quadratic Neural Networks to capture high-order feature interactions. As a result, QIN achieved an AUC of 0.9798 on the leaderboard and ranked second in the competition. The model code, training logs, hyperparameter configurations, and checkpoints are available at https://github.com/salmon1802/QIN.

cs.IR↗

arXiv2025

Primal-dual programs for the constrained optimal impulse control: discounted model

This paper studies constrained optimal impulse control problems of a deterministic system described by a (semi)flow, where the performance measures are the discounted total costs including both the costs incurred with applying impulses as well as running costs. We formulate the relaxed problem and the associated primal convex programs in measures together with the dual programs, and establish the relevant duality results. As an application, we formulate and justify a general procedure for obtaining optimal $(J+1)$-mixed strategies for the original impulse control problems. This procedure is illustrated with a solved example.

math.OC↗

arXiv2025

Towards Distribution Matching between Collaborative and Language Spaces for Generative Recommendation

Generative recommendation aims to learn the underlying generative process over the entire item set to produce recommendations for users. Although it leverages non-linear probabilistic models to surpass the limited modeling capacity of linear factor models, it is often constrained by a trade-off between representation ability and tractability. With the rise of a new generation of generative methods based on pre-trained language models (LMs), incorporating LMs into general recommendation with implicit feedback has gained considerable attention. However, adapting them to generative recommendation remains challenging. The core reason lies in the mismatch between the input-output formats and semantics of generative models and LMs, making it challenging to achieve optimal alignment in the feature space. This work addresses this issue by proposing a model-agnostic generative recommendation framework called DMRec, which introduces a probabilistic meta-network to bridge the outputs of LMs with user interactions, thereby enabling an equivalent probabilistic modeling process. Subsequently, we design three cross-space distribution matching processes aimed at maximizing shared information while preserving the unique semantics of each space and filtering out irrelevant information. We apply DMRec to three different types of generative recommendation methods and conduct extensive experiments on three public datasets. The experimental results demonstrate that DMRec can effectively enhance the recommendation performance of these generative models, and it shows significant advantages over mainstream LM-enhanced recommendation methods.

cs.IR↗

arXiv2025

Multiple Rota-Baxter algebra and multiple Rota-Baxter modules

In this paper, we develop the theory of multiple Rota-Baxter modules over multiple Rota-Baxter algebras. We introduce left, right, and bimodule structures and construct free $Ω$-operated modules with mixable tensor establishing free commutative multiple Rota-Baxter modules. We provide a necessary and sufficient condition for a free module to admit a free multiple Rota-Baxter module structure. Furthermore, we define projective and injective multiple Rota-Baxter modules, showing that their category has enough projective and injective objects to support derived $\mathrm{Hom}$ functors. Finally, we introduce the tensor product of multiple Rota-Baxter algebras and define flat multiple Rota-Baxter modules, proving that both free and projective modules satisfy the flatness property.

math.RA↗