arXiv subjects

Wen Zhang

Publications and source records attributed to Wen Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Quantile-Physics Hybrid Framework for Safe-Speed Recommendation under Diverse Weather Conditions Leveraging Connected Vehicle and Road Weather Information Systems Data

Inclement weather conditions can significantly impact driver visibility and tire-road surface friction, requiring adjusted safe driving speeds to reduce crash risk. This study proposes a hybrid predictive framework that recommends real-time safe speed intervals for freeway travel under diverse weather conditions. Leveraging high-resolution Connected Vehicle (CV) data and Road Weather Information System (RWIS) data collected in Buffalo, NY, from 2022 to 2023, we construct a spatiotemporally aligned dataset containing over 6.6 million records across 73 days. The core model employs Quantile Regression Forests (QRF) to estimate vehicle speed distributions in 10-minute windows, using 26 input features that capture meteorological, pavement, and temporal conditions. To enforce safety constraints, a physics-based upper speed limit is computed for each interval based on real-time road grip and visibility, ensuring that vehicles can safely stop within their sight distance. The final recommended interval fuses QRF-predicted quantiles with both posted speed limits and the physics-derived upper bound. Experimental results demonstrate strong predictive performance: the QRF model achieves a mean absolute error of 1.55 mph, with 96.43% of median speed predictions within 5 mph, a PICP (50%) of 48.55%, and robust generalization across weather types. The model's ability to respond to changing weather conditions and generalize across road segments shows promise for real-world deployment, thereby improving traffic safety and reducing weather-related crashes.

cs.LG↗

arXiv2026

Minimizing Total Travel Time for Collaborative Package Delivery with Heterogeneous Drones

Given a fleet of drones with different speeds and a set of package delivery requests, the collaborative delivery problem asks for a schedule for the drones to collaboratively carry out all package deliveries, with the objective of minimizing the total travel time of all drones. We show that the best non-preemptive schedule (where a package that is picked up at its source is immediately delivered to its destination by one drone) is within a factor of three of the best preemptive schedule (where several drones can participate in the delivery of a single package). Then, we present a constant-factor approximation algorithm for the problem of computing the best non-preemptive schedule. The algorithm reduces the problem to a tree combination problem and uses a primal-dual approach to solve the latter. We have implemented a version of the algorithm optimized for practical efficiency and report the results of experiments on large-scale instances with synthetic and real-world data, demonstrating that our algorithm is scalable and delivers schedules of excellent quality.

cs.DS↗

arXiv2026

SpecAware: A Spectral-Content Aware Foundation Model for Unifying Multi-Sensor Learning in Hyperspectral Remote Sensing Mapping

Hyperspectral imaging (HSI) is a critical technique for fine-grained land-use and land-cover (LULC) mapping. However, the inherent heterogeneity of HSI data, particularly the variation in spectral channels across sensors, has long constrained the development of model generalization via transfer learning or joint training. Existing HSI foundation models show promise for different downstream tasks, but typically underutilize the critical guiding role of sensor meta-attributes and image semantic features, resulting in limited adaptability to cross-sensor joint learning. To address these issues, we propose SpecAware, which is a novel hyperspectral spectral-content aware foundation model for unifying multi-sensor learning for HSI mapping. To support this work, we constructed the Hyper-400K dataset, which is a new large-scale pre-training dataset with over 400\,k high-quality patches from diverse airborne AVIRIS sensors that cover two data processing levels (L1 and L2). The core of SpecAware is a hypernetwork-driven unified image embedding process for HSI data. Firstly, we designed a meta-content aware module to generate a unique conditional input for each HSI sample, tailored to each spectral band by fusing the sensor meta-attributes and its own image content. Secondly, we designed the HyperEmbedding module, where a sample-conditioned hypernetwork dynamically generates a pair of matrix factors for channel-wise encoding. This process implements two-step matrix factorization, consisting of adaptive spatial pattern extraction and latent semantic feature projection, yielding a unified hyperspectral token representation. Thus, SpecAware learns to capture and interpret spatial-spectral features across diverse scenes and sensors, enabling adaptive processing of variable spectral channels within a unified multi-sensor joint pre-training framework.

cs.CV↗

arXiv2026

Every Little Helps: Building Knowledge Graph Foundation Model with Fine-grained Transferable Multi-modal Tokens

Multi-modal knowledge graph reasoning (MMKGR) aims to predict the missing links by exploiting both graph structure information and multi-modal entity contents. Most existing works are designed for a transductive setting, which learns dataset-specific embeddings and struggles to generalize to new KGs. Recent knowledge graph foundation models (KGFMs) improve cross-KG transfer, but they mainly exploit structural patterns and ignore rich multi-modal signals. We address these gaps by proposing a token-based foundation model (TOFU) for MMKGR, which exhibits strong generalization across different MMKGs. TOFU discretizes structural, visual, and textual information into modality-specific tokens. TOFU then employs a hierarchical fusion architecture with mixture-of-message mechanisms, aiming to process these tokens and obtain transferable features for MMKGR. Experimental results on 17 transductive, inductive, and fully-inductive MMKGs show that TOFU consistently outperforms strong KGFM and MMKGR baselines, delivering strong performance on unseen MMKGs.

cs.CL↗

arXiv2026

An Extension and Refinement of the Brouwer-Schauder-Tychonoff Fixed Point Theorem

In this paper, we present the Brouwer-Schauder-Tychonoff fixed point theorem on locally convex spaces as the following extension and improvement: Suppose that S is a compact star-shaped subset with respect to p in S with its convexity index alpha(p)>0. Then every continuous self-mapping f has one of the following two properties: (a) The point p is a fixed point of f; (b) f has uncountably many different eigenvalues and eigenvectors. Note that a closed bounded star-shaped set in a locally convex space is convex if and only if alpha=1, and we extend a Brouwer's type fixed-point theorem on compact star-shaped sets in Banach spaces in a more concise manner to locally convex spaces, thereby this is a simplification and an improvement of the Tychonoff fixed-point theorem to compact star-shaped sets.

math.FA↗

arXiv2026

Distributed Convoluted Rank Regression for Non-Shareable Data under Non-Additive Losses

We study high-dimensional rank regression when data are distributed across multiple machines and the loss is a non-additive U-statistic, as in convoluted rank regression (CRR). Classical communication-efficient surrogate likelihood (CSL) methods crucially rely on the additivity of the empirical loss and therefore break down for CRR, whose global loss couples all sample pairs across machines. We propose a distributed convoluted rank regression (DCRR) framework that constructs a similar surrogate loss and demonstrate its validity under the non-additive losses. We show that this surrogate shares the same population minimizer as the full-data CRR loss and yields estimators that are statistically equivalent to centralized CRR. Building on this, we develop a two-stage sparse DCRR procedure -- an iterative $\ell_1$-penalized stage followed by a folded-concave refinement -- and establish non-asymptotic error bounds, a distributed strong oracle property, and a DHBIC-type criterion for consistent model selection. A scaling result shows that the number of machines may diverge as $M = o({N/(s^2\log p)})$ while achieving centralized oracle rates with only $O(\log N)$ communication rounds. Simulations and a large-scale real data example demonstrate substantial gains over naive divide-and-conquer, particularly under heavy-tailed errors.

stat.ME↗

arXiv2026

Physics-Informed Neural Networks for the Quantum Droplets in Binary Bose-Einstein Condensates

Physics-Informed Neural Networks (PINNs), which integrate deep learning with physical prior knowledge, have proven to be a powerful tool for studying the dynamics of high-dimensional nonlinear systems. The present work utilizes PINNs to analyze the existence and evolution of quantum droplets (QDs) in a binary Bose-Einstein condensate (BEC), revealing the ability of this technique to accurately predict structural features of the QDs, their multipeak profiles, and dynamical behavior. The stable evolution of multipole QDs is thus demonstrated. Comparing different network architectures, including the training time, loss values, and $\mathbb{L_{2}}$ error, PINNs accurately predict specific dynamical characteristics of QDs. Furthermore, the PINN robustness is evaluated by the application of PINN to parameter-discovery tasks, considering both clean training data and data contaminated by $1\%$ random noise. The results highlight the efficiency of PINNs in modeling complex quantum systems and extracting reliable parameters under the noisy conditions.

cond-mat.quant-gas↗

arXiv2026

NEAT: Neuron-Based Early Exit for Large Reasoning Models

Large Reasoning Models (LRMs) often suffer from \emph{overthinking}, a phenomenon in which redundant reasoning steps are generated after a correct solution has already been reached. Existing early reasoning exit methods primarily rely on output-level heuristics or trained probing models to skip redundant reasoning steps, thereby mitigating overthinking. However, these approaches typically require additional rollout computation or externally labeled datasets. In this paper, we propose \textbf{NEAT}, a \textbf{N}euron-based \textbf{E}arly re\textbf{A}soning exi\textbf{T} framework that monitors neuron-level activation dynamics to enable training-free early exits, without introducing additional test-time computation. NEAT identifies exit-associated neurons and tracks their activation patterns during reasoning to dynamically trigger early exit or suppress reflection, thereby reducing unnecessary reasoning while preserving solution quality. Experiments on four reasoning benchmarks across six models with different scales and architectures show that, for each model, NEAT achieves an average token reduction of 22\% to 28\% when averaged over the four benchmarks, while maintaining accuracy.

cs.CL↗

arXiv2026

Adaptive traffic signal control optimization using a novel road partition and multi-channel state representation method

This study proposes a novel adaptive traffic signal control method leveraging a Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) to optimize signal timing by integrating variable cell length and multi-channel state representation. A road partition formula consisting of the sum of logarithmic and linear functions was proposed. The state variables are a vector composed of three channels: the number of vehicles, the average speed, and space occupancy. The set of available signal phases constitutes the action space, the selected phase is executed with a fixed green time. The reward function is formulated using the absolute values of key traffic state metrics - waiting time, speed, and fuel consumption. Each metric is normalized by a typical maximum value and assigned a weight that reflects its priority and optimization direction. The simulation results, using Sumo-TensorFlow-Python, demonstrate a cross-range transferability evaluation and show that the proposed variable cell length and multi-channel state representation method excels compared to fixed cell length in optimization performance.

eess.SY↗

arXiv2026

UAV-Assisted Joint Data Collection and Wireless Power Transfer for Batteryless Sensor Networks

The development of wireless power transfer (WPT) and Internet of Things (IoT) offers significant potential but faces challenges such as limited energy supply, dynamic environmental changes, and unstable transmission links. This paper presents an unmanned aerial vehicle (UAV)-assisted data collection and WPT scheme to support batteryless sensor (BLS) networks in remote areas. In this system, BLSs harvest energy from the UAV and utilize the harvested energy to transmit the collected data back to the UAV. The goal is to maximize the collected data volume and fairness index while minimizing the UAV energy consumption. To achieve these objectives, an optimization problem is formulated to jointly optimize the transmit power and UAV trajectory. Due to the non-convexity and dynamic nature of the problem, a deep reinforcement learning (DRL)-based algorithm is proposed to solve the problem. Specifically, this algorithm integrates prioritized experience replay and the performer module to enhance system stability and accelerate convergence. Simulation results demonstrate that the proposed approach consistently outperforms benchmark schemes in terms of collected data volume, fairness, and UAV energy consumption.

cs.NI↗

arXiv2026

ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation

Empathetic speech dialogue requires not only understanding linguistic content but also perceiving rich paralinguistic information such as prosody, tone, and emotional intensity for affective understandings. Existing speech-to-speech large language models either rely on ASR transcription or use encoders to extract latent representations, often weakening affective information and contextual coherence in multi-turn dialogues. To address this, we propose \textbf{ES4R}, a framework for speech-based empathetic response generation. Our core innovation lies in explicitly modeling structured affective context before speech encoding, rather than relying on implicit learning by the encoder or explicit emotion supervision. Specifically, we introduce a dual-level attention mechanism to capture turn-level affective states and dialogue-level affective dynamics. The resulting affective representations are then integrated with textual semantics through speech-guided cross-modal attention to generate empathetic responses. For speech output, we employ energy-based strategy selection and style fusion to achieve empathetic speech synthesis. ES4R consistently outperforms strong baselines in both automatic and human evaluations and remains robust across different LLM backbones.

eess.AS↗

arXiv2026

First Submillimeter Lights from Dome A: Tracing the Carbon Cycle in the Feedback of Massive Stars

The cycling of carbon between its ionized, atomic, and molecular phases shapes the chemical compositions and physical conditions of the interstellar medium (ISM). However, ground-based studies of the full carbon cycle have been limited by atmospheric absorption. Dome~A, the most promising site for submillimeter astronomy, has long resisted successful submillimeter astronomical observations. Using the 60~cm Antarctic Terahertz Explorer, we present the first successful CO ($4-3$) and [CI] ($^3P_1 - ^3P_0$) mapping observations of two archetypal triggered massive star-formation regions at Dome~A. These data, together with archival [CII], provide the first complete characterization of all three carbon phases in these environments. We find elevated C$^{0}$/CO abundance ratios in high-extinction regions, plausibly driven by deep penetration of intense radiation fields from massive stars into a clumpy ISM. These findings mark a major milestone for submillimeter astronomy at Dome~A and offer valuable insights into the impact of massive star feedback on the surrounding ISM.

astro-ph.GA↗

arXiv2025

On cable-graph percolation between dimensions 2 and 3

We consider the Gaussian free field on two-dimensional slabs with a thickness described by a height $h$ at spatial scale $N$. We investigate the radius of critical clusters for the associated cable-graph percolation problem, which depends sensitively on the parameter $h$. Our results unveil a whole family of new "fixed points", which interpolate between recent results from arXiv:2303.03782 in two dimensions and from arXiv:2405.17417 and arXiv:2406.02397 in three dimensions, and describe critical behaviour beyond those regimes. In the delocalised phase, the one-arm decay exhibits a "plateau", i.e. it doesn't depend on the speed at which the variance of the field diverges in the large-$N$ limit. Our methods rely on a careful analysis of the interplay between two- and three-dimensional effects for the underlying random walk, which manifest themselves in a corresponding decomposition of the field.

math.PR↗

arXiv2025

Human Decision-making is Susceptible to AI-driven Manipulation

AI systems are increasingly intertwined with daily life, assisting users with various tasks and guiding decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users' cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes. Through a randomized between-subjects experiment with 233 participants, we examined human susceptibility to such manipulation in financial (e.g., purchases) and emotional (e.g., conflict resolution) decision-making contexts. Participants interacted with one of three AI agents: a neutral agent (NA) optimizing for user benefit without explicit influence, a manipulative agent (MA) designed to covertly influence beliefs and behaviors, or a strategy-enhanced manipulative agent (SEMA) equipped with established psychological tactics, allowing it to select and apply them adaptively during interactions to reach its hidden objectives. By analyzing participants' preference ratings, we found significant susceptibility to AI-driven manipulation. Particularly across both decision-making domains, interacting with the manipulative agents significantly increased the odds of rating hidden incentives higher than optimal options (Financial, MA: OR=5.24, SEMA: OR=7.96; Emotional, MA: OR=5.52, SEMA: OR=5.71) compared to the NA group. Notably, we found no clear evidence that employing psychological strategies (SEMA) was overall more effective than simple manipulative objectives (MA) on our primary outcomes. Hence, AI-driven manipulation could become widespread even without requiring sophisticated tactics and expertise. While our findings are preliminary and derived from hypothetical, low-stakes scenarios, we highlight a critical vulnerability in human-AI interactions, emphasizing the need for ethical safeguards and regulatory frameworks to protect human autonomy.

cs.AI↗

arXiv2025

A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases

Rare diseases affect hundreds of millions worldwide, yet diagnosis often spans years. Convectional pipelines decouple noisy evidence extraction from downstream inferential diagnosis, and general/medical large language models (LLMs) face scarce real world electronic health records (EHRs), stale domain knowledge, and hallucinations. We assemble a large, domain specialized clinical corpus and a clinician validated reasoning set, and develop RareSeek R1 via staged instruction tuning, chain of thought learning, and graph grounded retrieval. Across multicenter EHR narratives and public benchmarks, RareSeek R1 attains state of the art accuracy, robust generalization, and stability under noisy or overlapping phenotypes. Augmented retrieval yields the largest gains when narratives pair with prioritized variants by resolving ambiguity and aligning candidates to mechanisms. Human studies show performance on par with experienced physicians and consistent gains in assistive use. Notably, transparent reasoning highlights decisive non phenotypic evidence (median 23.1%, such as imaging, interventions, functional tests) underpinning many correct diagnoses. This work advances a narrative first, knowledge integrated reasoning paradigm that shortens the diagnostic odyssey and enables auditable, clinically translatable decision support.

cs.CL↗

arXiv2025

Self-Correction Distillation for Structured Data Question Answering

Structured data question answering (QA), including table QA, Knowledge Graph (KG) QA, and temporal KG QA, is a pivotal research area. Advances in large language models (LLMs) have driven significant progress in unified structural QA frameworks like TrustUQA. However, these frameworks face challenges when applied to small-scale LLMs since small-scale LLMs are prone to errors in generating structured queries. To improve the structured data QA ability of small-scale LLMs, we propose a self-correction distillation (SCD) method. In SCD, an error prompt mechanism (EPM) is designed to detect errors and provide customized error messages during inference, and a two-stage distillation strategy is designed to transfer large-scale LLMs' query-generation and error-correction capabilities to small-scale LLM. Experiments across 5 benchmarks with 3 structured data types demonstrate that our SCD achieves the best performance and superior generalization on small-scale LLM (8B) compared to other distillation methods, and closely approaches the performance of GPT4 on some datasets. Furthermore, large-scale LLMs equipped with EPM surpass the state-of-the-art results on most datasets.

cs.CL↗

arXiv2025

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex multi-hop questions requiring multiple retrieval steps. We propose ReSearch, a novel framework that trains LLMs to Reason with Search via reinforcement learning without using any supervised data on reasoning steps. Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking, and search results subsequently influence further reasoning. We train ReSearch on Qwen2.5-7B(-Instruct) and Qwen2.5-32B(-Instruct) models and conduct extensive experiments. Despite being trained on only one dataset, our models demonstrate strong generalizability across various benchmarks. Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction during the reinforcement learning process.

cs.AI↗

arXiv2025

Scientific Objectives of the Xue-shan-mu-chang 15-meter Submillimeter Telescope

Submillimeter astronomy is poised to revolutionize our understanding of the Universe by revealing cosmic phenomena hidden from optical and near-infrared observations, particularly those associated with interstellar dust, molecular gas, and star formation. The Xue-shan-mu-chang 15-meter submillimeter telescope (XSMT-15m), to be constructed at a premier high-altitude site (4813 m) in Qinghai, China, marks a major milestone for Chinese astronomy, establishing the China mainland's first independently developed, world-class submillimeter facility. Equipped with state-of-the-art instruments, XSMT-15m will address a diverse range of frontier scientific questions spanning extragalactic astronomy, Galactic structure, time-domain astrophysics, and astrochemistry. In synergy with current and forthcoming observatories, XSMT-15m will illuminate the formation and evolution of galaxies, unravel the physical and chemical processes shaping the interstellar medium, and explore transient phenomena in the submillimeter regime. These capabilities will advance our understanding across extragalactic astronomy, Galactic ecology, astrochemistry, and time-domain astrophysics, inaugurating a new era for submillimeter research in China and the northern hemisphere.

astro-ph.GA↗