Searcharxiv⌕ Search

arXiv subjects

Zhan Zhao

Publications and source records attributed to Zhan Zhao.

At least 19 recordsLinked to original sources
arXiv2026

OhmicFlow: Forecasting transit passenger flow under extreme weather disruptions via Ohm's law

As climate change intensifies, extreme weather events (EWEs) increasingly disrupt the supply-demand balance of mass transit systems. Accurate and reliable prediction of origin-destination (OD) passenger flow is essential for timely emergency response, but remains difficult under abnormal conditions. Although existing physics-informed methods can enhance model robustness, they remain insufficient for transit systems under extreme weather disruptions, where passenger flow fluctuations are jointly shaped by the redistribution of latent demand as a direct result of EWEs (i.e., direct effects) and the increase in travel impedance due to EWE-induced supply contraction and congestion effects (i.e., indirect effects). To address these limitations, we first conceptualize the transit network as an electrical circuit, treating latent demand as voltage, travel impedance as resistance and passenger flow as current, and then propose the OhmicFlow framework to jointly predict these variables under disruptions through Ohm's law. Specifically, a future-aware spatiotemporal backbone is used as an ammeter to predict disrupted passenger flow, and its replica is reused as a bypass voltmeter with impedance controlled in the inputs to infer latent demand counterfactually and in parallel. Travel impedance under foreseeable EWE disruptions is further modeled using a thermistor analogy, enabling dynamic estimation by coupling supply contraction with congestion effects. A multi-objective loss is incorporated to fit observed data while enforcing the Ohmic constraint. Empirical experiments based on 10 years of Shenzhen Metro data covering 17 EWEs show that OhmicFlow consistently outperforms various baseline methods, achieving lower prediction errors across various chronological training settings while improving uncertainty calibration, robustness, transferability, and interpretability.

physics.soc-ph↗
arXiv2026

RcLLM: Accelerating Generative Recommendation via Beyond-Prefix KV Caching

Large Language Models (LLMs) are transforming recommendation from ranking into a generative task, but industrial deployment remains limited by the high latency of processing long, personalized prompts. Standard prefix caching provides limited benefit because reuse in recommendation workloads is often non-contiguous across user histories and item contexts. We present RcLLM, a distributed inference system for generative recommendation with Beyond-Prefix KV Caching. RcLLM decomposes prompts into reusable blocks and supports large item catalogs with a stratified distributed storage design: compact user-history caches are replicated for zero-latency retrieval, while massive item caches are sharded using similarity-aware placement. To reduce redundant quadratic attention computation, RcLLM combines an affinity-based global scheduler that improves data locality with a selective attention mechanism that corrects approximation errors. Experiments on real-world datasets show that RcLLM reduces Time-To-First-Token (TTFT) by 1.31x-9.51x compared with state-of-the-art prefix caching systems, enabling real-time serving with negligible impact on recommendation accuracy.

cs.DC↗
arXiv2026

Mesonic screening correlators in an external imaginary electric field at finite temperature

External electromagnetic fields provide a useful probe of QCD matter, but real electric fields are hindered by the sign problem, motivating studies with imaginary electric fields. We investigate mesonic screening correlators in lattice QCD at finite temperature in the presence of such a background using staggered fermions. At low temperature, scalar screening masses increase with the field strength, while pseudo-scalar masses remain largely unchanged, and charge-asymmetric channels show additional structure. At high temperature, the correlators exhibit clear spatial oscillations with frequencies set by the quark electric charges. These results demonstrate nontrivial modifications of screening properties induced by external electric fields.

hep-lat↗
arXiv2026

Wilson loops with oppositely oriented plaquettes as a probe of center vortex structure

We study Wilson loops with a nontrivial orientation structure in lattice gauge theory as a probe of the center vortex picture. The observable is a single Wilson loop containing two plaquettes with opposite orientations, realized in two geometries referred to as the vertical and parallel configurations. The vertical case behaves consistently with expectations from the vortex picture. In contrast, the parallel configuration shows a deviation from the naive area-law expectation which cannot be explained solely by the opposite orientations of the plaquettes. We introduce a simple qualitative vortex model which accounts for this behavior and shows that the observed effect can still be understood within the vortex framework.

hep-lat↗
arXiv2025

A Technical Report on the Second Place Solution for the CIKM 2025 AnalytiCup Competition

In this work, we address the challenge of multilingual category relevance judgment in e-commerce search, where traditional ensemble-based systems improve accuracy but at the cost of heavy training, inference, and maintenance complexity. To overcome this limitation, we propose a simplified yet effective framework that leverages prompt engineering with Chain-of-Thought task decomposition to guide reasoning within a single large language model. Specifically, our approach decomposes the relevance judgment process into four interpretable subtasks: translation, intent understanding, category matching, and relevance judgment -- and fine-tunes a base model (Qwen2.5-14B) using Low-Rank Adaptation (LoRA) for efficient adaptation. This design not only reduces computational and storage overhead but also enhances interpretability by explicitly structuring the model's reasoning path. Experimental results show that our single-model framework achieves competitive accuracy and high inference efficiency, processing 20 samples per second on a single A100 GPU. In the CIKM 2025 AnalytiCup Competition Proposals, our method achieved 0.8902 on the public leaderboard and 0.8889 on the private leaderboard, validating the effectiveness and robustness of the proposed approach. These results highlight that structured prompting combined with lightweight fine-tuning can outperform complex ensemble systems, offering a new paradigm for scalable industrial AI applications.

cs.IR↗
arXiv2025

LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

Recent research has been increasingly focusing on developing 3D world models that simulate complex real-world scenarios. World models have found broad applications across various domains, including embodied AI, autonomous driving, entertainment, etc. A more realistic simulation with accurate physics will effectively narrow the sim-to-real gap and allow us to gather rich information about the real world conveniently. While traditional manual modeling has enabled the creation of virtual 3D scenes, modern approaches have leveraged advanced machine learning algorithms for 3D world generation, with most recent advances focusing on generative methods that can create virtual worlds based on user instructions. This work explores such a research direction by proposing LatticeWorld, a simple yet effective 3D world generation framework that streamlines the industrial production pipeline of 3D environments. LatticeWorld leverages lightweight LLMs (LLaMA-2-7B) alongside the industry-grade rendering engine (e.g., Unreal Engine 5) to generate a dynamic environment. Our proposed framework accepts textual descriptions and visual instructions as multimodal inputs and creates large-scale 3D interactive worlds with dynamic agents, featuring competitive multi-agent interaction, high-fidelity physics simulation, and real-time rendering. We conduct comprehensive experiments to evaluate LatticeWorld, showing that it achieves superior accuracy in scene layout generation and visual fidelity. Moreover, LatticeWorld achieves over a $90\times$ increase in industrial production efficiency while maintaining high creative quality compared with traditional manual production methods. Our demo video is available at https://youtu.be/8VWZXpERR18

cs.AI↗
arXiv2025

Event-aware analysis of cross-city visitor flows using large language models and social media data

Public events, such as music concerts and fireworks displays, can cause irregular surges in cross-city travel demand, leading to potential overcrowding, travel delays, and public safety concerns. To better anticipate and accommodate such demand surges, it is essential to estimate cross-city visitor flows with awareness of public events. Although prior studies typically focused on the effects of a single mega event or disruptions around a single venue, this study introduces a generalizable framework to analyze visitor flows under diverse and concurrent events. We propose to leverage large language models (LLMs) to extract event features from multi-source online information and massive user-generated content on social media platforms. Specifically, social media popularity metrics are designed to capture the effects of online promotion and word-of-mouth in attracting visitors. An event-aware machine learning model is then adopted to uncover the specific impacts of different event features and ultimately predict visitor flows for upcoming events. Using Hong Kong as a case study, the framework is applied to predict daily flows of mainland Chinese visitors arriving at the city, achieving a testing R-squared of over 85%. We further investigate the heterogeneous event impacts on visitor numbers across different event types and major travel modes. Both promotional popularity and word-of-mouth popularity are found to be associated with increased visitor flows, but the specific effects vary by the event type. This association is more pronounced among visitors arriving by metro and high-speed rail, while it has less effect on air travelers. The findings can facilitate coordinated measures across government agencies and guide specialized transport policies, such as shuttle transit services to event venues, and comprehensive on-site traffic management strategies.

cs.SI↗
arXiv2025

Analyzing sequential activity and travel decisions with interpretable deep inverse reinforcement learning

Travel demand modeling has shifted from aggregated trip-based models to behavior-oriented activity-based models because daily trips are essentially driven by human activities. To analyze the sequential activity-travel decisions, deep inverse reinforcement learning (DIRL) has proven effective in learning the decision mechanisms by approximating a reward function to represent preferences and a policy function to replicate observed behavior using deep neural networks (DNNs). However, most existing research has focused on using DIRL to enhance only prediction accuracy, with limited exploration into interpreting the underlying decision mechanisms guiding sequential decision-making. To address this gap, we introduce an interpretable DIRL framework for analyzing activity-travel decision processes, bridging the gap between data-driven machine learning and theory-driven behavioral models. Our proposed framework adapts an adversarial IRL approach to infer the reward and policy functions of activity-travel behavior. The policy function is interpreted through a surrogate interpretable model based on choice probabilities from the policy function, while the reward function is interpreted by deriving both short-term rewards and long-term returns for various activity-travel patterns. Our analysis of real-world travel survey data reveals promising results in two key areas: (i) behavioral pattern insights from the policy function, highlighting critical factors in decision-making and variations among socio-demographic groups, and (ii) behavioral preference insights from the reward function, indicating the utility individuals gain from specific activity sequences.

cs.AI↗
arXiv2024

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning

Vision language models (VLMs) perform well on many tasks but often fail at spatial reasoning, which is essential for navigation and interaction with physical environments. Many spatial reasoning tasks depend on fundamental two-dimensional (2D) skills, yet our evaluation shows that state-of-the-art VLMs give implausible or incorrect answers to composite spatial problems, including simple pathfinding tasks that humans solve effortlessly. To address this, we enhance 2D spatial reasoning in VLMs by training them only on basic spatial capabilities. We first disentangle 2D spatial reasoning into three core components: direction comprehension, distance estimation, and localization. We hypothesize that mastering these skills substantially improves performance on complex spatial tasks that require advanced reasoning and combinatorial problem solving, while also generalizing to real-world scenarios. To test this, we introduce Sparkle, a framework that generates synthetic data to provide targeted supervision across these three capabilities and yields an instruction dataset for each. Experiments show that VLMs fine-tuned with \emph{Sparkle} improve not only on basic tasks but also on composite and out-of-distribution real-world spatial reasoning tasks. These results indicate that enhancing basic spatial skills through synthetic generalization effectively advances complex spatial reasoning and offers a systematic strategy for boosting the spatial understanding of VLMs. Source codes of Sparkle are available at https://github.com/YihongT/Sparkle.

cs.CV↗
arXiv2024

ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning

Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this paper, we introduce the novel task of Open-domain Urban Itinerary Planning (OUIP), which generates personalized urban itineraries from user requests in natural language. We then present ITINERA, an OUIP system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs. This involves decomposing user requests, selecting candidate points of interest (POIs), ordering the POIs based on cluster-aware spatial optimization, and generating the itinerary. Experiments on real-world datasets and the performance of the deployed system demonstrate our system's capacity to deliver personalized and spatially coherent itineraries compared to current solutions. Source codes of ITINERA are available at https://github.com/YihongT/ITINERA.

cs.AI↗
arXiv2023

Exploring Large Language Models for Human Mobility Prediction under Public Events

Public events, such as concerts and sports games, can be major attractors for large crowds, leading to irregular surges in travel demand. Accurate human mobility prediction for public events is thus crucial for event planning as well as traffic or crowd management. While rich textual descriptions about public events are commonly available from online sources, it is challenging to encode such information in statistical or machine learning models. Existing methods are generally limited in incorporating textual information, handling data sparsity, or providing rationales for their predictions. To address these challenges, we introduce a framework for human mobility prediction under public events (LLM-MPE) based on Large Language Models (LLMs), leveraging their unprecedented ability to process textual data, learn from minimal examples, and generate human-readable explanations. Specifically, LLM-MPE first transforms raw, unstructured event descriptions from online sources into a standardized format, and then segments historical mobility data into regular and event-related components. A prompting strategy is designed to direct LLMs in making and rationalizing demand predictions considering historical mobility and event features. A case study is conducted for Barclays Center in New York City, based on publicly available event information and taxi trip data. Results show that LLM-MPE surpasses traditional models, particularly on event days, with textual data significantly enhancing its accuracy. Furthermore, LLM-MPE offers interpretable insights into its predictions. Despite the great potential of LLMs, we also identify key challenges including misinformation and high costs that remain barriers to their broader adoption in large-scale human mobility analysis.

cs.AI↗
arXiv2023

RouteKG: A knowledge graph-based framework for route prediction on road networks

Short-term route prediction on road networks allows us to anticipate the future trajectories of road users, enabling various applications ranging from dynamic traffic control to personalized navigation. Despite recent advances in this area, existing methods focus primarily on learning sequential transition patterns, neglecting the inherent spatial relations in road networks that can affect human routing decisions. To fill this gap, this paper introduces RouteKG, a novel Knowledge Graph-based framework for route prediction. Specifically, we construct a Knowledge Graph on the road network to encode spatial relations, especially moving directions that are crucial for human navigation. Moreover, an n-ary tree-based algorithm is introduced to efficiently generate top-K routes in batch mode, enhancing computational efficiency. To further optimize prediction performance, a rank refinement module is incorporated to fine-tune candidate route rankings. The model performance is evaluated using two real-world vehicle trajectory datasets from two Chinese cities under various practical scenarios. The results demonstrate a significant improvement in accuracy over the baseline methods. We further validate the proposed method by utilizing the pre-trained model as a simulator for real-time traffic flow estimation at the link level. RouteKG has great potential to transform vehicle navigation, traffic management, and a variety of intelligent transportation tasks, playing a crucial role in advancing the core foundation of intelligent and connected urban systems. The source codes of RouteKG are available at https://github.com/YihongT/RouteKG.

cs.SI↗
arXiv2023

Deep trip generation with graph neural networks for bike sharing system expansion

Bike sharing is emerging globally as an active, convenient, and sustainable mode of transportation. To plan successful bike-sharing systems (BSSs), many cities start from a small-scale pilot and gradually expand the system to cover more areas. For station-based BSSs, this means planning new stations based on existing ones over time, which requires prediction of the number of trips generated by these new stations across the whole system. Previous studies typically rely on relatively simple regression or machine learning models, which are limited in capturing complex spatial relationships. Despite the growing literature in deep learning methods for travel demand prediction, they are mostly developed for short-term prediction based on time series data, assuming no structural changes to the system. In this study, we focus on the trip generation problem for BSS expansion, and propose a graph neural network (GNN) approach to predicting the station-level demand based on multi-source urban built environment data. Specifically, it constructs multiple localized graphs centered on each target station and uses attention mechanisms to learn the correlation weights between stations. We further illustrate that the proposed approach can be regarded as a generalized spatial regression model, indicating the commonalities between spatial regression and GNNs. The model is evaluated based on realistic experiments using multi-year BSS data from New York City, and the results validate the superior performance of our approach compared to existing methods. We also demonstrate the interpretability of the model for uncovering the effects of built environment features and spatial interactions between stations, which can provide strategic guidance for BSS station location selection and capacity planning.

cs.LG↗
arXiv2023

A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewards

Route choice modeling is a fundamental task in transportation planning and demand forecasting. Classical methods generally adopt the discrete choice model (DCM) framework with linear utility functions and high-level route characteristics. While several recent studies have started to explore the applicability of deep learning for route choice modeling, they are limited to path-based models with relatively simple model architectures and relying on predefined choice sets. Existing link-based models can capture the dynamic nature of link choices within the trip without the need for choice set generation, but still assume linear relationships and link-additive features. To address these issues, this study proposes a general deep inverse reinforcement learning (IRL) framework for link-based route choice modeling, which is capable of incorporating diverse features (of the state, action and trip context) and capturing complex relationships. Specifically, we adapt an adversarial IRL model to the route choice problem for efficient estimation of context-dependent reward functions without value iteration. Experiment results based on taxi GPS data from Shanghai, China validate the superior prediction performance of the proposed model over conventional DCMs and other imitation learning baselines, even for destinations unseen in the training data. Further analysis show that the model exhibits competitive computational efficiency and reasonable interpretability. The proposed methodology provides a new direction for future development of route choice models. It is general and can be adaptable to other route choice problems across different modes and networks.

cs.LG↗
arXiv2023

Quantifying the uneven efficiency benefits of ridesharing market integration

Ridesharing is recognized as one of the key pathways to sustainable urban mobility. With the emergence of Transportation Network Companies (TNCs) such as Uber and Lyft, the ridesharing market has become increasingly fragmented in many cities around the world, leading to efficiency loss and increased traffic congestion. While an integrated ridesharing market (allowing sharing across TNCs) can improve the overall efficiency, how such benefits may vary across TNCs based on actual market characteristics is still not well understood. In this study, we extend a shareability network framework to quantify and explain the efficiency benefits of ridesharing market integration using available TNC trip records. Through a case study in Manhattan, New York City, the proposed framework is applied to analyze a real-world ridesharing market with 3 TNCs$-$Uber, Lyft, and Via. It is estimated that a perfectly integrated market in Manhattan would improve ridesharing efficiency by 13.3%, or 5% of daily TNC vehicle hours traveled. Further analysis reveals that (1) the efficiency improvement is negatively correlated with the overall demand density and inter-TNC spatiotemporal unevenness (measured by network modularity), (2) market integration would generate a larger efficiency improvement in a competitive market, and (3) the TNC with a higher intra-TNC demand concentration (measured by clustering coefficient) would benefit less from market integration. As the uneven benefits may deter TNCs from collaboration, we also illustrate how to quantify each TNC's marginal contribution based on the Shapley value, which can be used to ensure equitable profit allocation. These results can help market regulators and business alliances to evaluate and monitor market efficiency and dynamically adjust their strategies, incentives, and profit allocation schemes to promote market integration and collaboration.

physics.soc-ph↗
arXiv2022

Adapting Node-Place Model to Predict and Monitor COVID-19 Footprints and Transmission Risks

The node-place model has been widely used to classify and evaluate transit stations, which sheds light on individual travel behaviors and supports urban planning through effectively integrating land use and transportation development. This article adapts this model to investigate whether and how node, place, and mobility would be associated with the transmission risks and presences of the local COVID-19 cases in a city. Similar studies on the model and its relevance to COVID-19, according to our knowledge, have not been undertaken before. Moreover, the unique metric drawn from detailed visit history of the infected, i.e., the COVID-19 footprints, is proposed and exploited. This study then empirically uses the adapted model to examine the station-level factors affecting the local COVID-19 footprints. The model accounts for traditional measures of the node and place as well as actual human mobility patterns associated with the node and place. It finds that stations with high node, place, and human mobility indices normally have more COVID-19 footprints in proximity. A multivariate regression is fitted to see whether and to what degree different indices and indicators can predict the COVID-19 footprints. The results indicate that many of the place, node, and human mobility indicators significantly impact the concentration of COVID-19 footprints. These are useful for policy-makers to predict and monitor hotspots for COVID-19 and other pandemics transmission.

physics.soc-ph↗
arXiv2022

Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks

For bike sharing systems, demand prediction is crucial to ensure the timely re-balancing of available bikes according to predicted demand. Existing methods for bike sharing demand prediction are mostly based on its own historical demand variation, essentially regarding it as a closed system and neglecting the interaction between different transportation modes. This is particularly important for bike sharing because it is often used to complement travel through other modes (e.g., public transit). Despite some recent progress, no existing method is capable of leveraging spatiotemporal information from multiple modes and explicitly considers the distribution discrepancy between them, which can easily lead to negative transfer. To address these challenges, this study proposes a domain-adversarial multi-relational graph neural network (DA-MRGNN) for bike sharing demand prediction with multimodal historical data as input. A temporal adversarial adaptation network is introduced to extract shareable features from demand patterns of different modes. To capture correlations between spatial units across modes, we adapt a multi-relational graph neural network (MRGNN) considering both cross-mode similarity and difference. In addition, an explainable GNN technique is developed to understand how our proposed model makes predictions. Extensive experiments are conducted using real-world bike sharing, subway and ride-hailing data from New York City. The results demonstrate the superior performance of our proposed approach compared to existing methods and the effectiveness of different model components.

cs.LG↗
arXiv2022

Activity-aware Human Mobility Prediction with Hierarchical Graph Attention Recurrent Network

Human mobility prediction is a fundamental task essential for various applications in urban planning, location-based services and intelligent transportation systems. Existing methods often ignore activity information crucial for reasoning human preferences and routines, or adopt a simplified representation of the dependencies between time, activities and locations. To address these issues, we present Hierarchical Graph Attention Recurrent Network (HGARN) for human mobility prediction. Specifically, we construct a hierarchical graph based on past mobility records and employ a Hierarchical Graph Attention Module to capture complex time-activity-location dependencies. This way, HGARN can learn representations with rich human travel semantics to model user preferences at the global level. We also propose a model-agnostic history-enhanced confidence (MAHEC) label to incorporate each user's individual-level preferences. Finally, we introduce a Temporal Module, which employs recurrent structures to jointly predict users' next activities and their associated locations, with the former used as an auxiliary task to enhance the latter prediction. For model evaluation, we test the performance of HGARN against existing state-of-the-art methods in both the recurring (i.e., returning to a previously visited location) and explorative (i.e., visiting a new location) settings. Overall, HGARN outperforms other baselines significantly in all settings based on two real-world human mobility data benchmarks. These findings confirm the important role that human activities play in determining mobility decisions, illustrating the need to develop activity-aware intelligent transportation systems. Source codes of this study are available at https://github.com/YihongT/HGARN.

cs.LG↗