arXiv subjects

Tao Cheng

Publications and source records attributed to Tao Cheng.

At least 19 recordsLinked to original sources

arXiv2026

Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding

Micro-dramas, characterized by ultra-short durations and hyper-dense storylines, pose unique challenges for video understanding that conventional benchmarks fail to address. To bridge this gap, we introduce M-Drama, the first large-scale bilingual benchmark for micro-drama comprehension, featuring over 35K instances across 9,138 clips. Furthermore, while reinforcement learning can enhance VLMs on complex narratives, existing reward metrics often suffer from sparse and superficial signals, failing to capture intricate character identities and temporal structures. We propose SAGA (Structure-Aware Graph Alignment), a novel graph-matching reward function that models narratives as heterogeneous graphs. SAGA computes dense, rigorous rewards via decoupled semantic triplet and structural temporal matching. Extensive experiments on Qwen3-VL-8B-Instruct demonstrate that SAGA outperforms existing baselines, delivering substantial improvements in open-ended accuracy and summary quality, while maintaining competitive out-of-domain generalization. Code is available at https://github.com/qyx1121/MDrama_SAGA.

cs.AI↗

arXiv2026

From Urban Mobility to Epidemic Dynamics: A Mixture-of-Experts Framework with Preference Alignment for Policy Scenario Simulation

Non-pharmaceutical interventions (NPIs) alter epidemic risk through behavioral reallocations, not simply aggregate mobility reductions. Scenario-based NPI analysis therefore requires a behavioral layer that translates alternative policy calendars into plausible activity and mobility trajectories before downstream outcomes are simulated. We introduce UrbanShare-MoE-PA, a data-driven agent-level framework that maps factual and alternative NPI calendars to daily time-allocation trajectories and propagates them through a calibrated behavior-driven SEIR simulator. The behavioral engine decomposes each agent-day into travel share, POI-category allocation conditional on staying, and travel-mode allocation conditional on traveling. It combines a structured UrbanShare baseline, mixture-of-experts heads for heterogeneous POI and mode responses, and phase-aware preference alignment for calendar-conditioned rollouts. Using data from 911 agents in Singapore observed from March to August 2020, we evaluate factual reconstruction, four alternative lockdown calendars, and epidemic-activity trade-offs. UrbanShare-MoE improves POI reconstruction over the baseline, while UrbanShare-MoE-PA achieves the lowest travel-mode errors and the clearest alternative-calendar trajectories. In the calibrated SEIR simulation, early lockdown lowers infectious burden, late lockdown increases it, and short lockdown preserves the highest weighted activity with only a modest increase in epidemic burden relative to the original policy. These results show that epidemic-activity conclusions depend on how policy calendars are translated into behavior, and that agent-level mobility-share modeling provides an interpretable bridge between policy timing, behavior, and downstream simulation.

cs.CY↗

arXiv2026

DS-MTNet:Structured Multi-Task EEG Decoding for Human-Machine Collaboration

Current human-machine collaboration (HMC) systems rely on environment-facing sensors to observe visible actions and scene states, but the internal perceptual, intention-related, and state-related processes of operators remain insufficiently integrated into machine perception. Electroencephalography (EEG) provides a non-invasive, time-resolved modality to capture neural activity associated with these processes and can serve as an additional sensing channel in HMC. However, HMC-relevant EEG evidence is often mixed in continuous recordings. Existing EEG decoding methods usually target task-specific classification or aggregate prediction, so multiple HMC-relevant readouts are rarely organized in a unified EEG representation. To address this gap, this paper proposed the Decomposed-Source Multi-Task Network (DS-MTNet), a structured multi-task EEG decoding framework. DS-MTNet integrated three streams, namely EEG waveforms, task-routed source embeddings, and temporal-spectral power features, into reusable slots and used dual gating mechanisms to route task-specific components. The model was tested on a sustained-attention driving EEG dataset with three representative readouts: lane-departure-related epochs for environmental-event processing, steering-response stage for response preparation, and reaction-time-defined alertness state for internal state. DS-MTNet achieved the best mean performance among traditional, single-task deep, and multi-task EEG baselines, with the most robust gains observed for steering-response stage decoding. Ablation and interpretability analyses suggested that DS-MTNet jointly decoded multiple readouts and organized event-related, response-related, and state-related EEG evidence in a unified source-slot representation. These findings provide a computational step toward incorporating operator-related neural evidence into machine perception in HMC.

cs.HC↗

arXiv2026

CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities

Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current evaluations are limited, typically focusing on one or two cities and tasks and relying on random splits that introduce spatial leakage, leading to inflated performance and weak support for cross-location generalization and fair comparison. To address this, we propose CityRep, a unified benchmark that evaluates urban representations across data modalities, cities, and tasks using spatially structured splits. CityRep consists of three key components: (1) a spatial unit-agnostic evaluation framework that supports heterogeneous urban representations through a standardized alignment module; (2) a unified evaluation protocol using block-based spatial splits to mitigate spatial leakage and enable rigorous model comparison; and (3) an extensible multi-city, multi-task benchmark suite spanning 8 cities and 8 tasks across regression, classification, and distribution prediction. We evaluate 11 representative urban representation models. Results show that performance is highly sensitive to the split protocol, with random splits inflating scores and altering model rankings. We also observe substantial variability across cities and tasks, underscoring the need for generalization-aware evaluation. CityRep is released as a reproducible benchmark with datasets, evaluation pipelines, and diagnostic tools to facilitate fair comparison and support future research in urban representation learning towards urban foundation models.

cs.AI↗

arXiv2026

HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization

Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typically discretizes signals to fit LLM inputs, causing early semantic collapse and discarding fine-grained details. While external tools can mitigate this, they introduce a rigid bottleneck, confining reasoning to predefined operations. Although recent latent reasoning paradigms internalize visual states to overcome these limitations, optimizing the resulting hybrid discrete-continuous action space remains challenging. In this work, we propose HyLaR (Hybrid Latent Reasoning), a framework that seamlessly interleaves discrete text generation with continuous visual latent representations. Specifically, following an initial cold-start supervised fine-tuning (SFT), we introduce DePO (Decoupled Policy Optimization) to enable effective reinforcement learning within this hybrid space. DePO decomposes the policy gradient objective, applying independent trust-region constraints to the textual and latent components, alongside an exact closed-form von Mises-Fisher (vMF) KL regularizer. Extensive experiments demonstrate that HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks. Code is available at https://github.com/EthenCheng/HyLaR.

cs.CV↗

arXiv2026

Generalized Transferable Neural Networks for Steady-State Partial Differential Equations

Deep learning has emerged as a compelling framework for scientific and engineering computing, motivating growing interest in neural network-based solvers for partial differential equations (PDEs). Within this landscape, network architectures with deterministic feature construction have become an appealing approach, offering both high accuracy and computational efficiency in practice. Among them, the transferable neural network (TransNet) is a special class of shallow neural networks (i.e., single-hidden-layer architectures), whose hidden-layer parameters are predetermined according to the principle of uniformly distributed partition hyperplanes. Although TransNet has demonstrated strong performance in solving PDEs with relatively smooth solutions, its accuracy and stability may deteriorate in the presence of highly oscillatory solution structures, where activation saturation and system conditioning issues become limiting factors. In this paper, we propose a generalized transferable neural network (GTransNet) for solving steady-state PDEs, which augments the original TransNet design with additional hidden layers while preserving its interpretable feature-generation mechanism. In particular, the first hidden layer of GTransNet retains TransNet's parameter sampling strategy but incorporates an additional symmetry constraint on the neuron biases, while the subsequent hidden layers omit bias terms and employ a variance-controlled sampling strategy for selecting neuron weights.

math.NA↗

arXiv2026

PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning

Achieving real-time physics-based animation that generalizes across diverse 3D shapes and discretizations remains a fundamental challenge. We introduce PhysSkin, a physics-informed framework that addresses this challenge. In the spirit of Linear Blend Skinning, we learn continuous skinning fields as basis functions lifting motion subspace coordinates to full-space deformation, with subspace defined by handle transformations. To generate mesh-free, discretization-agnostic, and physically consistent skinning fields that generalize well across diverse 3D shapes, PhysSkin employs a new neural skinning fields autoencoder which consists of a transformer-based encoder and a cross-attention decoder. Furthermore, we also develop a novel physics-informed self-supervised learning strategy that incorporates on-the-fly skinning-field normalization and conflict-aware gradient correction, enabling effective balancing of energy minimization, spatial smoothness, and orthogonality constraints. PhysSkin shows outstanding performance on generalizable neural skinning and enables real-time physics-based animation.

cs.GR↗

arXiv2026

DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics

Modeling wind-driven object dynamics from video observations is highly challenging due to the invisibility and spatio-temporal variability of wind, as well as the complex deformations of objects. We present DiffWind, a physics-informed differentiable framework that unifies wind-object interaction modeling, video-based reconstruction, and forward simulation. Specifically, we represent wind as a grid-based physical field and objects as particle systems derived from 3D Gaussian Splatting, with their interaction modeled by the Material Point Method (MPM). To recover wind-driven object dynamics, we introduce a reconstruction framework that jointly optimizes the spatio-temporal wind force field and object motion through differentiable rendering and simulation. To ensure physical validity, we incorporate the Lattice Boltzmann Method (LBM) as a physics-informed constraint, enforcing compliance with fluid dynamics laws. Beyond reconstruction, our method naturally supports forward simulation under novel wind conditions and enables new applications such as wind retargeting. We further introduce WD-Objects, a dataset of synthetic and real-world wind-driven scenes. Extensive experiments demonstrate that our method significantly outperforms prior dynamic scene modeling approaches in both reconstruction accuracy and simulation fidelity, opening a new avenue for video-based wind-object interaction modeling.

cs.CV↗

arXiv2026

Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach

Recent advances in vision-language models have opened up new possibilities for reasoning-driven image geolocalization. However, existing approaches often rely on synthetic reasoning annotations or external image retrieval, which can limit interpretability and generalizability. In this paper, we present Geo-R, a retrieval-free framework that uncovers structured reasoning paths from existing ground-truth coordinates and optimizes geolocation accuracy via reinforcement learning. We propose the Chain of Region, a rule-based hierarchical reasoning paradigm that generates precise, interpretable supervision by mapping GPS coordinates to geographic entities (e.g., country, province, city) without relying on model-generated or synthetic labels. Building on this, we introduce a lightweight reinforcement learning strategy with coordinate-aligned rewards based on Haversine distance, enabling the model to refine predictions through spatially meaningful feedback. Our approach bridges structured geographic reasoning with direct spatial supervision, yielding improved localization accuracy, stronger generalization, and more transparent inference. Experimental results across multiple benchmarks confirm the effectiveness of Geo-R, establishing a new retrieval-free paradigm for scalable and interpretable image geolocalization. To facilitate further research and ensure reproducibility, both the model and code will be made publicly available.

cs.CL↗

arXiv2025

Beyond AlphaEarth: Toward Human-Centered Geospatial Foundation Models via POI-Guided Contrastive Learning

Recent geospatial foundation models (GFMs) produce spatially extensive representations of the Earth's surface that capture rich physical and environmental patterns. Among them, the AlphaEarth Foundation (AE) represents a major step, generating 10 m embeddings from multi-source Earth Observation (EO) data that include diverse environmental and spectral characteristics. However, such EO-driven representations primarily encode physical and spectral patterns rather than human activities or urban semantics, limiting their ability to capture the functional dimensions of cities and making the learned representations difficult to interpret or query using natural language. We introduce AETHER (AlphaEarth-POI Enriched Representation Learning), a lightweight framework that aligns AlphaEarth with human-centered urban analysis through multimodal alignment guided by Points of Interest (POIs). By enforcing both cross-modal AE-POI alignment and intra-modal multi-scale consistency, AETHER integrates functional urban semantics with EO-driven representations and grounds the embedding space in natural language. The resulting representations support both urban mapping tasks and natural language-conditioned spatial retrieval. Experiments across four downstream tasks in Greater London and Singapore demonstrate consistent state-of-the-art performance, with relative improvements ranging from 4.5% to 21.9%. Furthermore, the aligned embedding space enables spatial localization through natural language queries. By aligning EO-based foundation models with human-centered semantics, AETHER improves the interpretability of geospatial representations and advances geospatial representation learning toward human-centered, language-accessible geospatial foundation models.

cs.AI↗

arXiv2025

Competing $s$-wave pairing in overdoped $t$-$J$ model

The $d$-wave pairing symmetry has long been considered a defining feature of high-temperature superconductivity in cuprates. In this work, we reveal that $s$-wave pairing states exhibit variational energies comparable to the $d$-wave state in a square $t$-$J$ model, particularly at high doping levels ($\delta\gtrsim 15\%$) by using the state-of-the-art tensor network simulation. This surprising result suggests that $s$-wave pairing may play an important role in the cuprate phase diagram, especially for the overdoped region. Our findings provide a potential resolution to discrepancies in recent Josephson tunneling experiments on twisted bilayer cuprates and offer new insights into the evolution of pairing symmetry with doping.

cond-mat.str-el↗

arXiv2025

CSRM-LLM: Embracing Multilingual LLMs for Cold-Start Relevance Matching in Emerging E-commerce Markets

As global e-commerce platforms continue to expand, companies are entering new markets where they encounter cold-start challenges due to limited human labels and user behaviors. In this paper, we share our experiences in Coupang to provide a competitive cold-start performance of relevance matching for emerging e-commerce markets. Specifically, we present a Cold-Start Relevance Matching (CSRM) framework, utilizing a multilingual Large Language Model (LLM) to address three challenges: (1) activating cross-lingual transfer learning abilities of LLMs through machine translation tasks; (2) enhancing query understanding and incorporating e-commerce knowledge by retrieval-based query augmentation; (3) mitigating the impact of training label errors through a multi-round self-distillation training strategy. Our experiments demonstrate the effectiveness of CSRM-LLM and the proposed techniques, resulting in successful real-world deployment and significant online gains, with a 45.8% reduction in defect ratio and a 0.866% uplift in session purchase rate.

cs.IR↗

arXiv2025

Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals' Mobility Beyond Visited Places

Predicting individuals' next locations is a core task in human mobility modelling, with wide-ranging implications for urban planning, transportation, public policy and personalised mobility services. Traditional approaches largely depend on location embeddings learned from historical mobility patterns, limiting their ability to encode explicit spatial information, integrate rich urban semantic context, and accommodate previously unseen locations. To address these challenges, we explore the application of CaLLiPer -- a multimodal representation learning framework that fuses spatial coordinates and semantic features of points of interest through contrastive learning -- for location embedding in individual mobility prediction. CaLLiPer's embeddings are spatially explicit, semantically enriched, and inductive by design, enabling robust prediction performance even in scenarios involving emerging locations. Through extensive experiments on four public mobility datasets under both conventional and inductive settings, we demonstrate that CaLLiPer consistently outperforms strong baselines, particularly excelling in inductive scenarios. Our findings highlight the potential of multimodal, inductive location embeddings to advance the capabilities of human mobility prediction systems. We also release the code and data (https://github.com/xlwang233/Into-the-Unknown) to foster reproducibility and future research.

cs.AI↗

arXiv2025

CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images

We present a CLIP-based, multi-modal, multi-label classifier for predicting geographical context tags from landscape photos in the Geograph dataset--a crowdsourced image archive spanning the British Isles, including remote regions lacking POIs and street-level imagery. Our approach addresses a Kaggle competition\footnote{https://www.kaggle.com/competitions/predict-geographic-context-from-landscape-photos} task based on a subset of Geograph's 8M images, with strict evaluation: exact match accuracy is required across 49 possible tags. We show that combining location and title embeddings with image features improves accuracy over using image embeddings alone. We release a lightweight pipeline\footnote{https://github.com/SpaceTimeLab/ClipTheLandscape} that trains on a modest laptop, using pre-trained CLIP image and text embeddings and a simple classification head. Predicted tags can support downstream tasks such as building location embedders for GeoAI applications, enriching spatial understanding in data-sparse regions.

cs.CV↗

arXiv2025

Enriching Location Representation with Detailed Semantic Information

Spatial representations that capture both structural and semantic characteristics of urban environments are essential for urban modeling. Traditional spatial embeddings often prioritize spatial proximity while underutilizing fine-grained contextual information from places. To address this limitation, we introduce CaLLiPer+, an extension of the CaLLiPer model that systematically integrates Point-of-Interest (POI) names alongside categorical labels within a multimodal contrastive learning framework. We evaluate its effectiveness on two downstream tasks, land use classification and socioeconomic status distribution mapping, demonstrating consistent performance gains of 4% to 11% over baseline methods. Additionally, we show that incorporating POI names enhances location retrieval, enabling models to capture complex urban concepts with greater precision. Ablation studies further reveal the complementary role of POI names and the advantages of leveraging pretrained text encoders for spatial representations. Overall, our findings highlight the potential of integrating fine-grained semantic attributes and multimodal learning techniques to advance the development of urban foundation models.

cs.CE↗

arXiv2025

MSD-LLM: Predicting Ship Detention in Port State Control Inspections with Large Language Model

Maritime transportation is the backbone of global trade, making ship inspection essential for ensuring maritime safety and environmental protection. Port State Control (PSC), conducted by national ports, enforces compliance with safety regulations, with ship detention being the most severe consequence, impacting both ship schedules and company reputations. Traditional machine learning methods for ship detention prediction are limited by the capacity of representation learning and thus suffer from low accuracy. Meanwhile, autoencoder-based deep learning approaches face challenges due to the severe data imbalance in learning historical PSC detention records. To address these limitations, we propose Maritime Ship Detention with Large Language Models (MSD-LLM), integrating a dual robust subspace recovery (DSR) layer-based autoencoder with a progressive learning pipeline to handle imbalanced data and extract meaningful PSC representations. Then, a large language model groups and ranks features to identify likely detention cases, enabling dynamic thresholding for flexible detention predictions. Extensive evaluations on 31,707 PSC inspection records from the Asia-Pacific region show that MSD-LLM outperforms state-of-the-art methods more than 12\% on Area Under the Curve (AUC) for Singapore ports. Additionally, it demonstrates robustness to real-world challenges, making it adaptable to diverse maritime risk assessment scenarios.

cs.AI↗

arXiv2025

Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner

Recent advances in vision language models (VLMs) have enabled broad progress in the general medical field. However, pathology still remains a more challenging subdomain, with current pathology specific VLMs exhibiting limitations in both diagnostic accuracy and reasoning plausibility. Such shortcomings are largely attributable to the nature of current pathology datasets, which are primarily composed of image description pairs that lack the depth and structured diagnostic paradigms employed by real world pathologists. In this study, we leverage pathology textbooks and real world pathology experts to construct high-quality, reasoning-oriented datasets. Building on this, we introduce Patho-R1, a multimodal RL-based pathology Reasoner, trained through a three-stage pipeline: (1) continued pretraining on 3.5 million image-text pairs for knowledge infusion; (2) supervised fine-tuning on 500k high-quality Chain-of-Thought samples for reasoning incentivizing; (3) reinforcement learning using Group Relative Policy Optimization and Decoupled Clip and Dynamic sAmpling Policy Optimization strategies for multimodal reasoning quality refinement. To further assess the alignment quality of our dataset, we propose Patho-CLIP, trained on the same figure-caption corpus used for continued pretraining. Comprehensive experimental results demonstrate that both Patho-CLIP and Patho-R1 achieve robust performance across a wide range of pathology-related tasks, including zero-shot classification, cross-modal retrieval, Visual Question Answering, and Multiple Choice Question. Our project is available at the Patho-R1 repository: https://github.com/Wenchuan-Zhang/Patho-R1.

cs.CV↗

arXiv2025

Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework

Geolocation, the task of identifying an image's location, requires complex reasoning and is crucial for navigation, monitoring, and cultural preservation. However, current methods often produce coarse, imprecise, and non-interpretable localization. A major challenge lies in the quality and scale of existing geolocation datasets. These datasets are typically small-scale and automatically constructed, leading to noisy data and inconsistent task difficulty, with images that either reveal answers too easily or lack sufficient clues for reliable inference. To address these challenges, we introduce a comprehensive geolocation framework with three key components: GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric, collectively designed to address critical challenges and drive advancements in geolocation research. At the core of this framework is GeoComp (Geolocation Competition Dataset), a large-scale dataset collected from a geolocation game platform involving 740K users over two years. It comprises 25 million entries of metadata and 3 million geo-tagged locations spanning much of the globe, with each location annotated thousands to tens of thousands of times by human users. The dataset offers diverse difficulty levels for detailed analysis and highlights key gaps in current models. Building on this dataset, we propose Geographical Chain-of-Thought (GeoCoT), a novel multi-step reasoning framework designed to enhance the reasoning capabilities of Large Vision Models (LVMs) in geolocation tasks. GeoCoT improves performance by integrating contextual and spatial cues through a multi-step process that mimics human geolocation reasoning. Finally, using the GeoEval metric, we demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.

cs.CV↗