arXiv subjects

Jiahang Li

Publications and source records attributed to Jiahang Li.

At least 19 recordsLinked to original sources

arXiv2026

InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors

Video virtual try-on is a highly constrained editing task requiring the precise replacement of a target person's clothing while strictly preserving the original video's spatial structure and temporal dynamics. Existing methods heavily rely on auxiliary handcrafted spatial priors (e.g., masks, poses) for editing control. However, these priors are prone to failure in unconstrained real-world videos and often compress rich visual context into incomplete structural signals. Furthermore, standard reconstruction objectives fail to fully capture try-on-specific human preferences. To address these challenges, we propose InstructVVT, an instruction-driven and reference-guided video virtual try-on framework based on a Diffusion Transformer (DiT) that operates without inference-time spatial priors. Our core insight is to recover fine-grained control directly from the input triplet (source video, reference garment, and instruction) via a dual-level reference conditioning scheme. Specifically, an MLLM infers semantic edit tokens for target disambiguation and structural preservation, while a lightweight conditioning pathway explicitly injects fine-grained visual garment details. Finally, we design a try-on-specific reward and utilize the DiffusionNFT algorithm to align the model with human preferences. Extensive experiments on ViViD-S and TripVVT-Bench demonstrate that InstructVVT outperforms state-of-the-art open-source methods in garment fidelity, structural preservation, and temporal consistency, despite requiring fewer inference-time controls.

cs.CV↗

arXiv2026

HexagonalWarriorMamba: Superior Threshold-Dependent Multi-label Classification of 12-Lead ECG Cardiac Abnormalities

The accurate automated diagnosis of cardiac abnormalities from 12-lead electrocardiograms (ECGs) is critical for managing cardiovascular disease. However, detecting concurrent conditions remains a challenge for traditional deep learning models, which often have limited ability to model the long-range dependencies inherent in ECG signals. This manuscript proposes HexagonalWarriorMamba (HWMamba), a framework built on the Mamba architecture that processes 12-lead ECGs as single-channel 2D images rather than conventional 1D time series. By integrating a hierarchical architecture with a 2D Selective Scan mechanism, HWMamba is designed to model global context and complex spatial relationships within the data. The model is evaluated on the PhysioNet/Computing in Cardiology Challenge 2021 dataset, which includes 26 diagnostic labels and comprises recordings collected from seven institutions across four countries and three continents. Results demonstrate that HWMamba outperforms current state-of-the-art (SOTA) methods across five key threshold-dependent metrics, including Challenge Score and Subset Accuracy. These improvements provide a balance between strong discriminative capability and effective threshold selection derived from the training data, while maintaining near-SOTA performance in Macro AUROC. This Hexagonal Warrior performance, reflecting consistent performance across multiple evaluation dimensions, positions HWMamba as a robust and versatile approach for multi-label ECG classification.

cs.CV↗

arXiv2026

Coordination Engineering of Dual-Atom Catalysts for Overall Water Splitting: Mechanistic Insights from Constant-Potential First-Principles and Machine Learning

The rational design of bifunctional electrocatalysts for the hydrogen evolution reaction (HER) and oxygen evolution reaction (OER) is essential for achieving efficient and cost-effective overall water splitting. Atomically dispersed transition-metal catalysts, including single-atom catalysts and dual-atom catalysts (DACs), have emerged as a prominent class of heterogeneous catalysts, in which coordination engineering plays a decisive role in tuning catalytic performance. Herein, we explore coordination-engineered bifunctional overall water splitting electrocatalysts using graphene-supported DACs (TM1TM2-C6-xNx) as model systems. By tuning C/N coordination and dual-metal combinations (Fe, Co, Ni, and Cu), a library of 228 structures was constructed. A three-step screening strategy, combining constant-charge and constant-potential density functional theory with kinetic analysis of proton-coupled electron transfer (PCET), identifies 24 highly active candidates (TM1TM2 = CoNi, CoCu and Co2) with mixed C/N coordination for OER. These catalysts exhibit overpotentials comparable to that of IrO2 and low PCET barriers (lower than 0.40 eV), among which 22 also show high HER activity. Machine learning reveals clear coordination-dependent structure-performance relationships. Such bifunctionality arises from coordination engineering that enables the simultaneous optimization of OER intermediate adsorption and the hydrogen binding strength for HER. This work establishes coordination engineering as an effective strategy for designing high-performance bifunctional dual-atom electrocatalysts for overall water splitting.

cond-mat.mtrl-sci↗

arXiv2026

IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly

We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial angle grinder with professional-grade tools. To our knowledge, IMPACT is the first real industrial assembly benchmark that jointly provides synchronized ego-exo RGB-D capture, decoupled bimanual annotation, compliance-aware state tracking, and explicit anomaly--recovery supervision within a single real industrial workflow. It comprises 112 trials from 13 participants totaling 39.5 hours, with multi-route execution governed by a partial-order prerequisite graph, a six-category anomaly taxonomy, and operator cognitive load measured via NASA-TLX. The annotation hierarchy links hand-specific atomic actions to coarse procedural steps, component assembly states, and per-hand compliance phases, with synchronized null spans across views to decouple perceptual limitations from algorithmic failure. Systematic baselines reveal fundamental limitations that remain invisible to single-task benchmarks, particularly under realistic deployment conditions that involve incomplete observations, flexible execution paths, and corrective behavior. The full dataset, annotations, and evaluation code are available at https://github.com/Kratos-Wen/IMPACT.

cs.CV↗

arXiv2026

DeepSlide: From Artifacts to Presentation Delivery

Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize the artifact (a visually plausible deck) while under-optimizing the delivery process (pacing, narrative, and presentation preparation). We present DeepSlide, a human-in-the-loop multi-agent system that supports preparing the full presentation process, from requirement elicitation and time-budgeted narrative planning, to evidence-grounded slide--script generation, attention augmentation, and rehearsal support. DeepSlide integrates (i) a controllable logical-chain planner with per-node time budgets, (ii) a lightweight content-tree retriever for grounding, (iii) Markov-style sequential rendering with style inheritance, and (iv) sandboxed execution with minimal repair to ensure renderability. We further introduce a dual-scoreboard benchmark that cleanly separates static artifact quality from dynamic delivery excellence. Across 20 domains and diverse audience profiles, DeepSlide matches strong baselines on artifact quality while consistently achieving larger gains on delivery metrics, improving narrative flow, pacing precision, and slide--script synergy with clearer attention guidance.

cs.AI↗

arXiv2026

Human Identification at a Distance: Challenges, Methods and Results on the Competition HID 2025

Human identification at a distance (HID) is challenging because traditional biometric modalities such as face and fingerprints are often difficult to acquire in real-world scenarios. Gait recognition provides a practical alternative, as it can be captured reliably at a distance. To promote progress in gait recognition and provide a fair evaluation platform, the International Competition on Human Identification at a Distance (HID) has been organized annually since 2020. Since 2023, the competition has adopted the challenging SUSTech-Competition dataset, which features substantial variations in clothing, carried objects, and view angles. No dedicated training data are provided, requiring participants to train their models using external datasets. Each year, the competition applies a different random seed to generate distinct evaluation splits, which reduces the risk of overfitting and supports a fair assessment of cross-domain generalization. While HID 2023 and HID 2024 already used this dataset, HID 2025 explicitly examined whether algorithmic advances could surpass the accuracy limits observed previously. Despite the heightened difficulty, participants achieved further improvements, and the best-performing method reached 94.2% accuracy, setting a new benchmark on this dataset. We also analyze key technical trends and outline potential directions for future research in gait recognition.

cs.CV↗

arXiv2026

Potential-Induced Dynamic Coordination of Nonmetal Atoms Directly Bound to Metal Centers in Graphene-Embedded Single-Atom Catalysts and Its Implications

Electrode-potential-induced dynamic coordination is an essential factor governing the performance of graphene-embedded single-atom catalysts (SACs). While previous studies have primarily centered on structural dynamics at the metal site, the response of its coordinated nonmetal atoms remains largely unexplored. Here, using Ni SACs with mixed nitrogen/carbon coordination (NiN4-xCx) as representatives, we investigate potential-driven hydrogenation of metal-center-coordinated nonmetallic atoms through constant-potential density functional theory and ab initio molecular dynamics. We find that the C sites directly bound to Ni undergo potential-driven hydrogenation, whereas hydrogenation at N sites is thermodynamically unfavorable. Taking NiNC3 as a representative system, we demonstrate that these hydrogenation processes proceed with accessible kinetic barriers and obey the Br{\o}nsted-Evans-Polanyi relation. The resulting dynamic coordination reshapes the Ni 3d and dz2 orbitals, modulates the stability of the active center, and weakens molecular adsorption through combined electronic and steric effects. These findings reveal that electrode potential and solvent not only regulate the metal center but also dynamically reconfigure its coordination environment, offering novel mechanistic insights into potential-induced coordination dynamics and guiding the rational design of coordination-engineered SACs.

cond-mat.mtrl-sci↗

arXiv2025

A data-driven approach to linking design features with manufacturing process data for sustainable product development

The growing adoption of Industrial Internet of Things (IIoT) technologies enables automated, real-time collection of manufacturing process data, unlocking new opportunities for data-driven product development. Current data-driven methods are generally applied within specific domains, such as design or manufacturing, with limited exploration of integrating design features and manufacturing process data. Since design decisions significantly affect manufacturing outcomes, such as error rates, energy consumption, and processing times, the lack of such integration restricts the potential for data-driven product design improvements. This paper presents a data-driven approach to mapping and analyzing the relationship between design features and manufacturing process data. A comprehensive system architecture is developed to ensure continuous data collection and integration. The linkage between design features and manufacturing process data serves as the basis for developing a machine learning model that enables automated design improvement suggestions. By integrating manufacturing process data with sustainability metrics, this approach opens new possibilities for sustainable product development.

cs.LG↗

arXiv2025

Large Scale Manufacture of Phase Pure Two-Dimensional Metallic MoS2 Nanosheets

Metallic monolayered [or two - dimensional (2D)] MoS2 nanosheets show tremendous promise for energy storage and catalysis applications. However, state-of-the-art chemical exfoliation methods require > 48 hours to produce milligrams of metallic 2D MoS2. Further, chemically exfoliated MoS2 nanosheets are a mixture of metallic (1T or 1T prime 50% to 70%) and semiconducting (2H 30% to 50%) phases. Here, we demonstrate large-scale and rapid (>600 grams per hour) production of purely metallic phase 2D MoS2 (and WS2, MoSe2) nanosheets using microwave irradiation. Atomic resolution imaging shows 1T or 1T prime metallic phase in basal plane - consistent with close to 100% metallic phase concentration measured by X-ray photoelectron spectroscopy. The high 1T phase concentration results in the highest exchange current density of 0.175 plus-minus 0.03 mA cm-2 and among the lowest Tafel slopes (39 - 43 mV dec-1) measured to date for the hydrogen evolution reaction. In supercapacitors and lithium-sulfur pouch cell batteries, record-high volumetric capacitance of 753 plus-minus 3.6 F cm-3 and specific capacity of 1245 plus-minus 16 mAh g-1 (at exceptionally low electrolyte to sulfur ratio = 2 microlitre g-1), respectively, are obtained. Our method provides a practical pathway for producing high quality purely metallic phase 2D materials for high performance energy devices.

cond-mat.mtrl-sci↗

arXiv2025

DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization

RGB-D scene parsing methods effectively capture both semantic and geometric features of the environment, demonstrating great potential under challenging conditions such as extreme weather and low lighting. However, existing RGB-D scene parsing methods predominantly rely on supervised training strategies, which require a large amount of manually annotated pixel-level labels that are both time-consuming and costly. To overcome these limitations, we introduce DepthMatch, a semi-supervised learning framework that is specifically designed for RGB-D scene parsing. To make full use of unlabeled data, we propose complementary patch mix-up augmentation to explore the latent relationships between texture and spatial features in RGB-D image pairs. We also design a lightweight spatial prior injector to replace traditional complex fusion modules, improving the efficiency of heterogeneous feature fusion. Furthermore, we introduce depth-guided boundary loss to enhance the model's boundary prediction capabilities. Experimental results demonstrate that DepthMatch exhibits high applicability in both indoor and outdoor scenes, achieving state-of-the-art results on the NYUv2 dataset and ranking first on the KITTI Semantics benchmark.

cs.CV↗

arXiv2025

Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification

Inspired by human visual attention, deep neural networks have widely adopted attention mechanisms to learn locally discriminative attributes for challenging visual classification tasks. However, existing approaches primarily emphasize the representation of such features while neglecting their precise localization, which often leads to misclassification caused by shortcut biases. This limitation becomes even more pronounced when models are evaluated on transfer or out-of-distribution datasets. In contrast, humans are capable of leveraging prior object knowledge to quickly localize and compare fine-grained attributes, a capability that is especially crucial in complex and high-variance classification scenarios. Motivated by this, we introduce Gaze-CIFAR-10, a human gaze time-series dataset, along with a dual-sequence gaze encoder that models the precise sequential localization of human attention on distinct local attributes. In parallel, a Vision Transformer (ViT) is employed to learn the sequential representation of image content. Through cross-modal fusion, our framework integrates human gaze priors with machine-derived visual sequences, effectively correcting inaccurate localization in image feature representations. Extensive qualitative and quantitative experiments demonstrate that gaze-guided cognitive cues significantly enhance classification accuracy.

cs.CV↗

arXiv2024

Establishing Reality-Virtuality Interconnections in Urban Digital Twins for Superior Intelligent Road Inspection and Simulation

Road inspection is crucial for maintaining road serviceability and ensuring traffic safety, as road defects gradually develop and compromise functionality. Traditional inspection methods, which rely on manual evaluations, are labor-intensive, costly, and time-consuming. While data-driven approaches are gaining traction, the scarcity and spatial sparsity of real-world road defects present significant challenges in acquiring high-quality datasets. Existing simulators designed to generate detailed synthetic driving scenes, however, lack models for road defects. Moreover, advanced driving tasks that involve interactions with road surfaces, such as planning and control in defective areas, remain underexplored. To address these limitations, we propose a multi-modal sensor platform integrated with an urban digital twin (UDT) system for intelligent road inspection. First, hierarchical road models are constructed from real-world driving data collected using vehicle-mounted sensors, resulting in highly detailed representations of road defect structures and surface elevations. Next, digital road twins are generated to create simulation environments for comprehensive analysis and evaluation of algorithm performance. These scenarios are then imported into a simulator to facilitate both data acquisition and physical simulation. Experimental results demonstrate that driving tasks, including perception and decision-making, benefit significantly from the high-fidelity road defect scenes generated by our system.

cs.CV↗

arXiv2024

@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology

As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of performing multiple tasks simultaneously. However, benchmarking VLMs for ATs remains under-explored. To bridge this gap, we first create a novel AT benchmark (@Bench). Guided by a pre-design user study with PVIs, our benchmark includes the five most crucial vision-language tasks: Panoptic Segmentation, Depth Estimation, Optical Character Recognition (OCR), Image Captioning, and Visual Question Answering (VQA). Besides, we propose a novel AT model (@Model) that addresses all tasks simultaneously and can be expanded to more assistive functions for helping PVIs. Our framework exhibits outstanding performance across tasks by integrating multi-modal information, and it offers PVIs a more comprehensive assistance. Extensive experiments prove the effectiveness and generalizability of our framework.

cs.CV↗

arXiv2024

RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion

Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and fuses these features through attention mechanisms, demonstrating compelling efficacy in RGB-Normal road scene parsing. However, its performance significantly deteriorates when handling other types/sources of data or performing more universal, all-category scene parsing tasks. To overcome these limitations, this study introduces RoadFormer+, an efficient, robust, and adaptable model capable of effectively fusing RGB-X data, where ``X'', represents additional types/modalities of data such as depth, thermal, surface normal, and polarization. Specifically, we propose a novel hybrid feature decoupling encoder to extract heterogeneous features and decouple them into global and local components. These decoupled features are then fused through a dual-branch multi-scale heterogeneous feature fusion block, which employs parallel Transformer attentions and convolutional neural network modules to merge multi-scale features across different scales and receptive fields. The fused features are subsequently fed into a decoder to generate the final semantic predictions. Notably, our proposed RoadFormer+ ranks first on the KITTI Road benchmark and achieves state-of-the-art performance in mean intersection over union on the Cityscapes, MFNet, FMB, and ZJU datasets. Moreover, it reduces the number of learnable parameters by 65\% compared to RoadFormer. Our source code will be publicly available at mias.group/RoadFormerPlus.

cs.CV↗

arXiv2024

TiCoSS: Tightening the Coupling between Semantic Segmentation and Stereo Matching within A Joint Learning Framework

Semantic segmentation and stereo matching, respectively analogous to the ventral and dorsal streams in our human brain, are two key components of autonomous driving perception systems. Addressing these two tasks with separate networks is no longer the mainstream direction in developing computer vision algorithms, particularly with the recent advances in large vision models and embodied artificial intelligence. The trend is shifting towards combining them within a joint learning framework, especially emphasizing feature sharing between the two tasks. The major contributions of this study lie in comprehensively tightening the coupling between semantic segmentation and stereo matching. Specifically, this study introduces three novelties: (1) a tightly coupled, gated feature fusion strategy, (2) a hierarchical deep supervision strategy, and (3) a coupling tightening loss function. The combined use of these technical contributions results in TiCoSS, a state-of-the-art joint learning framework that simultaneously tackles semantic segmentation and stereo matching. Through extensive experiments on the KITTI and vKITTI2 datasets, along with qualitative and quantitative analyses, we validate the effectiveness of our developed strategies and loss function, and demonstrate its superior performance compared to prior arts, with a notable increase in mIoU by over 9%. Our source code will be publicly available at mias.group/TiCoSS upon publication.

cs.CV↗

arXiv2024

Enhanced Geological Prediction for Tunnel Excavation Using Full Waveform Inversion Integrating Sobolev Space Regularization with a Quadratic Penalty Method

In the process of tunnel excavation, advanced geological prediction technology has become indispensable for safe, economical, and efficient tunnel construction. Although traditional methods such as drilling and geological analysis are effective, they typically involve destructive processes, carry high risks, and incur significant costs. In contrast, non-destructive geophysical exploration offers a more convenient and economical alternative. However, the accuracy and precision of these non-destructive methods can be severely compromised by complex geological structures, restrictions on observation coverage and environmental noise. To address these challenges effectively, a novel approach using frequency domain full waveform inversion, based on a penalty method and Sobolev space regularization, has been proposed to enhance the performance of non-destructive predictions. The proposed method constructs a soft-constrained optimization problem by restructuring the misfit function into a combination of data misfit and wave equation drive terms to enhance convexity. Additionally, it semi-extends the search space to both the wavefield and the model parameters to mitigate the strong nonlinearity of the optimization, facilitating high-resolution inversion. Furthermore, a Sobolev space regularization algorithm is introduced to flexibly adjust the regularization path, addressing issues related to noise and artefacts to enhance the robustness of the algorithm. We evaluated the performance of the proposed full waveform inversion using several tunnel models with fault structures by comparing the results of the enhanced method with those of traditional least-squares-based Tikhonov regularization and total variation regularization full waveform inversion methods. The verification results confirm the superior capabilities of the proposed method as expected.

physics.geo-ph↗

arXiv2024

4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs

Although RDBs store vast amounts of rich, informative data spread across interconnected tables, the progress of predictive machine learning models as applied to such tasks arguably falls well behind advances in other domains such as computer vision or natural language processing. This deficit stems, at least in part, from the lack of established/public RDB benchmarks as needed for training and evaluation purposes. As a result, related model development thus far often defaults to tabular approaches trained on ubiquitous single-table benchmarks, or on the relational side, graph-based alternatives such as GNNs applied to a completely different set of graph datasets devoid of tabular characteristics. To more precisely target RDBs lying at the nexus of these two complementary regimes, we explore a broad class of baseline models predicated on: (i) converting multi-table datasets into graphs using various strategies equipped with efficient subsampling, while preserving tabular characteristics; and (ii) trainable models with well-matched inductive biases that output predictions based on these input subgraphs. Then, to address the dearth of suitable public benchmarks and reduce siloed comparisons, we assemble a diverse collection of (i) large-scale RDB datasets and (ii) coincident predictive tasks. From a delivery standpoint, we operationalize the above four dimensions (4D) of exploration within a unified, scalable open-source toolbox called 4DBInfer. We conclude by presenting evaluations using 4DBInfer, the results of which highlight the importance of considering each such dimension in the design of RDB predictive models, as well as the limitations of more naive approaches such as simply joining adjacent tables. Our source code is released at https://github.com/awslabs/multi-table-benchmark .

cs.LG↗

arXiv2024

HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion

Data-fusion networks have shown significant promise for RGB-thermal scene parsing. However, the majority of existing studies have relied on symmetric duplex encoders for heterogeneous feature extraction and fusion, paying inadequate attention to the inherent differences between RGB and thermal modalities. Recent progress in vision foundation models (VFMs) trained through self-supervision on vast amounts of unlabeled data has proven their ability to extract informative, general-purpose features. However, this potential has yet to be fully leveraged in the domain. In this study, we take one step toward this new research area by exploring a feasible strategy to fully exploit VFM features for RGB-thermal scene parsing. Specifically, we delve deeper into the unique characteristics of RGB and thermal modalities, thereby designing a hybrid, asymmetric encoder that incorporates both a VFM and a convolutional neural network. This design allows for more effective extraction of complementary heterogeneous features, which are subsequently fused in a dual-path, progressive manner. Moreover, we introduce an auxiliary task to further enrich the local semantics of the fused features, thereby improving the overall performance of RGB-thermal scene parsing. Our proposed HAPNet, equipped with all these components, demonstrates superior performance compared to all other state-of-the-art RGB-thermal scene parsing networks, achieving top ranks across three widely used public RGB-thermal scene parsing datasets. We believe this new paradigm has opened up new opportunities for future developments in data-fusion scene parsing approaches.

cs.CV↗