arXiv subjects

Yu Yang

Publications and source records attributed to Yu Yang.

At least 91 records · Page 5Linked to original sources

arXiv2025

PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis

Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models from limited real-world video data, especially for deformable objects with spatially-varying physical properties. To overcome the challenge of data scarcity, we propose PhysWorld, a novel framework that utilizes a simulator to synthesize physically plausible and diverse demonstrations to learn efficient world models. Specifically, we first construct a physics-consistent digital twin within MPM simulator via constitutive model selection and global-to-local optimization of physical properties. Subsequently, we apply part-aware perturbations to the physical properties and generate various motion patterns for the digital twin, synthesizing extensive and diverse demonstrations. Finally, using these demonstrations, we train a lightweight GNN-based world model that is embedded with physical properties. The real video can be used to further refine the physical properties. PhysWorld achieves accurate and fast future predictions for various deformable objects, and also generalizes well to novel interactions. Experiments show that PhysWorld has competitive performance while enabling inference speeds 47 times faster than the recent state-of-the-art method, i.e., PhysTwin.

cs.CV↗

arXiv2025

Large Language Model-Guided Semantic Alignment for Human Activity Recognition

Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in activity patterns, device types, and sensor placements create distribution gaps across datasets, reducing the performance of HAR models. To address this, we propose LanHAR, a novel system that leverages Large Language Models (LLMs) to generate semantic interpretations of sensor readings and activity labels for cross-dataset HAR. This approach not only mitigates cross-dataset heterogeneity but also enhances the recognition of new activities. LanHAR employs an iterative re-generation method to produce high-quality semantic interpretations with LLMs and a two-stage training framework that bridges the semantic interpretations of sensor readings and activity labels. This ultimately leads to a lightweight sensor encoder suitable for mobile deployment, enabling any sensor reading to be mapped into the semantic interpretation space. Experiments on five public datasets demonstrate that our approach significantly outperforms state-of-the-art methods in both cross-dataset HAR and new activity recognition. The source code is publicly available at https://github.com/DASHLab/LanHAR.

cs.CV↗

arXiv2025

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

As LLM-based agents are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging diverse resources, and managing dynamic user interactions. To address this gap, we introduce VitaBench, a challenging benchmark that evaluates agents on versatile interactive tasks grounded in real-world settings. Drawing from daily applications in food delivery, in-store consumption, and online travel services, VitaBench presents agents with the most complex life-serving simulation environment to date, comprising 66 tools. Through a framework that eliminates domain-specific policies, we enable flexible composition of these scenarios and tools, yielding 100 cross-scenario tasks (main results) and 300 single-scenario tasks. Each task is derived from multiple real user requests and requires agents to reason across temporal and spatial dimensions, utilize complex tool sets, proactively clarify ambiguous instructions, and track shifting user intent throughout multi-turn conversations. Moreover, we propose a rubric-based sliding window evaluator, enabling robust assessment of diverse solution pathways in complex environments and stochastic interactions. Our comprehensive evaluation reveals that even the most advanced models achieve only 30% success rate on cross-scenario tasks, and less than 50% success rate on others. Overall, we believe VitaBench will serve as a valuable resource for advancing the development of AI agents in practical real-world applications. The code, dataset, and leaderboard are available at https://vitabench.github.io/

cs.CL↗

arXiv2025

FTIN: Frequency-Time Integration Network for Inertial Odometry

Inertial odometry (IO) leverages inertial measurement unit (IMU) signals for cost-effective localization. However, high IMU sampling rates introduce substantial redundancy that impedes IO's ability to attend to salient components, thereby creating an information bottleneck. To address this challenge, we propose a cross-domain IO framework that fuses information from the frequency and time domains. Specifically, we exploit the global context and energy-compaction properties of frequency-domain representations to capture holistic motion patterns and alleviate the bottleneck. To the best of our knowledge, this is among the first attempts to incorporate frequency-domain feature processing into IO. Experimental results on multiple public datasets demonstrate the effectiveness of the proposed frequency--time-domain fusion strategy.

cs.RO↗

arXiv2025

CKANIO: Learnable Chebyshev Polynomials for Inertial Odometry

Inertial odometry (IO) relies exclusively on signals from an inertial measurement unit (IMU) for localization and offers a promising avenue for consumer grade positioning. However, accurate modeling of the nonlinear motion patterns present in IMU signals remains the principal limitation on IO accuracy. To address this challenge, we propose CKANIO, an IO framework that integrates Chebyshev based Kolmogorov-Arnold Networks (Chebyshev KAN). Specifically, we design a novel residual architecture that leverages the nonlinear approximation capabilities of Chebyshev polynomials within the KAN framework to more effectively model the complex motion characteristics inherent in IMU signals. To the best of our knowledge, this work represents the first application of an interpretable KAN model to IO. Experimental results on five publicly available datasets demonstrate the effectiveness of CKANIO.

cs.RO↗

arXiv2025

StarIO: A Lightweight Inertial Odometry for Nonlinear Motion

Inertial odometry (IO) directly estimates the position of a carrier from inertial sensor measurements and serves as a core technology for the widespread deployment of consumer grade localization systems. While existing IO methods can accurately reconstruct simple and near linear motion trajectories, they often fail to account for drift errors caused by complex motion patterns such as turning. This limitation significantly degrades localization accuracy and restricts the applicability of IO systems in real world scenarios. To address these challenges, we propose a lightweight IO framework. Specifically, inertial data is projected into a high dimensional implicit nonlinear feature space using the Star Operation method, enabling the extraction of complex motion features that are typically overlooked. We further introduce a collaborative attention mechanism that jointly models global motion dynamics across both channel and temporal dimensions. In addition, we design Multi Scale Gated Convolution Units to capture fine grained dynamic variations throughout the motion process, thereby enhancing the model's ability to learn rich and expressive motion representations. Extensive experiments demonstrate that our proposed method consistently outperforms SOTA baselines across six widely used inertial datasets. Compared to baseline models on the RoNIN dataset, it achieves reductions in ATE ranging from 2.26% to 65.78%, thereby establishing a new benchmark in the field.

cs.RO↗

arXiv2025

IONext: Unlocking the Next Era of Inertial Odometry

Researchers have increasingly adopted Transformer-based models for inertial odometry. While Transformers excel at modeling long-range dependencies, their limited sensitivity to local, fine-grained motion variations and lack of inherent inductive biases often hinder localization accuracy and generalization. Recent studies have shown that incorporating large-kernel convolutions and Transformer-inspired architectural designs into CNN can effectively expand the receptive field, thereby improving global motion perception. Motivated by these insights, we propose a novel CNN-based module called the Dual-wing Adaptive Dynamic Mixer (DADM), which adaptively captures both global motion patterns and local, fine-grained motion features from dynamic inputs. This module dynamically generates selective weights based on the input, enabling efficient multi-scale feature aggregation. To further improve temporal modeling, we introduce the Spatio-Temporal Gating Unit (STGU), which selectively extracts representative and task-relevant motion features in the temporal domain. This unit addresses the limitations of temporal modeling observed in existing CNN approaches. Built upon DADM and STGU, we present a new CNN-based inertial odometry backbone, named Next Era of Inertial Odometry (IONext). Extensive experiments on six public datasets demonstrate that IONext consistently outperforms state-of-the-art (SOTA) Transformer- and CNN-based methods. For instance, on the RNIN dataset, IONext reduces the average ATE by 10% and the average RTE by 12% compared to the representative model iMOT.

cs.CV↗

arXiv2025

Small Fleet, Big Impact: Enhancing Shared Micromobility Efficiency through Minimal Autonomous Vehicle Deployment

Shared micromobility systems, such as electric scooters and bikes, have gained widespread popularity as sustainable alternatives to traditional transportation modes. However, these systems face persistent challenges due to spatio-temporal demand fluctuations, often resulting in a mismatch between vehicle supply and user demand. Existing shared micromobility vehicle scheduling methods typically redistribute vehicles once or twice per day, which makes them vulnerable to performance degradation under atypical conditions. In this work, we design to augment existing micromobility scheduling methods by integrating a small number of autonomous shared micromobility vehicles (ASMVs), which possess self-rebalancing capabilities to dynamically adapt to real-time demand. Specifically, we introduce SMART, a hierarchical reinforcement learning framework that jointly optimizes high-level initial deployment and low-level real-time rebalancing for ASMVs. We evaluate our framework based on real-world e-scooter usage data from Chicago. Our experiment results show that our framework is highly effective and possesses strong generalization capability, allowing it to seamlessly integrate with existing vehicle scheduling methods and significantly enhance overall micromobility service performance.

cs.MA↗

arXiv2025

Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studies

Designing and evaluating personalized and proactive assistant agents remains challenging due to the time, cost, and ethical concerns associated with human-in-the-loop experimentation. Existing Human-Computer Interaction (HCI) methods often require extensive physical setup and human participation, which introduces privacy concerns and limits scalability. Simulated environments offer a partial solution but are typically constrained by rule-based scenarios and still depend heavily on human input to guide interactions and interpret results. Recent advances in large language models (LLMs) have introduced the possibility of generative agents that can simulate realistic human behavior, reasoning, and social dynamics. However, their effectiveness in modeling human-assistant interactions remains largely unexplored. To address this gap, we present a generative agent-based simulation platform designed to simulate human-assistant interactions. We identify ten prior studies on assistant agents that span different aspects of interaction design and replicate these studies using our simulation platform. Our results show that fully simulated experiments using generative agents can approximate key aspects of human-assistant interactions. Based on these simulations, we are able to replicate the core conclusions of the original studies. Our work provides a scalable and cost-effective approach for studying assistant agent design without requiring live human subjects. Additional resources and project materials are available at https://dash-gidea.github.io/

cs.HC↗

arXiv2025

STARC: See-Through-Wall Augmented Reality Framework for Human-Robot Collaboration in Emergency Response

In emergency response missions, first responders must navigate cluttered indoor environments where occlusions block direct line-of-sight, concealing both life-threatening hazards and victims in need of rescue. We present STARC, a see-through AR framework for human-robot collaboration that fuses mobile-robot mapping with responder-mounted LiDAR sensing. A ground robot running LiDAR-inertial odometry performs large-area exploration and 3D human detection, while helmet- or handheld-mounted LiDAR on the responder is registered to the robot's global map via relative pose estimation. This cross-LiDAR alignment enables consistent first-person projection of detected humans and their point clouds - rendered in AR with low latency - into the responder's view. By providing real-time visualization of hidden occupants and hazards, STARC enhances situational awareness and reduces operator risk. Experiments in simulation, lab setups, and tactical field trials confirm robust pose alignment, reliable detections, and stable overlays, underscoring the potential of our system for fire-fighting, disaster relief, and other safety-critical operations. Code and design will be open-sourced upon acceptance.

cs.RO↗

arXiv2025

SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI

Existing benchmarks for evaluating the security risks and capabilities (e.g., vulnerability detection) of code-generating large language models (LLMs) face several key limitations: (1) limited coverage of risk and capabilities; (2) reliance on static evaluation metrics such as LLM judgments or rule-based detection, which lack the precision of dynamic analysis; and (3) a trade-off between data quality and benchmark scale. To address these challenges, we introduce a general and scalable benchmark construction framework that begins with manually validated, high-quality seed examples and expands them via targeted mutations. Our approach provides a comprehensive suite of artifacts so the benchmark can support comprehensive risk assessment and security capability evaluation using dynamic metrics. By combining expert insights with automated generation, we strike a balance between manual effort, data quality, and benchmark scale. Applying this framework to Python, C/C++, and Java, we build SeCodePLT, a dataset of more than 5.9k samples spanning 44 CWE-based risk categories and three security capabilities. Compared with state-of-the-art benchmarks, SeCodePLT offers broader coverage, higher data fidelity, and substantially greater scale. We use SeCodePLT to evaluate leading code LLMs and agents, revealing their strengths and weaknesses in both generating secure code and identifying or fixing vulnerabilities.

cs.CR↗

arXiv2025

Modeling Adaptive Tracking of Predictable Stimuli in Electric Fish

The weakly electric fish \emph{Eigenmannia virescens} naturally swims back and forth to stay within a moving refuge, tracking its motion using visual and electrosensory feedback. Previous experiments show that when the refuge oscillates as a low-frequency sinusoid (below about 0.5 Hz), the tracking is nearly perfect, but phase lag increases and gain decreases at higher frequencies. Here, we model this nonlinear behavior as an adaptive internal model principle (IMP) system. Specifically, an adaptive state estimator identifies the \emph{a priori} unknown frequency, and feeds this parameter estimate into a closed-loop IMP-based system built around a lightly damped harmonic oscillator. We prove that the closed-loop tracking error of the IMP-based system, where the online adaptive frequency estimate is used as a surrogate for the unknown frequency, converges exponentially to that of an ideal control system with perfect information about the stimulus. Simulations further show that our model reproduces the fish refuge tracking Bode plot across a wide frequency range. These results establish the theoretical validity of combining the IMP with an adaptive identification process and provide a basic framework in adaptive sensorimotor control.

eess.SY↗

arXiv2025

DVDP: An End-to-End Policy for Mobile Robot Visual Docking with RGB-D Perception

Automatic docking has long been a significant challenge in the field of mobile robotics. Compared to other automatic docking methods, visual docking methods offer higher precision and lower deployment costs, making them an efficient and promising choice for this task. However, visual docking methods impose strict requirements on the robot's initial position at the start of the docking process. To overcome the limitations of current vision-based methods, we propose an innovative end-to-end visual docking method named DVDP(direct visual docking policy). This approach requires only a binocular RGB-D camera installed on the mobile robot to directly output the robot's docking path, achieving end-to-end automatic docking. Furthermore, we have collected a large-scale dataset of mobile robot visual automatic docking dataset through a combination of virtual and real environments using the Unity 3D platform and actual mobile robot setups. We developed a series of evaluation metrics to quantify the performance of the end-to-end visual docking method. Extensive experiments, including benchmarks against leading perception backbones adapted into our framework, demonstrate that our method achieves superior performance. Finally, real-world deployment on the SCOUT Mini confirmed DVDP's efficacy, with our model generating smooth, feasible docking trajectories that meet physical constraints and reach the target pose.

cs.RO↗

arXiv2025

Learning to Generate 4D LiDAR Sequences

While generative world models have advanced video and occupancy-based data synthesis, LiDAR generation remains underexplored despite its importance for accurate 3D perception. Extending generation to 4D LiDAR data introduces challenges in controllability, temporal stability, and evaluation. We present LiDARCrafter, a unified framework that converts free-form language into editable LiDAR sequences. Instructions are parsed into ego-centric scene graphs, which a tri-branch diffusion model transforms into object layouts, trajectories, and shapes. A range-image diffusion model generates the initial scan, and an autoregressive module extends it into a temporally coherent sequence. The explicit layout design further supports object-level editing, such as insertion or relocation. To enable fair assessment, we provide EvalSuite, a benchmark spanning scene-, object-, and sequence-level metrics. On nuScenes, LiDARCrafter achieves state-of-the-art fidelity, controllability, and temporal consistency, offering a foundation for LiDAR-based simulation and data augmentation.

cs.CV↗

arXiv2025

Mechanism of the quasi-elastic scattering based on the dinuclear system concept

A unified description of full reaction channels in low-energy heavy-ion collisions is a great challenge. Although the theoretical models based on the dinuclear system (DNS) concept have been successfully employed in multinucleon transfer (MNT) reactions, the underestimation of the quasi-elastic (QE) channel results in unreliable description of few nucleon transfer, especially for the light reaction systems. In this work, the DNS-sysu model is improved by introducing the impact-parameter-dependent transition probabilities for a unified description of few nucleon and many nucleon transfer in MNT reactions. Extensive experimental data -- including reactions such as 40Ca, 58Ni, 64Ni, 136Xe, and 208Pb + 208Pb -- were compared with the model predictions. The calculated isotopic distributions, mass distributions, and charge distributions show good agreement with experimental measurements. The improved DNS-sysu model enables reasonable characterization and description of the QE/grazing collisions, notably resolving long-standing underestimation in the QE channel.

nucl-th↗

arXiv2025

FedGraph: A Research Library and Benchmark for Federated Graph Learning

Federated graph learning is an emerging field with significant practical challenges. While algorithms have been proposed to improve the accuracy of training graph neural networks, such as node classification on federated graphs, the system performance is often overlooked, despite it is crucial for real-world deployment. To bridge this gap, we introduce FedGraph, a research library designed for practical distributed training and comprehensive benchmarking of FGL algorithms. FedGraph supports a range of state-of-the-art graph learning methods and includes a monitoring class that evaluates system performance, with a particular focus on communication and computation costs during training. Unlike existing federated learning platforms, FedGraph natively integrates homomorphic encryption to enhance privacy preservation and supports scalable deployment across multiple physical machines with system-level performance evaluation to guide the system design of future algorithms. To enhance efficiency and privacy, we propose a low-rank communication scheme for algorithms like FedGCN that require pre-training communication, accelerating both the pre-training and training phases. Extensive experiments benchmark FGL algorithms on three major graph learning tasks and demonstrate FedGraph as the first efficient FGL framework to support encrypted low-rank communication and scale to graphs with 100 million nodes.

cs.LG↗

arXiv2025

A correlated pseudo-marginal approach to doubly intractable problems

Doubly intractable models are encountered in a number of fields, e.g. social networks, ecology and epidemiology. Inference for such models requires the evaluation of a likelihood function, whose normalising factor depends on the model parameters and is assumed to be computationally intractable. The normalising constant of the posterior distribution and the additional normalising factor of the likelihood function result in a so-called doubly intractable posterior, for which it is difficult to directly apply Markov chain Monte Carlo methods. We propose a signed pseudo-marginal Metropolis-Hastings algorithm with an unbiased block-Poisson estimator to sample from the posterior distribution of doubly intractable models. As the estimator can be negative, the algorithm targets the absolute value of the estimated posterior and uses an importance sampling estimator to ensure simulation-consistent estimates of the posterior mean of a function of the parameters. The importance sampling estimator can perform poorly when its denominator is close to zero. We derive a finite-sample concentration inequality that ensures, with high probability, that this pathological case does not occur. Our estimator for doubly intractable problems has three advantages over existing estimators. First, the estimator is well-suited for efficient parallelisation and vectorisation. Second, its structure is ideal for correlated pseudo-marginal methods, which are well known to dramatically increase sampling efficiency. Third, the estimator enables the derivation of heuristic guidelines for tuning its hyperparameters under simplifying assumptions. We demonstrate the superior performance of our method in the standard benchmark example that models correlated spatial data using the Ising model, as well as the Kent distribution model for spherical data.

stat.ME↗

arXiv2025

Towards Scalable and Interpretable Mobile App Risk Analysis via Large Language Models

Mobile application marketplaces are responsible for vetting apps to identify and mitigate security risks. Current vetting processes are labor-intensive, relying on manual analysis by security professionals aided by semi-automated tools. To address this inefficiency, we propose Mars, a system that leverages Large Language Models (LLMs) for automated risk identification and profiling. Mars is designed to concurrently analyze multiple applications across diverse risk categories with minimal human intervention. To enhance analytical precision and operational efficiency, Mars leverages a pre-constructed risk identification tree to extract relevant indicators from high-dimensional application features. This initial step filters the data, reducing the input volume for the LLM and mitigating the potential for model hallucination induced by irrelevant features. The extracted indicators are then subjected to LLM analysis for final risk determination. Furthermore, Mars automatically generates a comprehensive evidence chain for each assessment, documenting the analytical process to provide transparent justification. These chains are designed to facilitate subsequent manual review and to inform enforcement decisions, such as application delisting. The performance of Mars was evaluated on a real-world dataset from a partner Android marketplace. The results demonstrate that Mars attained an F1-score of 0.838 in risk identification and an F1-score of 0.934 in evidence retrieval. To assess its practical applicability, a user study involving 20 expert analysts was conducted, which indicated that Mars yielded a substantial efficiency gain, ranging from 60% to 90%, over conventional manual analysis.

cs.CR↗