arXiv subjects

Zhe Han

Publications and source records attributed to Zhe Han.

At least 19 recordsLinked to original sources

arXiv2026

When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models

Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood. In this work, we present the first systematic multilingual evaluation of VLA models by translating the LIBERO benchmark into ten languages, revealing severe performance degradation under non-English instructions, with success rates dropping by 30-50%. Through fine-grained analysis of task executions, we find that language influence is highly non-uniform across steps: certain steps exhibit strong language dependence and dominate overall task failure, while others are largely language-agnostic. Based on this insight, we propose a step-wise inference-time intervention that aligns representations according to step language sensitivity, substantially improving performance under linguistic variation. Our results indicate that language robustness in VLA models is fundamentally a step-wise control problem, highlighting the importance of temporally structured analysis for reliable embodied agents.

cs.CL↗

arXiv2026

Deep learning-based pavement performance modeling using multiple distress indicators and road work history

The deterioration of pavement is a complex and dynamic process determined by different factors including material, environment, design, and some other unobserved variables. Accurate predictions of pavement condition can help maximize the use of available resources for pavement management agencies through better coordinated preservation and maintenance activities. This paper uses deep neural networks such as the convolutional neural network (CNN) and the long short-term memory (LSTM) to model the pavement deterioration process. In this paper, pavement condition data and maintenance and rehabilitation history collected by the Texas Department of Transportation over the past 18 years were used. Twenty-one flexible pavement condition indicators, including cracking, rutting, raveling, and roughness, collected from more than 100,000 pavement sections were included in the proposed models. Promising preliminary results were obtained. Case study results show that the proposed CNN model outperforms standard machine learning models in predicting pavement condition values.

cs.LG↗

arXiv2026

EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents

Scientific research follows multi-turn, multi-step workflows that require proactively searching the literature, consulting figures and tables, and integrating evidence across papers to align experimental settings and support reproducible conclusions. This joint capability is not systematically assessed in existing benchmarks, which largely under-evaluate proactive search, multi-evidence integration and sustained evidence use over time. In this work, we introduce EpiBench, an episodic multi-turn multimodal benchmark that instantiates short research workflows. Given a research task, agents must navigate across papers over multiple turns, align evidence from figures and tables, and use the accumulated evidence in the memory to answer objective questions that require cross paper comparisons and multi-figure integration. EpiBench introduces a process-level evaluation framework for fine-grained testing and diagnosis of research agents. Our experiments show that even the leading model achieves an accuracy of only 29.23% on the hard split, indicating substantial room for improvement in multi-turn, multi-evidence research workflows, providing an evaluation platform for verifiable and reproducible research agents.

cs.CL↗

arXiv2026

Learning From a Steady Hand: A Weakly Supervised Agent for Robot Assistance under Microscopy

This paper rethinks steady-hand robotic manipulation by using a weakly supervised framework that fuses calibration-aware perception with admittance control. Unlike conventional automation that relies on labor-intensive 2D labeling, our framework leverages reusable warm-up trajectories to extract implicit spatial information, thereby achieving calibration-aware, depth-resolved perception without the need for external fiducials or manual depth annotation. By explicitly characterizing residuals from observation and calibration models, the system establishes a task-space error budget from recorded warm-ups. The uncertainty budget yields a lateral closed-loop accuracy of approx. 49 micrometers at 95% confidence (worst-case testing subset) and a depth accuracy of <= 291 micrometers at 95% confidence bound during large in-plane moves. In a within-subject user study (N=8), the learned agent reduces overall NASA-TLX workload by 77.1% relative to the simple steady-hand assistance baseline. These results demonstrate that the weakly supervised agent improves the reliability of microscope-guided biomedical micromanipulation without introducing complex setup requirements, offering a practical framework for microscope-guided intervention.

cs.RO↗

arXiv2025

HL-IK: A Lightweight Implementation of Human-Like Inverse Kinematics in Humanoid Arms

Traditional IK methods for redundant humanoid manipulators emphasize end-effector (EE) tracking, frequently producing configurations that are valid mechanically but not human-like. We present Human-Like Inverse Kinematics (HL-IK), a lightweight IK framework that preserves EE tracking while shaping whole-arm configurations to appear human-like, without full-body sensing at runtime. The key idea is a learned elbow prior: using large-scale human motion data retargeted to the robot, we train a FiLM-modulated spatio-temporal attention network (FiSTA) to predict the next-step elbow pose from the EE target and a short history of EE-elbow states.This prediction is incorporated as a small residual alongside EE and smoothness terms in a standard Levenberg-Marquardt optimizer, making HL-IK a drop-in addition to numerical IK stacks. Over 183k simulation steps, HL-IK reduces arm-similarity position and direction error by 30.6% and 35.4% on average, and by 42.2% and 47.4% on the most challenging trajectories. Hardware teleoperation on a robot distinct from simulation further confirms the gains in anthropomorphism. HL-IK is simple to integrate, adaptable across platforms via our pipeline, and adds minimal computation, enabling human-like motions for humanoid robots.

cs.RO↗

arXiv2025

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs

This paper presents the development of an AI-powered workflow that uses Large Language Models (LLMs) to assist in drafting schematic architectural floor plans from natural language prompts. The proposed system interprets textual input to automatically generate layout options including walls, doors, windows, and furniture arrangements. It combines prompt engineering, a furniture placement refinement algorithm, and Python scripting to produce spatially coherent draft plans compatible with design tools such as Autodesk Revit. A case study of a mid-sized residential layout demonstrates the approach's ability to generate functional and structured outputs with minimal manual effort. The workflow is designed for transparent replication, with all key prompt specifications documented to enable independent implementation by other researchers. In addition, the generated models preserve the full range of Revit-native parametric attributes required for direct integration into professional BIM processes.

cs.AI↗

arXiv2025

ROBUST-MIPS: A Combined Skeletal Pose and Instance Segmentation Dataset for Laparoscopic Surgical Instruments

Localisation of surgical tools constitutes a foundational building block for computer-assisted interventional technologies. Works in this field typically focus on training deep learning models to perform segmentation tasks. Performance of learning-based approaches is limited by the availability of diverse annotated data. We argue that skeletal pose annotations are a more efficient annotation approach for surgical tools, striking a balance between richness of semantic information and ease of annotation, thus allowing for accelerated growth of available annotated data. To encourage adoption of this annotation style, we present, ROBUST-MIPS, a combined tool pose and tool instance segmentation dataset derived from the existing ROBUST-MIS dataset. Our enriched dataset facilitates the joint study of these two annotation styles and allow head-to-head comparison on various downstream tasks. To demonstrate the adequacy of pose annotations for surgical tool localisation, we set up a simple benchmark using popular pose estimation methods and observe high-quality results. To ease adoption, together with the dataset, we release our benchmark models and custom tool pose annotation software.

cs.CV↗

arXiv2025

Collaborative Human-Robot Surgery for Mandibular Angle Split Osteotomy: Optical Tracking based Approach

Mandibular Angle Split Osteotomy (MASO) is a significant procedure in oral and maxillofacial surgery. Despite advances in technique and instrumentation, its success still relies heavily on the surgeon's experience. In this work, a human-robot collaborative system is proposed to perform MASO according to a preoperative plan and under guidance of a surgeon. A task decomposition methodology is used to divide the collaborative surgical procedure into three subtasks: (1) positional control and (2) orientation control, both led by the robot for precise alignment; and (3) force-control, managed by surgeon to ensure safety. Additionally, to achieve patient tracking without the need for a skull clamp, an optical tracking system (OTS) is utilized. Movement of the patient mandibular is measured with an optical-based tracker mounted on a dental occlusal splint. A registration method and Robot-OTS calibration method are introduced to achieve reliable navigation within our framework. The experiments of drilling were conducted on the realistic phantom model, which demonstrated that the average error between the planned and actual drilling points is 1.85mm.

cs.RO↗

arXiv2025

Large Language Model-Driven Code Compliance Checking in Building Information Modeling

This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling (BIM) by introducing a Large Language Model (LLM)-driven approach to semi-automate this critical process. The developed system integrates LLMs such as GPT, Claude, Gemini, and Llama, with Revit software to interpret building codes, generate Python scripts, and perform semi-automated compliance checks within the BIM environment. Case studies on a single-family residential project and an office building project demonstrated the system's ability to reduce the time and effort required for compliance checks while improving accuracy. It streamlined the identification of violations, such as non-compliant room dimensions, material usage, and object placements, by automatically assessing relationships and generating actionable reports. Compared to manual methods, the system eliminated repetitive tasks, simplified complex regulations, and ensured reliable adherence to standards. By offering a comprehensive, adaptable, and cost-effective solution, this proposed approach offers a promising advancement in BIM-based compliance checking, with potential applications across diverse regulatory documents in construction projects.

cs.SE↗

arXiv2025

Dual Teacher-Student Learning for Semi-supervised Medical Image Segmentation

Semi-supervised learning reduces the costly manual annotation burden in medical image segmentation. A popular approach is the mean teacher (MT) strategy, which applies consistency regularization using a temporally averaged teacher model. In this work, the MT strategy is reinterpreted as a form of self-paced learning in the context of supervised learning, where agreement between the teacher's predictions and the ground truth implicitly guides the model from easy to hard. Extending this insight to semi-supervised learning, we propose dual teacher-student learning (DTSL). It regulates the learning pace on unlabeled data using two signals: a temporally averaged signal from an in-group teacher and a cross-architectural signal from a student in a second, distinct model group. Specifically, a novel consensus label generator (CLG) creates the pseudo-labels from the agreement between these two signals, establishing an effective learning curriculum. Extensive experiments on four benchmark datasets demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches. Remarkably, on three of the four datasets, our semi-supervised method with limited labeled data surpasses its fully supervised counterparts, validating the effectiveness of our self-paced learning design.

cs.CV↗

arXiv2025

Intelligent Spatial Perception by Building Hierarchical 3D Scene Graphs for Indoor Scenarios with the Help of LLMs

This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to construct hierarchical 3D Scene Graphs (3DSGs) for indoor scenarios. The proposed framework constructs 3DSGs consisting of a fundamental layer with rich metric-semantic information, an object layer featuring precise point-cloud representation of object nodes as well as visual descriptors, and higher layers of room, floor, and building nodes. Thanks to the innovative application of LLMs, not only object nodes but also nodes of higher layers, e.g., room nodes, are annotated in an intelligent and accurate manner. A polling mechanism for room classification using LLMs is proposed to enhance the accuracy and reliability of the room node annotation. Thorough numerical experiments demonstrate the system's ability to integrate semantic descriptions with geometric data, creating an accurate and comprehensive representation of the environment instrumental for context-aware navigation and task planning.

cs.RO↗

arXiv2024

Semi-Autonomous Laparoscopic Robot Docking with Learned Hand-Eye Information Fusion

In this study, we introduce a novel shared-control system for key-hole docking operations, combining a commercial camera with occlusion-robust pose estimation and a hand-eye information fusion technique. This system is used to enhance docking precision and force-compliance safety. To train a hand-eye information fusion network model, we generated a self-supervised dataset using this docking system. After training, our pose estimation method showed improved accuracy compared to traditional methods, including observation-only approaches, hand-eye calibration, and conventional state estimation filters. In real-world phantom experiments, our approach demonstrated its effectiveness with reduced position dispersion (1.23\pm 0.81 mm vs. 2.47 \pm 1.22 mm) and force dispersion (0.78\pm 0.57 N vs. 1.15 \pm 0.97 N) compared to the control group. These advancements in semi-autonomy co-manipulation scenarios enhance interaction and stability. The study presents an anti-interference, steady, and precision solution with potential applications extending beyond laparoscopic surgery to other minimally invasive procedures.

cs.RO↗

arXiv2024

Serre functor and torsion pairs

Given a torsion pair $(\mathcal{T},\mathcal{F})$ in an abelian category $\mathcal{A}$ and its Happel-Reiten-Smal{\o} tilt $\mathcal{B}$, the equivalence of the realization functor $D^b({\mathcal B})\to D^b({\mathcal A})$ is determined by some properties of the torsion pair [9]. We call $(\mathcal{T},\mathcal{F})$ satisfying such a property effaceable. If $\mathcal{A}$ is an Ext-finite abelian category with Serre duality, we prove that $(\mathcal{T},\mathcal{F})$ is effaceable implies that $\mathcal{U}_{\mathcal T}$ is closed under Serre functor. Conversely, when $\mathcal A$ is the module category of a finite-dimensional hereditary algebra, we prove that the torsion pair $(\mathcal{T},\mathcal{F})$ is effaceable if and only if $\mathcal{U}_\mathcal{T}$ is closed under the Serre functor via a recollement of $D^b({\mathcal A})$.

math.RT↗

arXiv2024

Excitation Trajectory Optimization for Dynamic Parameter Identification Using Virtual Constraints in Hands-on Robotic System

This paper proposes a novel, more computationally efficient method for optimizing robot excitation trajectories for dynamic parameter identification, emphasizing self-collision avoidance. This addresses the system identification challenges for getting high-quality training data associated with co-manipulated robotic arms that can be equipped with a variety of tools, a common scenario in industrial but also clinical and research contexts. Utilizing the Unified Robotics Description Format (URDF) to implement a symbolic Python implementation of the Recursive Newton-Euler Algorithm (RNEA), the approach aids in dynamically estimating parameters such as inertia using regression analyses on data from real robots. The excitation trajectory was evaluated and achieved on par criteria when compared to state-of-the-art reported results which didn't consider self-collision and tool calibrations. Furthermore, physical Human-Robot Interaction (pHRI) admittance control experiments were conducted in a surgical context to evaluate the derived inverse dynamics model showing a 30.1\% workload reduction by the NASA TLX questionnaire.

cs.RO↗

arXiv2023

Cluster braid groups of Coxeter-Dynkin diagrams

Cluster exchange groupoids are introduced by King-Qiu as an enhancement of cluster exchange graphs to study stability conditions and quadratic differentials. In this paper, we introduce the exchange groupoid for any finite Coxeter-Dynkin diagram $\Delta$ and show that the fundamental group of which is isomorphic to the corresponding braid group associated with $\Delta$.

math.CO↗

arXiv2023

Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppression

This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation. Specifically, after linear filtering, we split the full-band signal into wide-band (16KHz) and high-band (16-48KHz) for residual echo removal with lower modeling difficulty. The wide-band signal is processed by an updated gated convolutional recurrent network (GCRN) with U$^2$ encoder while the high-band signal is processed by a high-band post-filter net with lower complexity. Our approach submitted to ICASSP 2023 AEC Challenge has achieved an overall mean opinion score (MOS) of 4.344 and a word accuracy (WAcc) ratio of 0.795, leading to the 2$^{nd}$ (tied) in the ranking of the non-personalized track.

eess.AS↗

arXiv2018

$p$-adic singular integral and their commutator in generalized Morrey space

For a prime number $p,$ let $\mathbb{Q}_p$ be the field of $p$-adic numbers. In this paper, we established the boundedness of a class of $p$-adic singular integral operators on the $p$-adic generalized Morrey spaces. The corresponding boundedness for the commutators generalized by the $p$-adic singular integral operators and $p$-adic Lipschitz functions or $p$-adic generalized Campanato functions is also considered.

math.FA↗

arXiv2018

Derived equivalences via HRS-tilting

Let $\mathcal{A}$ be an abelian category and $\mathcal{B}$ be the Happel-Reiten-Smal{\o} tilt of $\mathcal{A}$ with respect to a torsion pair. We give necessary and sufficient conditions for the existence of a derived equivalence between $\mathcal{B}$ and $\mathcal{A}$, which is compatible with the inclusion of $\mathcal{B}$ into the derived category of $\mathcal{A}$. In particular, any splitting torsion pair induces a derived equivalence. We prove that for the realization functor of any bounded $t$-structure, its denseness implies its fully-faithfulness.

math.RT↗