papers

Publications (20)

cs.RO2026

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

Huanyu Tian, Martin Huber, Lingyun Zeng +7

This paper rethinks steady-hand robotic manipulation by using a weakly supervised framework that fuses calibration-aware perception with admittance control. Unlike conventional aut…

cs.AI2025

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

Jayakrishna Duggempudi, Lu Gao, Ahmed Senouci +2

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…

math.RT2014

A note on generic objects and locally finite triangulated categories

Zhe Han

We show that the homotopy category of injective -modules is generically trivial if and only if the derived category of all modules is generically trivial for an algebra . Mor…

cs.LG2026

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

Lu Gao, Zhe Han, Yunshen Chen

The deterioration of pavement is a complex and dynamic process determined by different factors including material, environment, design, and some other unobserved variables. Accurat…

cs.CL2026

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

Xuan Dong, Zhe Han, Tianhao Niu +2

Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understo…

math.FA2018

-adic singular integral and their commutator in generalized Morrey space

Huixia Mo, Zhe Han, Liu Yang

For a prime number let be the field of -adic numbers. In this paper, we established the boundedness of a class of -adic singular integral operators on the…

cs.RO2025

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

Yao Cheng, Zhe Han, Fengyang Jiang +4

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 harnesse…

cs.RO2024

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

Huanyu Tian, Martin Huber, Christopher E. Mower +4

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 inform…

cs.RO2024

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

Huanyu Tian, Martin Huber, Christopher E. Mower +4

This paper proposes a novel, more computationally efficient method for optimizing robot excitation trajectories for dynamic parameter identification, emphasizing self-collision avo…

math.CO2023

Cluster braid groups of Coxeter-Dynkin diagrams

Zhe Han, Ping He, Yu Qiu

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 intr…

cs.RO2026

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

Bingjie Chen, Zihan Wang, Zhe Han +3

Traditional IK methods for redundant humanoid manipulators emphasize end-effector (EE) tracking, frequently producing configurations that are valid mechanically but not human-like.…

math.RT2025

Serre functor and torsion pairs

Zhe Han, Ping He

Given a torsion pair in an abelian category and its Happel-Reiten-Smalø tilt , the equivalence of the realization functor $D…

math.RT2018

Derived equivalences via HRS-tilting

Xiao-Wu Chen, Zhe Han, Yu Zhou

Let be an abelian category and be the Happel-Reiten-Smalø tilt of with respect to a torsion pair. We give necessary and sufficient condit…

cs.CV2025

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

Pengchen Zhang, Alan J. X. Guo, Sipin Luo +2

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…

cs.CL2026

EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents

Xuan Dong, Huanyang Zheng, Tianhao Niu +7

Scientific research follows multi-turn, multi-step workflows that require proactively searching the literature, consulting figures and tables, and integrating evidence across paper…

cs.RO2025

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

Zhe Han, Huanyu Tian, Tom Vercauteren +3

Mandibular Angle Split Osteotomy (MASO) is a significant procedure in oral and maxillofacial surgery. Despite advances in technique and instrumentation, its success still relies he…

math.CO2015

Two coloring problems on matrix graphs

Zhe Han, Mei Lu

In this paper, we propose a new family of graphs, matrix graphs, whose vertex set is the set of all matrices over a finite field $\mathbb{F}_…

cs.SE2025

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

Soumya Madireddy, Lu Gao, Zia Din +4

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 (L…

cs.CV2026

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

Zhe Han, Charlie Budd, Gongyu Zhang +3

Localisation of surgical tools constitutes a foundational building block for computer-assisted interventional technologies. Works in this field typically focus on training deep lea…

eess.AS2023

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

Zihan Zhang, Shimin Zhang, Mingshuai Liu +4

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 sig…