Publications
Peer-reviewed papers and preprints.
Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification
Chuanhang Qiu, Yanran Xu, Yue Wang, Anthony Bagnall
arXiv preprint arXiv:2609.00093 2026
A post-hoc feature augmentation module that measures local exposure and class-mixture risk, then appends a signed residual drawn from nearby training geometry. Evaluated on the UCR / Bake Off Redux benchmarks.
Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning
Yue Wang, Yanran Xu, Wenbo Wu, Chuanhang Qiu, Zhaoxing Li
International Conference on Artificial Neural Networks (ICANN) 2026
A floating-base robot dynamics library written in plain PyTorch, covering URDF parsing, FK, Jacobians, RNEA, CRBA, ABA and autodiff. On an H200 at batch 4096 it reaches 64x and 63x the throughput of Pinocchio for FK and Jacobians.
GAFT: Geo-Anchored Fine-Tuning for Hazard Identification from Rare Failures
Yanran Xu, Chuanhang Qiu, Yue Wang, Wenbo Wu, Zhaoxing Li
Pacific Rim International Conference on Artificial Intelligence (PRICAI) 2026
Parameter-efficient adaptation of vision foundation models for off-road navigation, using geometry-derived priors to steer LoRA adaptation so that pretrained representations survive fine-tuning on very few failure cases.
SPARC: Spine with Prismatic And Revolute Compliance for Faster Quadrupedal Bounding
Yue Wang, Yanran Xu
arXiv preprint arXiv:2510.01984 2025
A 1.26 kg three-DoF sagittal spine module that combines revolute and prismatic compliance, with a floating-base impedance controller that sets stiffness and damping in task space. Across 97 bounding runs on an 8-DoF quadruped it reached 1.029 m/s, 1.53x the rigid-spine maximum. First posted October 2025, latest revision September 2026.
HMCF: A Human-in-the-Loop Multi-Robot Collaboration Framework Based on Large Language Models
Zhaoxing Li, Wenbo Wu, Yue Wang, Yanran Xu, William Hunt, Sebastian Stein
International Conference on Principles and Practice of Multi-Agent Systems (PRIMA) 2025
Task allocation and safe execution across human supervisors, LLM agents and a heterogeneous robot fleet.
Quattro: Transformer-Accelerated Iterative Linear Quadratic Regulator Framework for Fast Trajectory Optimization
Yue Wang, Haoyu Wang, Zhaoxing Li
IEEE Conference on Decision and Control (CDC) 2025
A Transformer predicts the feedback and feedforward matrices of iLQR in parallel, cutting the sequential bottleneck. Up to 27x faster per optimisation iteration on a quadrotor, 17.8x on the full MPC loop, and 27.3x once deployed on FPGA.