collaborators

7 papers

cs.LG2026

MP3: Multi-Period Pattern Pre-training for Spatio-Temporal Forecasting

Lilan Peng, Yandi Liu, Qingren Yao +2

Spatio-Temporal forecasting is crucial in diverse fields, such as transportation, climate, and energy. Urban spatio-temporal data exhibits temporal mirage: similar short-window inp…

cs.CV2026

Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

Pedro Alonso, Chongshou Li, Tianrui Li

Despite extensive progress in point cloud robustness, existing methods primarily rely on augmentation strategies or defense mechanisms while overlooking the geometric nature of adv…

cs.CV2026

Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification

Jun Chen, Xinke Li, Mingyue Xu +2

Gradient-based adversarial attacks are widely used to evaluate the robustness of 3D point cloud classifiers, yet they often rely on uniform update rules that neglect point-wise het…

cs.CV2025

ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification

Pedro Alonso, Tianrui Li, Chongshou Li

We introduce ModelNet40-E, a new benchmark designed to assess the robustness and calibration of point cloud classification models under synthetic LiDAR-like noise. Unlike existing…

cs.CV2025

GeoCD: A Differential Local Approximation for Geodesic Chamfer Distance

Pedro Alonso, Tianrui Li, Chongshou Li

Chamfer Distance (CD) is a widely adopted metric in 3D point cloud learning due to its simplicity and efficiency. However, it suffers from a fundamental limitation: it relies solel…

cs.CV2025

LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning

Chenxi Li, Nuo Chen, Fengyun Tan +4

We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical la…