8 papers
RAHF-Net: Range-Aware Heterogeneous Fusion for LiDAR-Assisted RGB Semantic Segmentation
R. D. Lin, Pengcheng Weng, Ge Wang +2
This paper studies LiDAR-assisted RGB semantic segmentation, where LiDAR point-cloud features improve dense pixel-wise predictions in the RGB image plane rather than 3D point label…
Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits
Lishang Xu, Guodong Ma, Pengcheng Weng +1
Exploration in centralized serial-dictatorship matching bandits must use complete matchings, so learning one player-arm pair can impose regret on others. We study this externality…
DiFA: Dual Evidence Fusion and Aggregation for Token-Level Text Anomaly Detection
Yanyu Qian, Pengcheng Weng, Yue Tan +3
Text anomaly detection, the task of identifying text instances that deviate from normal language patterns, is crucial for language-driven applications. However, most existing metho…
TRE: Training-Free Hallucination Detection for Diffusion Language Models
Pengcheng Weng, Yanyu Qian, Yue Tan +1
Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination problem. Existing hallucina…
Purify-then-Align: Towards Robust Human Sensing under Modality Missing with Knowledge Distillation from Noisy Multimodal Teacher
Pengcheng Weng, Yanyu Qian, Yangxin Xu +1
Robust multimodal human sensing must overcome the critical challenge of missing modalities. Two principal barriers are the Representation Gap between heterogeneous data and the Con…
COMPASS: Fusion-Matched Supervision for Missing-Modality Human Sensing
Hao Wang, Yanyu Qian, Pengcheng Weng +4
Multimodal human activity recognition (HAR) and human pose estimation (HPE) must cope with modalities missing at inference. Completions generated for a fixed fusion model must pres…
Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion
Zixuan Xia, Hao Wang, Pengcheng Weng +4
Multimodal fusion is often treated as an optimization-balancing problem, where training signals are adjusted to prevent one modality from dominating the others. However, balanced o…
HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving
R. D. Lin, Pengcheng Weng, Yinqiao Wang +3
LiDAR point cloud semantic segmentation plays a crucial role in autonomous driving. In recent years, semi-supervised methods have gained popularity due to their significant reducti…