5 papers
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…
COMPASS: Complete Multimodal Fusion via Proxy Tokens and Shared Spaces for Ubiquitous Sensing
Hao Wang, Yanyu Qian, Pengcheng Weng +4
Missing modalities in multimodal sensing cause not only information loss but also a fusion-interface mismatch: a fusion head trained on a canonical set of modality slots must opera…
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…
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…
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…