7 papers
FedDSR: Federated Deep Supervision and Regularization Towards Autonomous Driving
Wei-Bin Kou, Guangxu Zhu, Bingyang Cheng +3
Federated Learning (FL) enables collaborative training of autonomous driving (AD) models across distributed vehicles while preserving data privacy. However, FL encounters critical…
Statistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving
Wei-Bin Kou, Guangxu Zhu, Jingreng Lei +3
Autonomous driving (AD) scenarios are inherently complex and diverse, posing significant challenges for a single deep learning model to effectively cover all possible conditions, s…
ELPO: Ensemble Learning Based Prompt Optimization for Large Language Models
Qing Zhang, Bing Xu, Xudong Zhang +9
The remarkable performance of Large Language Models (LLMs) highly relies on crafted prompts. However, manual prompt engineering is a laborious process, creating a core bottleneck f…
Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modeling
Chen Zhang, Weixin Bu, Wendong Xu +3
Transformers have achieved remarkable success in time series modeling, yet their internal mechanisms remain opaque. This work demystifies the Transformer encoder by establishing it…
Aligning Effective Tokens with Video Anomaly in Large Language Models
Yingxian Chen, Jiahui Liu, Ruidi Fan +6
Understanding abnormal events in videos is a vital and challenging task that has garnered significant attention in a wide range of applications. Although current video understandin…
Nonparametric Teaching for Graph Property Learners
Chen Zhang, Weixin Bu, Zeyi Ren +3
Inferring properties of graph-structured data, e.g., the solubility of molecules, essentially involves learning the implicit mapping from graphs to their properties. This learning…
Shadow-FT: Tuning Instruct Model via Training on Paired Base Model
Taiqiang Wu, Runming Yang, Jiayi Li +4
Large language models (LLMs) consistently benefit from further fine-tuning on various tasks. However, we observe that directly tuning the Instruct (i.e., instruction-tuned) models…