2 citations · 4 across the 14 of their papers we have counts for
15 papers
Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models
Rongguang Ye, Zhan Zhuang, Yichen Wu +2
Continually adapting large language models requires acquiring new knowledge while preserving previously learned capabilities. Jointly adapting model parameters and task-specific so…
OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization
Wei-Bin Kou, Guangxu Zhu, Ming Tang +4
The global deployment of edge intelligence operates across heterogeneous legal frameworks. While some regions permit centralized learning (CL) via cloud data aggregation, others en…
On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
Rongguang Ye, Ming Tang, Edith C. H. Ngai
As increasingly large pre-trained models are released, deploying them on edge devices for privacy-preserving applications requires effective compression. Recent works combine quant…
Adverse Weather-Independent Framework Towards Autonomous Driving Perception through Temporal Correlation and Unfolded Regularization
Wei-Bin Kou, Guangxu Zhu, Rongguang Ye +5
Various adverse weather conditions such as fog and rain pose a significant challenge to autonomous driving (AD) perception tasks like semantic segmentation, object detection, etc.…
One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models
Rongguang Ye, Ming Tang
Existing pruning methods for large language models (LLMs) focus on achieving high compression rates while maintaining model performance. Although these methods have demonstrated sa…
iMacHSR: Intermediate Multi-Access Heterogeneous Supervision and Regularization Scheme Toward Architecture-Agnostic Training
Wei-Bin Kou, Guangxu Zhu, Yichen Jin +4
While deep supervision is a powerful training strategy by supervising intermediate layers with auxiliary losses, it faces three underexplored problems: (I) Existing deep supervisio…
FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving
Wei-Bin Kou, Guangxu Zhu, Bingyang Cheng +3
Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization d…
Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning
Rongguang Ye, Ming Tang
Recent methods leverage a hypernet to handle the performance-fairness trade-offs in federated learning. This hypernet maps the clients' preferences between model performance and fa…
Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator
Wei-Bin Kou, Guangxu Zhu, Rongguang Ye +3
Learning-based street scene semantic understanding in autonomous driving (AD) has advanced significantly recently, but the performance of the AD model is heavily dependent on the q…
Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectory
Wei-Bin Kou, Qingfeng Lin, Ming Tang +5
To improve the generalization of the autonomous driving (AD) perception model, vehicles need to update the model over time based on the continuously collected data. As time progres…
Fast-Convergent and Communication-Alleviated Heterogeneous Hierarchical Federated Learning in Autonomous Driving
Wei-Bin Kou, Qingfeng Lin, Ming Tang +4
Street Scene Semantic Understanding (denoted as TriSU) is a complex task for autonomous driving (AD). However, inference model trained from data in a particular geographical region…
Generalizable Autonomous Driving System across Diverse Adverse Weather Conditions
Wei-Bin Kou, Guangxu Zhu, Rongguang Ye +4
Various adverse weather conditions pose a significant challenge to autonomous driving (AD) street scene semantic understanding (segmentation). A common strategy is to minimize the…
FedRC: A Rapid-Converged Hierarchical Federated Learning Framework in Street Scene Semantic Understanding
Wei-Bin Kou, Qingfeng Lin, Ming Tang +3
Street Scene Semantic Understanding (denoted as TriSU) is a crucial but complex task for world-wide distributed autonomous driving (AD) vehicles (e.g., Tesla). Its inference model…
pFedLVM: A Large Vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving
Wei-Bin Kou, Qingfeng Lin, Ming Tang +8
Deep learning-based Autonomous Driving (AD) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL)…
PraFFL: A Preference-Aware Scheme in Fair Federated Learning
Rongguang Ye, Wei-Bin Kou, Ming Tang
Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model among groups (e.g., male or female) of diverse sensitive features. However, th…