3 citations · 6 across the 15 of their papers we have counts for
6 papers · 1 filter
CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning
Xiang Zou, Shengzhu Shi, Junqi Gao +1
Reliable temporal-difference targets are central to off-policy actor-critic learning. Direct value improvement refines the next-state target with alternative actions, but the relia…
Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
Junqi Gao, Dazhi Zhang, Zhichang Guo +3
Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dyna…
PDAC: Efficient Coreset Selection for Continual Learning via Probability Density Awareness
Junqi Gao, Zhichang Guo, Dazhi Zhang +3
Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of…
Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
Junqi Gao, Zhichang Guo, Dazhi Zhang +5
Heterogeneous Large Language Model (LLM) fusion integrates the strengths of multiple source LLMs with different architectures into a target LLM with low computational overhead. Whi…
Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
Junqi Gao, Biqing Qi, Yao Li +4
The transferability of adversarial perturbations provides an effective shortcut for black-box attacks. Targeted perturbations have greater practicality but are more difficult to tr…
PINNsFailureRegion Localization and Refinement through White-box AdversarialAttack
Shengzhu Shi, Yao Li, Zhichang Guo +2
Physics-informed neural networks (PINNs) have shown great promise in solving partial differential equations (PDEs). However, vanilla PINNs often face challenges when solving comple…