Picture for Ziqing Fan

Ziqing Fan

Continual Task Learning through Adaptive Policy Self-Composition

Add code
Nov 18, 2024
Figure 1 for Continual Task Learning through Adaptive Policy Self-Composition
Figure 2 for Continual Task Learning through Adaptive Policy Self-Composition
Figure 3 for Continual Task Learning through Adaptive Policy Self-Composition
Figure 4 for Continual Task Learning through Adaptive Policy Self-Composition
Viaarxiv icon

Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning

Add code
Nov 02, 2024
Viaarxiv icon

Reconstruct the Pruned Model without Any Retraining

Add code
Jul 18, 2024
Viaarxiv icon

Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts

Add code
May 29, 2024
Figure 1 for Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
Figure 2 for Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
Figure 3 for Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
Figure 4 for Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
Viaarxiv icon

Federated Learning with Bilateral Curation for Partially Class-Disjoint Data

Add code
May 29, 2024
Viaarxiv icon

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization

Add code
May 29, 2024
Figure 1 for Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
Figure 2 for Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
Figure 3 for Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
Figure 4 for Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
Viaarxiv icon

Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping

Add code
May 29, 2024
Viaarxiv icon

HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning

Add code
May 28, 2024
Viaarxiv icon

Q-value Regularized Transformer for Offline Reinforcement Learning

Add code
May 27, 2024
Viaarxiv icon

FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation

Add code
Dec 14, 2022
Figure 1 for FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
Figure 2 for FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
Figure 3 for FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
Figure 4 for FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
Viaarxiv icon