PRISM maintains per-expert gradient subspace bases preserved under FedAvg to resolve spurious isolation in federated multimodal continual learning, outperforming 16 baselines with larger gains on longer task sequences.
Model-Free Cooperative Optimal Output Regulation for Linear Discrete-Time Multi-Agent Systems Using Reinforcement Learning,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
TiLP integrates network, training, and task sub-twins into a digital twin and uses receding-horizon cross-entropy planning with actor-critic guidance to jointly optimize resource allocation in federated split learning, improving task success by 9.5 percentage points on robotic tasks.
A new dual-timescale FCL framework with layer-selective rehearsal and knowledge recovery improves mIoU by up to 8.3% in federated settings for autonomous systems.
citing papers explorer
-
PRISM: Exposing and Resolving Spurious Isolation in Federated Multimodal Continual Learning
PRISM maintains per-expert gradient subspace bases preserved under FedAvg to resolve spurious isolation in federated multimodal continual learning, outperforming 16 baselines with larger gains on longer task sequences.
-
Application-Aware Twin-in-the-Loop Planning for Federated Split Learning over Wireless Edge Networks
TiLP integrates network, training, and task sub-twins into a digital twin and uses receding-horizon cross-entropy planning with actor-critic guidance to jointly optimize resource allocation in federated split learning, improving task success by 9.5 percentage points on robotic tasks.
-
Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems
A new dual-timescale FCL framework with layer-selective rehearsal and knowledge recovery improves mIoU by up to 8.3% in federated settings for autonomous systems.