PBSD derives a reward-reweighted teacher distribution as the analytic optimum of a reward-regularized objective, yielding better stability and performance than KL-based self-distillation on math reasoning and tool-use tasks.
Pfeddst: Personalized federated learning with de- centralized selection training,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
Murmura uses epistemic uncertainty from Dirichlet evidential models to score peer compatibility and enable selective trust-aware aggregation for personalized models in decentralized federated learning on non-IID wearable IoT data.
citing papers explorer
-
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
PBSD derives a reward-reweighted teacher distribution as the analytic optimum of a reward-regularized objective, yielding better stability and performance than KL-based self-distillation on math reasoning and tool-use tasks.
-
On What We Can Learn from Low-Resolution Data
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
-
Evidential Trust-Aware Model Personalization in Decentralized Federated Learning for Wearable IoT
Murmura uses epistemic uncertainty from Dirichlet evidential models to score peer compatibility and enable selective trust-aware aggregation for personalized models in decentralized federated learning on non-IID wearable IoT data.