H2Tune enables federated fine-tuning across heterogeneous foundation models by sharing sparsified rank-aligned middle matrices with learned layer mappings and alternating shared/private updates.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
H2Tune: Federated Foundation Model Fine-Tuning with Hybrid Heterogeneity
H2Tune enables federated fine-tuning across heterogeneous foundation models by sharing sparsified rank-aligned middle matrices with learned layer mappings and alternating shared/private updates.