SLAD uses shared LoRA adapters in joint training to align teacher-student features, boosting both models' performance and halving training time versus fine-tuning in distillation.
Effect of LoRA Rank We evaluate the sensitivity of SLAD to the rankrof the LoRA adapters on CUB (ViT-B→ViT-S)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SLAD : Shared LoRA Adapters for Task Specific Distillation
SLAD uses shared LoRA adapters in joint training to align teacher-student features, boosting both models' performance and halving training time versus fine-tuning in distillation.