By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.
More: A mixture of low-rank experts for adaptive multi-task learning.arXiv preprint arXiv:2505.22694,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A3B2 introduces an adaptive asymmetric adapter with uncertainty-aware dampening to reduce branch bias in few-shot vision-language image classification and outperforms standard adapter and prompt methods.
STK-Adapter adds Spatial-Temporal MoE, Event-Aware MoE, and Cross-Modality Alignment MoE to integrate evolving TKG graphs and event chains into LLMs, reducing information loss and improving extrapolation performance over prior methods.
citing papers explorer
-
Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.
-
A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning
A3B2 introduces an adaptive asymmetric adapter with uncertainty-aware dampening to reduce branch bias in few-shot vision-language image classification and outperforms standard adapter and prompt methods.
-
STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation
STK-Adapter adds Spatial-Temporal MoE, Event-Aware MoE, and Cross-Modality Alignment MoE to integrate evolving TKG graphs and event chains into LLMs, reducing information loss and improving extrapolation performance over prior methods.