Yejun Zhang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budget gaps, the benefit is highly task-dependent and does not guarantee superior performance.
The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budget gaps, the benefit is highly task-dependent and does not guarantee superior performance.
Papers
Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters
Xinjue Wang, Xiuheng Wang, Yejun Zhang, Sergiy A. Vorobyov +2 more
The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budge…