NeuroImprint attack assigns isolated memorization neurons to training samples in PEFT adapters, enabling closed-form reconstruction of 59-79% of samples across BERT, GPT-2, Qwen2, and Llama3.2 on multiple datasets.
Counter-interference adapter for multilingual machine translation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
background 1representative citing papers
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
A SiLU-gated, non-mergeable low-rank adapter reports higher MATH pass@1 at rank 64 than rank-512 LoRA with 1/8 the parameters.
citing papers explorer
-
From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning
NeuroImprint attack assigns isolated memorization neurons to training samples in PEFT adapters, enabling closed-form reconstruction of 59-79% of samples across BERT, GPT-2, Qwen2, and Llama3.2 on multiple datasets.
-
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
-
CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation with Non-linearity Retained at Inference
A SiLU-gated, non-mergeable low-rank adapter reports higher MATH pass@1 at rank 64 than rank-512 LoRA with 1/8 the parameters.