Coupling-subnet LoRA isolation plus TSA/ACL/TAL yields SOTA continual anomaly detection (98.4% MVTec, 93% VisA I-AUC) with parameter-level zero forgetting under correct routing.
arXiv preprint arXiv:2502.17920 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
ProCL organizes LoRA adapters into input-conditioned program memory slots that combine with a distributed adapter to improve retention and reduce forgetting in continual LLM fine-tuning.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.
citing papers explorer
-
DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
Coupling-subnet LoRA isolation plus TSA/ACL/TAL yields SOTA continual anomaly detection (98.4% MVTec, 93% VisA I-AUC) with parameter-level zero forgetting under correct routing.
-
Continual Fine-Tuning of Large Language Models via Program Memory
ProCL organizes LoRA adapters into input-conditioned program memory slots that combine with a distributed adapter to improve retention and reduce forgetting in continual LLM fine-tuning.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
-
Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.