PLAN: Proactive Low-Rank Allocation for Continual Learning
"低秩自适应" 相关文章
Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models
Continual Knowledge Consolidation LORA for Domain Incremental Learning
Continual Knowledge Consolidation LORA for Domain Incremental Learning
Continual Knowledge Consolidation LORA for Domain Incremental Learning
FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning
Multimodal Carotid Risk Stratification with Large Vision-Language Models: Benchmarking, Fine-Tuning, and Clinical Insights
PrunedLoRA: Robust Gradient-Based structured pruning for Low-rank Adaptation in Fine-tuning
TensLoRA: Tensor Alternatives for Low-Rank Adaptation
Low-Resource Fine-Tuning for Multi-Task Structured Information Extraction with a Billion-Parameter Instruction-Tuned Model
Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models
Regularizing Subspace Redundancy of Low-Rank Adaptation
MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems
LoRA Is Slower Than You Think
The Primacy of Magnitude in Low-Rank Adaptation
SingLoRA: Low Rank Adaptation Using a Single Matrix
ST-LoRA: Low-rank Adaptation for Spatio-Temporal Forecasting
