Entities · Models
LoRA
26 articles tagged with this entity.
-
FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
-
OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation
-
ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval
-
Beyond LoRA: Can you beat the most popular fine-tuning technique?
-
CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented Generation
-
FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization
-
PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization
-
Recoverable but Not Stationary:Local Linear Structures in Weights and Activations
-
Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals
-
Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune
-
The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning
-
UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning
-
GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech
-
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
-
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
-
Understanding LoRA as Knowledge Memory: An Empirical Analysis
-
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
-
FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
-
FoRA: Fisher-orthogonal Rank Adaptation for Parameter-Efficient Fine-Tuning
-
PromptEmbedder:: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting
-
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
-
NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
-
FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning
-
Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures
-
Learning When to Adapt
-
Selective LoRA for Visual Tokens and Attention Heads