FogFool creates fog-based adversarial perturbations using Perlin noise optimization to achieve high black-box transferability (83.74% TASR) and robustness to defenses in remote sensing classification.
HSplitLoRA: A Heterogeneous Split Parameter- Efficient Fine-Tuning Framework for Large Language Models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
SL-FAC reduces communication in split learning via frequency-aware compression of activations and gradients while aiming to preserve training-critical information.
A survey that introduces a unified training pipeline and taxonomizes split learning approaches for LLM fine-tuning across model, system, and privacy dimensions.
The paper derives the first convergence upper bound for split federated learning under activation upload, gradient download, and aggregation failures, then jointly optimizes client sampling and model splitting to minimize the bound, with simulations on EMNIST and CIFAR-10.
HiCoLoRA uses hierarchical LoRA with spectral domain-slot clustering, adaptive fusion, and semantic SVD initialization to achieve SOTA zero-shot DST on MultiWOZ and SGD.
citing papers explorer
-
Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
FogFool creates fog-based adversarial perturbations using Perlin noise optimization to achieve high black-box transferability (83.74% TASR) and robustness to defenses in remote sensing classification.
-
SL-FAC: A Communication-Efficient Split Learning Framework with Frequency-Aware Compression
SL-FAC reduces communication in split learning via frequency-aware compression of activations and gradients while aiming to preserve training-critical information.
-
A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations
A survey that introduces a unified training pipeline and taxonomizes split learning approaches for LLM fine-tuning across model, system, and privacy dimensions.
-
Optimizing Split Federated Learning with Unstable Client Participation
The paper derives the first convergence upper bound for split federated learning under activation upload, gradient download, and aggregation failures, then jointly optimizes client sampling and model splitting to minimize the bound, with simulations on EMNIST and CIFAR-10.
-
HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST
HiCoLoRA uses hierarchical LoRA with spectral domain-slot clustering, adaptive fusion, and semantic SVD initialization to achieve SOTA zero-shot DST on MultiWOZ and SGD.