Spike-NVPT creates noise-robust binary visual prompts by using integrate-and-fire spiking neurons to filter signals and discretize them, yielding up to 11.2% better robustness than standard prompt tuning while keeping clean accuracy competitive.
Learning multiple layers of features from tiny im- ages
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
SeAl-KD selectively aligns class-level and temporal knowledge in SNNs by equalizing competing logits at erroneous timesteps and reweighting alignment by confidence and inter-timestep similarity, outperforming uniform KD methods on image and event datasets.
GSEC uses MLLM-generated semantic descriptions and a bi-layer ensemble (BatchEnsemble inner layer plus alignment outer layer) to reduce bias and variance, outperforming 18 prior methods on six image clustering benchmarks.
FedIDM filters abnormal updates in federated learning by creating condensed data through distribution matching and rejecting updates that deviate or cause high loss on that data.
citing papers explorer
-
Spike-NVPT: Learning Robust Visual Prompts via Bio-Inspired Temporal Filtering and Discretization
Spike-NVPT creates noise-robust binary visual prompts by using integrate-and-fire spiking neurons to filter signals and discretize them, yielding up to 11.2% better robustness than standard prompt tuning while keeping clean accuracy competitive.
-
Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks
SeAl-KD selectively aligns class-level and temporal knowledge in SNNs by equalizing competing logits at erroneous timesteps and reweighting alignment by confidence and inter-timestep similarity, outperforming uniform KD methods on image and event datasets.
-
Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering
GSEC uses MLLM-generated semantic descriptions and a bi-layer ensemble (BatchEnsemble inner layer plus alignment outer layer) to reduce bias and variance, outperforming 18 prior methods on six image clustering benchmarks.
-
FedIDM: Achieving Fast and Stable Convergence in Byzantine Federated Learning through Iterative Distribution Matching
FedIDM filters abnormal updates in federated learning by creating condensed data through distribution matching and rejecting updates that deviate or cause high loss on that data.