Introduces Synergistic Faithfulness metric based on Shapley Interaction Index to evaluate cross-modal synergy in VLM explainers, revealing over-reliance on visual salience in existing methods.
Axiomatic attribution for deep networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
On Llama-2-7B, path-rerouting magnitude in paired transcoder attribution graphs correlates with jailbreak success (r=0.461), while static node metrics and top-feature ablations do not.
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
Mamba model reaches 84% balanced accuracy on 3-class sleep staging from multimodal wearable data without EEG in 357 adults with concurrent PSG.
Benchmark study of ten GNN explainers on eight architectures and six datasets that isolates usable components and issues practical recommendations.
citing papers explorer
-
Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability
Introduces Synergistic Faithfulness metric based on Shapley Interaction Index to evaluate cross-modal synergy in VLM explainers, revealing over-reliance on visual salience in existing methods.
-
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
On Llama-2-7B, path-rerouting magnitude in paired transcoder attribution graphs correlates with jailbreak success (r=0.461), while static node metrics and top-feature ablations do not.
-
PRiSE-EEG: A Prior-Guided Foundation Model with Depth-Stratified Experts for Cross-Paradigm EEG Representation Learning
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
-
Mamba-based Deep Learning Approach for Sleep Staging on a Wireless Multimodal Wearable System without Electroencephalography
Mamba model reaches 84% balanced accuracy on 3-class sleep staging from multimodal wearable data without EEG in 357 adults with concurrent PSG.
-
Explaining the Explainers in Graph Neural Networks: a Comparative Study
Benchmark study of ten GNN explainers on eight architectures and six datasets that isolates usable components and issues practical recommendations.