EEG foundation models show no single winner across failure modes, attend to correct brain regions but decode corrupted signals, and retain task information in early layers while late layers adapt during fine-tuning.
hub Mixed citations
Bach , author A
Mixed citation behavior. Most common role is method (60%).
14
Pith papers citing it
4,586
external citations · OpenAlex
Method
60% of classified citations
hub tools
citation-role summary
method 3
background 2
citation-polarity summary
representative citing papers
OmniTrace converts token-level signals into span-level cross-modal attributions for open-ended generation in omni-modal LLMs via generation-time tracing.
Deep neural network predicts molecular wavefunctions in atomic orbital basis from which quantum properties are derived at force-field efficiency.
A causal audit via neuron-row zeroing shows attribution methods (LRP, IG) faithfully identify dispensable neurons and can install refusal behavior, while rank-stability proxies systematically miss selector failures.
XtrAIn shifts occlusion from input space to parameter space along the training trajectory to produce cleaner feature attributions than standard methods.
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
LRP on EEG transformers reveals Clever Hans artifacts in motor imagery tasks and a recurring central electrode cluster as a candidate sensorimotor signature of arousal.
APEX generates four types of prototype-based explanations for pre-trained audio classifiers that preserve output invariance and target acoustic properties better than gradient methods applied to spectrograms.
Scaling vision models by depth and parameter count does not consistently improve localisation-based explanation quality across architectures, datasets, and post-hoc methods; smaller models often perform comparably or better.
HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.
A method uses spurious-positive samples to identify and regularize neurons that rely on spurious features, improving model robustness without extra annotations or balanced data.
In interviews with 11 Portuguese-language model developers, four AI ethics tools guided general ethical reflection but failed to surface Portuguese-specific harms like cultural misrepresentation and low language performance.
Aurora's latent space is organized by seasonal cycles with evidence of encoding 3D vertical atmospheric structure for storms, confirmed by perturbation experiments.
A survey proposing a taxonomy of XAI techniques for food quality research organized by data types and explanation methods.
citing papers explorer
-
Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models
EEG foundation models show no single winner across failure modes, attend to correct brain regions but decode corrupted signals, and retain task information in early layers while late layers adapt during fine-tuning.
-
OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs
OmniTrace converts token-level signals into span-level cross-modal attributions for open-ended generation in omni-modal LLMs via generation-time tracing.
-
Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctions
Deep neural network predicts molecular wavefunctions in atomic orbital basis from which quantum properties are derived at force-field efficiency.
-
Faithfulness to Refusal: A Causal Audit of Neuron Selectors
A causal audit via neuron-row zeroing shows attribution methods (LRP, IG) faithfully identify dispensable neurons and can install refusal behavior, while rank-stability proxies systematically miss selector failures.
-
XtrAIn: Training-Guided Occlusion for Feature Attribution
XtrAIn shifts occlusion from input space to parameter space along the training trajectory to produce cleaner feature attributions than standard methods.
-
On What We Can Learn from Low-Resolution Data
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
-
From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP
LRP on EEG transformers reveals Clever Hans artifacts in motor imagery tasks and a recurring central electrode cluster as a candidate sensorimotor signature of arousal.
-
APEX: Audio Prototype EXplanations for Classification Tasks
APEX generates four types of prototype-based explanations for pre-trained audio classifiers that preserve output invariance and target acoustic properties better than gradient methods applied to spectrograms.
-
Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
Scaling vision models by depth and parameter count does not consistently improve localisation-based explanation quality across architectures, datasets, and post-hoc methods; smaller models often perform comparably or better.
-
HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.
-
Shortcut Mitigation via Spurious-Positive Samples
A method uses spurious-positive samples to identify and regularize neurons that rely on spurious features, improving model robustness without extra annotations or balanced data.
-
Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Study
In interviews with 11 Portuguese-language model developers, four AI ethics tools guided general ethical reflection but failed to surface Portuguese-specific harms like cultural misrepresentation and low language performance.
-
Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution
Aurora's latent space is organized by seasonal cycles with evidence of encoding 3D vertical atmospheric structure for storms, confirmed by perturbation experiments.
-
Explainable Artificial Intelligence Techniques for Interpretation of Food Models: a Review
A survey proposing a taxonomy of XAI techniques for food quality research organized by data types and explanation methods.