Multimodal contrastive learning using multilinear products is fragile to single bad modalities, and a gated version improves top-1 retrieval accuracy on synthetic and real trimodal data.
The mythos of model interpretability,
10 Pith papers cite this work, alongside 457 external citations. Polarity classification is still indexing.
10
Pith papers citing it
457
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
In a real UK law-enforcement deployment, crime analysts selectively used AI linkage predictions and validated them against behavioural matrices, attending most to MO similarity and geography.
Phoneme-aligned Grad-CAM on a WavLM-CNN detector reveals significant attack- and speaker-dependent importance of vowels, fricatives and pauses for spoof vs bona-fide decisions on ASVspoof 5.
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.
The paper defines five AI system categories for public administration and reports that 55% of 91 recent papers leave the system type underspecified while 31% study one type but motivate with another.
XtrAIn shifts occlusion from input space to parameter space along the training trajectory to produce cleaner feature attributions than standard methods.
ZKMLOps is an MLOps framework that uses zero-knowledge proofs to generate verifiable cryptographic evidence of AI model compliance without revealing confidential information.
Introduces a unified evaluation framework for XAI using five principled metrics and the PGCA method that fuses grid perturbation with Grad-CAM++ , reporting top scores in fidelity, interpretability and fairness on ResNet-50 models across five image domains.
Joint NMF and binomial regression learns response-relevant text signals with competitive performance on simulations and review data.
Neural network learning opacity stems from three dynamical complexity properties in training, rendering some sources of opacity irreducible.
citing papers explorer
-
Hidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning
Multimodal contrastive learning using multilinear products is fragile to single bad modalities, and a gated version improves top-1 retrieval accuracy on synthetic and real trimodal data.
-
How Analysts Use AI in High-Stakes Crime Linkage: An Industrial Study
In a real UK law-enforcement deployment, crime analysts selectively used AI linkage predictions and validated them against behavioural matrices, attending most to MO similarity and geography.
-
Why Do You Say It Like That? A Phoneme-Level Framework for Explainable Speech Deepfake Detection
Phoneme-aligned Grad-CAM on a WavLM-CNN detector reveals significant attack- and speaker-dependent importance of vowels, fricatives and pauses for spoof vs bona-fide decisions on ASVspoof 5.
-
Validating Causal Abstraction Metrics on Simulated Complex Systems
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.
-
A Technical Typology of AI Systems in Public Administration
The paper defines five AI system categories for public administration and reports that 55% of 91 recent papers leave the system type underspecified while 31% study one type but motivate with another.
-
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.
-
"Show Me You Comply... Without Showing Me Anything": Zero-Knowledge Software Auditing for AI-Enabled Systems
ZKMLOps is an MLOps framework that uses zero-knowledge proofs to generate verifiable cryptographic evidence of AI model compliance without revealing confidential information.
-
A Unified Framework for Evaluating and Enhancing the Transparency of Explainable AI Methods via Perturbation-Gradient Consensus Attribution
Introduces a unified evaluation framework for XAI using five principled metrics and the PGCA method that fuses grid perturbation with Grad-CAM++ , reporting top scores in fidelity, interpretability and fairness on ResNet-50 models across five image domains.
-
Learning Interpretable Text Signals for Structured Responses
Joint NMF and binomial regression learns response-relevant text signals with competitive performance on simulations and review data.
-
How Complexity Contributes to Learning Opacity in Machine Learning
Neural network learning opacity stems from three dynamical complexity properties in training, rendering some sources of opacity irreducible.