EPB distills NCO models into evolving program portfolios via LLM-driven textual-numerical optimization, matching original performance while exposing stage-dependent heuristic-like behavior.
hub
arXiv preprint arXiv:2205.15480 , year=
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 14roles
background 3polarities
background 3representative citing papers
Concept Flow Models use hierarchical concept-driven decision trees to mitigate information leakage in concept bottleneck models while matching their predictive performance.
Concept-level adversarial attacks exploit CBM interpretability on the CUB dataset, but SPECTRA raises required perturbation norm from 0.46 to over 4200 while keeping accuracy loss under 2.2%.
α-TCAV replaces TCAV's hard indicator with a tunable smooth function to create a unified probabilistic framework with lower variance and guidance for parameter choice or Bayes-optimal scoring.
OceanCBM is the first concept bottleneck model for spatiotemporal ocean prediction that uses mixed supervision on physical concepts and a free concept to deliver consistent mechanistic representations for mixed layer heat content forecasts.
Rough-set analysis finds 16.4% of 305 concept profiles in Derm7pt inconsistent (306 images), capping hard CBM accuracy at 92.1%; symmetric filtering produces a 705-image consistent benchmark where EfficientNet-B5 reaches 0.90 label accuracy.
GRAPE augments prototype medical image classifiers with graph attention for co-occurrence, a mismatch safety check, and open-vocabulary anchoring to support incremental addition of findings from single examples.
Introduces synthetic benchmarks for concept bottleneck models that control data modality, concept choice, annotation quality, and completeness to evaluate performance in decision support and automation.
A new semi-supervised hypergraph Concept Bottleneck Model framework improves label efficiency and interpretability for medical image diagnosis on PAS ultrasound, breast ultrasound, and SkinCon datasets.
Tree of Concepts uses a fixed rule-based concept interface from a shallow decision tree to support continual adaptation in clinical data while preserving consistent explanations across updates.
HIL-CBM is a hierarchical label-free concept bottleneck model that improves classification accuracy and explanation quality over prior single-level CBMs using a visual consistency loss and dual heads.
An attribute-guided dual-branch framework fuses a standard classifier with an interpretable attribute-prior branch to boost ultrasound classification accuracy and explainability.
Introduces 3D-CBM framework mapping raw 3D inputs to multi-tiered interpretable concepts, achieving 88.8% concept accuracy and test-time intervention on PartNet and ShapeNet.
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
citing papers explorer
-
Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
EPB distills NCO models into evolving program portfolios via LLM-driven textual-numerical optimization, matching original performance while exposing stage-dependent heuristic-like behavior.