CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models
cs.AI
Submitted: 2026-07-28
Updated: 2026-11-16
Code: https://github.com/JayDuan123/2027-KDD-Ai4s-track-CADENCE
Terminology
Sources
- Understanding intermediate layers using linear classifier probes
- BatchTopK Sparse Autoencoders
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Scaling and evaluating sparse autoencoders
- Sparse Autoencoders Reveal Interpretable Structure in Small Gene Language Models
- Finding Neurons in a Haystack: Case Studies with Sparse Probing
- Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT
- Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
- Adam: A Method for Stochastic Optimization
- CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
- Concept Bottleneck Models
- A Unified Approach to Interpreting Model Predictions
- k-Sparse Autoencoders
- ECG-FM: An Open Electrocardiogram Foundation Model
- Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Improving Dictionary Learning with Gated Sparse Autoencoders
- Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
- Axiomatic Attribution for Deep Networks
- Steering Language Models With Activation Engineering
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents