The Standard Interpretable Model: Design interpretable machine learning methods from elementary symmetries
cs.LG, cs.AI, cs.NE
Submitted: 2026-06-10
Updated: 2026-11-06
Code: https://github.com/guidelabs/steerling
Terminology
Sources
- There Was Never a Bottleneck in Concept Bottleneck Models
- Qwen3-VL Technical Report
- Foundations of Interpretable Models
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Prototype-Grounded Concept Models for Verifiable Concept Alignment
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
- Towards A Rigorous Science of Interpretable Machine Learning
- Towards Automatic Concept-based Explanations
- Physics of Learning: A Lagrangian perspective to different learning paradigms
- The (Un)reliability of saliency methods
- Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
- k-Sparse Autoencoders
- Imposing Hard Constraints on Deep Networks: Promises and Limitations
- HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
- Interpretability Can Be Actionable
- Concept-based Explainable Artificial Intelligence: A Survey
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- A Closer Look at the Intervention Procedure of Concept Bottleneck Models
- Scaling Inherently Interpretable Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis