Transformation Laws in Neural Representations: Structure, Realisability, and Construction
cs.LG, cs.NE
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: 46 pages, 12 figures, 63 tables
Code: https://github.com/hcgt-c/TLNR
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Lie Derivative for Measuring Learned Equivariance
- What Affects Learned Equivariance in Deep Image Recognition Models?
- Constrained consensus-based optimization
- Does equivariance matter at scale?
- How Data Augmentation Shapes Neural Representations
- Equivariant Contrastive Learning
- Understanding the Role of Equivariance in Self-supervised Learning
- General $E(2)$-Equivariant Steerable CNNs
- Color Equivariant Convolutional Networks
- Learning Color Equivariant Representations
- A Hypertoroidal Covering for Perfect Color Equivariance
- A Characterization Theorem for Equivariant Networks with Point-wise Activations
- Towards a Definition of Disentangled Representations
- Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens
- On the Non-Identifiability of Steering Vectors in Large Language Models
- Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
- Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
- EditCLEVR: A Paired-Scene Intervention Benchmark for Compositional Faithfulness of Object-Centric Representations
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks