Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization
cs.LG, cs.AI, cs.LO
Submitted: 2026-09-21
Updated: 2026-09-21
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
- Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
- On the Measure of Intelligence
- ARC Prize 2025: Technical Report
- Don't throw the baby out with the bathwater: How and why deep learning for ARC
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- Lagrangian Neural Networks
- Inductive logic programming at 30: a new introduction
- Neural Networks and the Chomsky Hierarchy
- Discovering and Explaining the Representation Bottleneck of DNNs
- Tensor Logic: The Language of AI
- DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
- Adaptive Computation Time for Recurrent Neural Networks
- Neural Turing Machines
- On the Binding Problem in Artificial Neural Networks
- Hamiltonian Neural Networks
- Deep Neural Networks Tend To Extrapolate Predictably
- Standard Neural Computation Alone Is Insufficient for Logical Intelligence
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
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