Invariance before structure: two modes of emergent compression in representation learning
cs.LG, cs.NE, q-bio.NC
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Understanding deep learning requires rethinking generalization
- Convergent Learning: Do different neural networks learn the same representations?
- Getting aligned on representational alignment
- The Platonic Representation Hypothesis
- Emergent Generalization by Representation Learning in Artificial Neural Networks
- The information bottleneck method
- Deep Variational Information Bottleneck
- Improved estimators of causal emergence for large systems
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