Susceptibilities for Neural Networks Learning from Physical Data
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
- Towards Spectroscopy: Susceptibility Clusters in Language Models
- From Global to Local: A Scalable Benchmark for Local Posterior Sampling
- Influence Dynamics and Stagewise Data Attribution
- You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
- Formal Algorithms for Transformers
- Structure Development in List-Sorting Transformers
- Embryology of a Language Model
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