Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
cs.LG, math.DS, stat.ML
Submitted: 2026-05-28
Updated: 2026-11-08
Terminology
Sources
- DiScoFormer: Plug-In Density and Score Estimation with Transformers
- Constrained Denoising, Empirical Bayes, and Optimal Transport
- Back to Basics: Let Denoising Generative Models Denoise
- Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants
- The Mean-Field Dynamics of Transformers
- Attention Residuals
- Solving Empirical Bayes via Transformers
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