Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Geometric Scaling of Bayesian Inference in LLMs
Naman Agarwal, Siddhartha R. Dalal, Vishal Misra
Recent work has shown that small transformers trained in controlled "wind-tunnel'' settings can implement exact Bayesian inference, and that their training dynamics produce a geome…
cs.LG2025
The Bayesian Geometry of Transformer Attention
Naman Agarwal, Siddhartha R. Dalal, Vishal Misra
Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analytic posteriors, and large models confl…