2.5k citations · 2.7k across the 13 of their papers we have counts for
3 papers · 1 filter
Amortizing intractable inference in large language models
Edward J. Hu, Moksh Jain, Eric Elmoznino +4
Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowled…
Differentiable Tree Operations Promote Compositional Generalization
Paul Soulos, Edward Hu, Kate McCurdy +4
In the context of structure-to-structure transformation tasks, learning sequences of discrete symbolic operations poses significant challenges due to their non-differentiability. T…
GFlowNet-EM for learning compositional latent variable models
Edward J. Hu, Nikolay Malkin, Moksh Jain +3
Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large number of possible configurations of the l…