Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
World-Time Compute with Verified Code World Models
James Schwoebel, Ingrida Semenec, Jenia Rousseva +8
LLMs generalize across a domain only after seeing many real, labeled examples, which most domains lack. We study a way to manufacture it cheaply. When a domain's dynamics can be wr…
cs.LG2026
Protein contacts are already in the attention: a single-forward-pass alternative to the Categorical Jacobian
Rome Thorstenson
The Categorical Jacobian of Zhang et al. (2024) reads protein contacts from a language model by perturbing every residue with every alternative amino acid, about forward pass…
cs.LG2025
Sparsity and Superposition in Mixture of Experts
Marmik Chaudhari, Jeremi Nuer, Rome Thorstenson
Mixture of Experts (MoE) models have become central to scaling large language models, yet their mechanistic differences from dense networks remain poorly understood. Previous work…