3 papers
cs.AI2025
Unsupervised decoding of encoded reasoning using language model interpretability
Ching Fang, Samuel Marks
As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investi…
cs.RO2025
A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
TRI LBM Team, Jose Barreiros, Andrew Beaulieu +79
Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently…
cs.AI2025
From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers
Ching Fang, Kanaka Rajan
Humans and animals show remarkable learning efficiency, adapting to new environments with minimal experience. This capability is not well captured by standard reinforcement learnin…