160 citations · 403 across the 56 of their papers we have counts for
3 papers · 1 filter
Where Small Mistakes Matter: Quantifying State Criticality for Imitation Learning
Yusuf Umut Ciftci, Joonwon Kang, Ajay Suresha Sathya +1
Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the dataset. Yet not all states are cre…
Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
Sathwik Karnik, Somil Bansal
Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach --…
MBMF: Model-Based Priors for Model-Free Reinforcement Learning
Somil Bansal, Roberto Calandra, Kurtland Chua +2
Reinforcement Learning is divided in two main paradigms: model-free and model-based. Each of these two paradigms has strengths and limitations, and has been successfully applied to…