3 papers
cs.LG2026
Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models
Sankaran Vaidyanathan, Rafal Urbaniak, Emily Bunnapradist +2
Localizing behavior to individual components of a language model is a central goal of mechanistic interpretability. However, scoring components one at a time misses context-depende…
cs.RO2026
EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning
Yichao Liang, Amber Li, Dat Nguyen +13
A robot should be able to learn through experiments how unfamiliar objects behave and interact, then plan with that knowledge. It need not start from scratch: physics engines suppl…
cs.AI2026
A Computationally Feasible Framework for Causal Probabilistic Explanation
Rafal Urbaniak, Sam Witty, Daniel Waxman +7
Explaining why a specific outcome occurred, and which inputs deserve the blame or credit, is central to philosophical, scientific, and policy analysis. Existing tools split into tw…