2 papers
cs.LG2026
When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy
April Chan, Davide D'Ascenzo, Sebastiano Cultrera di Montesano
Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances th…
cs.RO2024
Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
Marcel Torne, Anthony Simeonov, Zechu Li +4
Imitation learning methods need significant human supervision to learn policies robust to changes in object poses, physical disturbances, and visual distractors. Reinforcement lear…