STOMP extends direct preference optimization to the multi-objective setting via smooth Tchebysheff scalarization and standardization of observed rewards, achieving highest hypervolume in eight of nine protein engineering evaluations.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Active sensing emerges as a requirement for task-level control in adaptive sensor systems, producing discrete explore and exploit modes observed in biology.
citing papers explorer
-
Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebysheff Scalarization
STOMP extends direct preference optimization to the multi-objective setting via smooth Tchebysheff scalarization and standardization of observed rewards, achieving highest hypervolume in eight of nine protein engineering evaluations.
-
Active Sensing Subserves Task-Level Control
Active sensing emerges as a requirement for task-level control in adaptive sensor systems, producing discrete explore and exploit modes observed in biology.