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.
Williams
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
SURF derives weight sampling rules from the arc-length CDF of the scalarization path to uniformly traverse the Pareto front in multi-objective optimization.
POW3R adapts rubric criterion weights via rollout contrast in RLVR to improve mean reward, strict completion rates, and training speed over static rubric aggregation on multimodal and text tasks.
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.
-
SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
SURF derives weight sampling rules from the arc-length CDF of the scalarization path to uniformly traverse the Pareto front in multi-objective optimization.
-
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
POW3R adapts rubric criterion weights via rollout contrast in RLVR to improve mean reward, strict completion rates, and training speed over static rubric aggregation on multimodal and text tasks.