QUIVER adaptively mixes objective evaluations with two types of preference queries in surrogate-assisted evolutionary multi-objective optimization to reduce final utility regret, reporting 25% gains on hard WFG benchmarks.
and Finn, Chelsea , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
BlendIn replaces binary guidance acceptance with confidence-weighted distribution blending between base and guidance models, mitigating cascading failures in inference-time LLM alignment.
citing papers explorer
-
QUIVER: Cost-Aware Adaptive Preference Querying in Surrogate-Assisted Evolutionary Multi-Objective Optimization
QUIVER adaptively mixes objective evaluations with two types of preference queries in surrogate-assisted evolutionary multi-objective optimization to reduce final utility regret, reporting 25% gains on hard WFG benchmarks.
-
To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending
BlendIn replaces binary guidance acceptance with confidence-weighted distribution blending between base and guidance models, mitigating cascading failures in inference-time LLM alignment.