RLHF, RLIF, and soft best-of-N sampling reduce to the same exponential-tilting objective under parameter matching, and test-time scaling can asymptotically implement classifier-free diffusion guidance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology
RLHF, RLIF, and soft best-of-N sampling reduce to the same exponential-tilting objective under parameter matching, and test-time scaling can asymptotically implement classifier-free diffusion guidance.