Ray Zhou

Papers on Lattice

Total citations

Topics

Research focus

RLHF & Preference Learning (1)Scalable Oversight & Alignment Theory (1)

Frequent co-authors

Ely Hahami (1)Jack Benarroch Jedlicki (1)

Papers (1)

Jun 8, 2026

Ely Hahami +2Jun 8, 2026

A Unifying Lens on Reward Uncertainty in RLHF

Reward hacking can be mitigated by a unified distributional reward model that reveals the hidden connections between existing aggregation heuristics in RLHF.

Ely Hahami, Ray Zhou, Jack Benarroch Jedlicki

RLHF & Preference Learning Scalable Oversight & Alignment Theory

Ray Zhou

Research focus

Frequent co-authors

Papers (1)

Search

Ray Zhou

Research focus

Frequent co-authors

Papers (1)