Latticethe structure behind the noise

Papers Digest Topics Selected Labs Collections FAQ

Created by Flynn Lachendro

Papers Digest Topics Labs Saved

Search

Search papers, labs, and topics across Lattice.

Built by Flynn Lachendro·𝕏 / Twitter·RSS··FAQ·Glossary·Privacy

Nilay Pochhi | Lattice

Nilay Pochhi

Papers on Lattice

1

Total citations

1

Topics

2

h-index

2

Research focus

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

Frequent co-authors

Tarun Raheja (1)

Papers (1)

Jan 3, 2026

Tarun Raheja +1Jan 3, 2026

From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models

Preference learning methods like RLHF and DPO are not as different as you think: they're just different choices along three key axes.

Tarun Raheja, Nilay Pochhi

RLHF & Preference Learning Scalable Oversight & Alignment Theory