Qiang He

Papers on Lattice

Total citations

Topics

h-index

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)RLHF & Preference Learning (1)

Frequent co-authors

Setareh Maghsudi (1)

Papers (1)

Aug 11, 2025

Qiang He +1Aug 11, 2025

Pareto Multi-Objective Alignment for Language Models

Aligning LLMs to multiple objectives just got 1000x faster: PAMA reduces the computational complexity of multi-objective RLHF from quadratic to linear, enabling practical Pareto optimization.

Qiang He, Setareh Maghsudi

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks RLHF & Preference Learning

Search

Qiang He

Research focus

Frequent co-authors

Papers (1)