Shweta Verma

Papers on Lattice

Total citations

Topics

Research focus

Code Generation & Program Synthesis (1)RLHF & Preference Learning (1)Training Efficiency & Optimization (1)

Frequent co-authors

Mingze Wu (1)Abhinav Anand (1)

Papers (1)

May 27, 2026

Mingze Wu +2May 27, 2026

Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning

Offline RL can give smaller LLMs a surprising edge on challenging coding problems, rivaling the performance of larger models without the costly online interaction.

Mingze Wu, Abhinav Anand, Shweta Verma

Code Generation & Program Synthesis RLHF & Preference Learning Training Efficiency & Optimization

Shweta Verma

Research focus

Frequent co-authors

Papers (1)

Search

Shweta Verma

Research focus

Frequent co-authors

Papers (1)