Zhilin Wang

NVIDIA researcher known for HelpSteer reward-model datasets, the Nemotron-Reward family, and SteerLM alignment work.

Role: researcher
Currently at: NVIDIA
Twitter: twitter.com/zhilin_wang
Scholar: scholar.google.com/citations
Papers: 10

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile: scholar.google.com/citations

Attribution policy →

10papers·1tool contribs

Authored papers

10

π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

arXiv 2026

Llama-Nemotron: Efficient Reasoning Models

arXiv 2025

Evaluating Parameter Efficient Methods for RLVR

arXiv 2025

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas

arXiv 2025

Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration

arXiv 2025

From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning

arXiv 2025

Lost in Literalism: How Supervised Training Shapes Translationese in LLMs

arXiv 2025

HelpSteer2: Open-source Dataset for Training Top-Performing Reward Models

NeurIPS

Nemotron-4 340B Technical Report

arXiv 2024

MAGE: Machine-generated Text Detection in the Wild

arXiv 2023

Tool contributions

1

HelpSteer2

NVIDIA

NVIDIA's permissively-licensed human-annotated preference dataset with 5-axis Likert ratings - engineered to train high-quality reward models.

PreferenceHallucinationSafetyInstruction Following

Affiliations

Currently at

researcher · infra

Frequent co-authors

10

from 10 papers

Yafu Li

5 shared papers

Gerald Shen

engineer

3 shared papers

Jiaqi Zeng

researcher

3 shared papers

Jimmy Zhang

researcher

3 shared papers

Oleksii Kuchaiev

researcher

3 shared papers

Olivier Delalleau

researcher

3 shared papers

Yu Cheng

3 shared papers

Aleksander Ficek

2 shared papers

Ameya Sunil Mahabaleshwarkar

2 shared papers

Boris Ginsburg

2 shared papers