LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Ruofei Zhu

Public OpenReview and DBLP records link Ruofei Zhu to 2025 ByteDance reinforcement-learning work on LLMs, including DAPO, VAPO, and Seed1.5-Thinking. OpenReview also lists an MS in Software Engineering from Peking University.

ByteDance researcher focused on reinforcement learning for large language models.1 organizations1 reports

Profile status: updated

updated 3 public sources
reinforcement learninglarge language modelsreasoning models

Current frame

ByteDance researcher focused on reinforcement learning for large language models.

Extended note

Public sources identify Ruofei Zhu as a ByteDance researcher with expertise in reinforcement learning. DBLP attributes multiple 2025 LLM and reasoning-related papers to this profile, including DAPO, VAPO, and the provided Seed1.5-Thinking report. An OpenReview profile for the same name lists a confirmed @bytedance.com email and an MS in the Program for Software Engineering at Peking University (2017-2020).

Education

Peking University MS · Software Engineering 2017 → 2020

Public links

openreview OpenReview dblp DBLP

Organizations

core ByteDance Seed

Reports

Report Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Official and primary sources

dblp: Ruofei Zhu Official source · dblp · DBLP Ruofei Zhu | OpenReview Official source · openreview · OpenReview

Supporting sources

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning Supporting source · report · arXiv