updated 2 public sources
large language modelsreinforcement learningreasoning models

Current frame

Researcher at ByteDance working on large language models and reinforcement learning.

Extended note

Bole Ma is publicly listed on OpenReview as a researcher at ByteDance, with career history there shown as 2023 to present. Publicly attributable research linked from OpenReview and the provided ByteDance Seed report places him on work about large language models, reinforcement learning, and reasoning-oriented model development, including Seed1.5-Thinking, DAPO, and Model Merging in Pre-training of Large Language Models.