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

Atlas / People / Detail

Mingji Han

Mingji Han is publicly listed as a coauthor of ByteDance Seed's Seed1.5-Thinking report and the DBLP-indexed NSDI 2025 paper ByteCheckpoint, indicating work spanning reasoning-model reinforcement learning and large foundation model infrastructure.

Research contributor on reasoning models and large foundation model systems.1 organizations1 reports

Profile status: updated

updated 2 public sources
reasoning modelsreinforcement learningfoundation model systemscheckpointing

Current frame

Research contributor on reasoning models and large foundation model systems.

Organizations

core ByteDance Seed

Reports

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

Official and primary sources

ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development Official source · dblp · DBLP

Supporting sources

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