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

Atlas / People / Detail

Xiaobo Qin

Xiaobo Qin is a researcher at Seed, ByteDance Inc. Public OpenReview records connect Qin to reasoning-model training work, reinforcement learning, and large language model research, including Pass@k Training for large reasoning models.

Researcher at ByteDance Seed focused on reasoning models and reinforcement learning1 organizations1 reports

Profile status: updated

updated 3 public sources
Seed1.5-VLreasoning modelsreinforcement learninglarge language models

Current frame

Researcher at ByteDance Seed focused on reasoning models and reinforcement learning

Work

ByteDance Seed Researcher 2024-01-01

Public links

openreview OpenReview profile website Personal homepage

Organizations

core ByteDance Seed

Reports

Vision-Language Models Seed1.5-VL Technical Report

Official and primary sources

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models Official source · openreview · OpenReview Xiaobo Qin - OpenReview profile Official source · openreview · OpenReview

Supporting sources

Seed1.5-VL Technical Report Supporting source · report · arXiv