Shoubo Hu

Researcher, Huawei Technologies Ltd.

Joined

March 2019

Names

Shoubo Hu (Preferred)

Emails

****@gmail.com (Confirmed)

****@cse.cuhk.edu.hk (Confirmed)

****@huawei.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Researcher

Huawei Technologies Ltd. (huawei.com)

2020 – Present

Advisors, Relations & Conflicts

Coauthor

Bei Yu

2024 – Present

Expertise

LLM

2024 – Present

AI for EDA

2020 – 2024

transfer learning

2017 – 2020

causal inference

2015 – 2020

Publications

A Causal Direction Test for Heterogeneous Populations
Vahid Partovi Nia, Xinlin Li, Masoud Asgharian, Shoubo Hu, Yanhui Geng, Zhitang Chen
- Machine Learning with Applications
- Readers: Everyone
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
Ziru Liu, Cheng Gong, Xinyu Fu, Yaofang Liu, Ran Chen, Shoubo Hu, Suiyun Zhang, Rui Liu, Qingfu Zhang, Dandan Tu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Harnessing Large Language Models Locally: Empirical Results and Implications
Qingyu Song, Peiyu Liao, Wenqian Zhao, Yiwen Wang, Shoubo Hu, Hui-Ling Zhen, Ning Jiang, Mingxuan Yuan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Architect of the Bits World: Masked Autoregressive Modeling for Circuit Generation Guided by Truth Table
Haoyuan Wu, Haisheng Zheng, Shoubo Hu, Zhuolun He, Bei Yu
- Submitted to ICLR 2026
- Readers: Everyone
ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving
Haoyuan Wu, Xueyi Chen, Rui Ming, Jilong Gao, Shoubo Hu, Zhuolun He, Bei Yu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Rui Ming, Haoyuan Wu, Shoubo Hu, Zhuolun He, Bei Yu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Rui Ming, Haoyuan Wu, Shoubo Hu, Zhuolun He, Bei Yu
- CoRR 2025
- Readers: Everyone
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
Ziru Liu, Cheng Gong, Xinyu Fu, Yaofang Liu, Ran Chen, Shoubo Hu, Suiyun Zhang, Rui Liu, Qingfu Zhang, Dandan Tu
- CoRR 2025
- Readers: Everyone
Harnessing On-Device Large Language Model: Empirical Results and Implications for AI PC
Qingyu Song, Peiyu Liao, Wenqian Zhao, Yiwen Wang, Shoubo Hu, Hui-Ling Zhen, Ning Jiang, Mingxuan Yuan
- CoRR 2025
- Readers: Everyone
ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving
Haoyuan Wu, Xueyi Chen, Rui Ming, Jilong Gao, Shoubo Hu, Zhuolun He, Bei Yu
- CoRR 2025
- Readers: Everyone

View all 32 publications

Co-Authors

View all 66 co-authors