Photo

Yuhao Shen (沈宇豪)

Hey, I'm Yuhao Shen, a direct PhD student at the College of Control Science and Engineering, Zhejiang University, advised by Prof. Cong Wang. I also received my B.E. degree from Zhejiang University.

My research lies in MLSys, LLM Inference, AI Infrastructure, and Edge Computing. Over the past two years, I have been deeply engaged in the field of speculative sampling and decoding. Outside academia, I enjoy playing basketball, video games, and photography.

Email Scholar GitHub

Recent News

[2026/02] ParallelVLM is accepted at CVPR 2026!
[2026/01] SpecBranch is accepted at ICLR 2026!
[2026/01] Multiple papers including Double, Atlas, SSL, Spark, and TALON submitted to arXiv!
[2025/01] Hetero² Pipe is accepted at ICDCS 2025!
[2024/09/01] I started my Direct Ph.D. journey at Zhejiang University!

Education

	Zhejiang University, Hangzhou, China Direct Ph.D. in Control Science and Engineering, 2024 - 2029 Advisor: Cong Wang
	Zhejiang University, Hangzhou, China Bachelor of Engineering in Control Science and Engineering, 2020 - 2024 Advisor: Cong Wang

Publications

ParallelVLM illustration

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding

Quan Kong*, Yuhao Shen*, Yicheng Ji, Huan Li, Cong Wang (Equal Contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Double illustration

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism

Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Huan Li, Cong Wang

arXiv (2026)

SpecBranch illustration

SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism

Yuhao Shen*, Junyi Shen*, Quan Kong, Tianyu Liu, Yao Lu, Cong Wang

International Conference on Learning Representations (ICLR), 2026

ICLR 2026, Code

Atlas illustration

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

Jinyang Wu, G Zhai, R Jin, J Yuan, Yuhao Shen, S Zhang, Z Wen, J Tao

arXiv (2026)

SSL illustration

SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization

Jinyang Wu, C Yang, Yuhao Shen, F Xu, B Ni, C Liao, Y Liu, H Wang, S Nie, S Zhang, et al.

arXiv (2026)

Spark illustration

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Jinyang Wu, S Yang, C Yang, Yuhao Shen, S Zhang, Z Wen, J Tao

arXiv (2026)

TALON illustration

TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees

Tianyu Liu, Q Lv, Yuhao Shen, X Sun, X Sun

arXiv (2026)

Hetero 2 Pipe illustration

Hetero² Pipe: Pipelining Multi-DNN Inference on Heterogeneous Mobile Processors under Co-Execution Slowdown

Yuhao Shen, Z Wang, T Wang, C Gu, Z Wen, Y Shu, Cong Wang

IEEE 45th International Conference on Distributed Computing Systems (ICDCS), 2025

SENGraph illustration

SENGraph: A self-learning evolutionary and node-aware graph network for soft sensing in industrial processes

F Yan, Cong Wang, Z Wang, Yuhao Shen, C Yang

IEEE Transactions on Neural Networks and Learning Systems, 2024

Profession

	Research Intern, Qwen Application Nov. 2025 - Present Topic: Speculative Decoding, AI Infra Advisor: Ye Shuang, Jun Dai, Lei Chen Hangzhou, China