Jiahao Wang

Undergraduate Student

Harbin Institute of Technology, Shenzhen

Research Interests

Large Language Models (LLMs)

Reinforcement Learning with Verifiable Rewards (RLVR)

Code Intelligence

Reasoning Optimization

About

I am a final-year undergraduate student at the School of Computer Science, Harbin Institute of Technology, Shenzhen (HITSZ), advised by Prof. Jing Li. I will join The Hong Kong Polytechnic University as a PhD student in 2026.

I am currently a research intern at Tencent Youtu Lab. My research interests lie in Natural Language Processing, particularly Large Language Models, Reinforcement Learning with Verifiable Rewards (RLVR), Code Intelligence, and Reasoning Optimization.

I have published papers at top-tier venues including ICML and ACL.

Selected Publications

View All →

Sufficiency-guided Continuous Adaptive Reasoning

Jiahao Wang, Bingyu Liang, Chenhao Hu, Longhui Zhang, Xuebo Liu, Min Zhang, Jing Li, Xuelong Li

ICML 2026

CCF A

A sufficiency-guided two-stage training framework that lets LLMs autonomously adjust reasoning effort based on problem complexity.

Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation

Longhui Zhang, Jiahao Wang, Chenhao Hu, Bingyu Liang, Jing Li, Min Zhang

ICML 2026

CCF A

Improving both correctness and runtime efficiency of LLM-based code translation via multi-perspective exploration and difference-aware selection.

Speed Up Your Code: Progressive Code Acceleration Through Bidirectional Tree Editing

Longhui Zhang, Jiahao Wang, Meishan Zhang, Gaoxiong Cao, Ensheng Shi, Yuchi Ma, Jun Yu, Honghai Liu, Jing Li, Min Zhang

ACL 2025

CCF A

BITE improves LLM code acceleration through bidirectional tree editing and progressive learning, with a new benchmark and metric.

Function-to-Style Guidance of LLMs for Code Translation

Longhui Zhang, Bin Wang, Jiahao Wang, Xiaofeng Zhao, Min Zhang, Hao Yang, Meishan Zhang, YU LI, Jing Li, Jun Yu, Min Zhang

ICML 2025

CCF A

F2STrans integrates function learning and style learning to improve LLM-based code translation.

System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition

Jiahao Wang, Ramen Liu, Longhui Zhang, Jing Li

CCL 2025

The SRAG-MAV framework enhances fine-grained Chinese hate speech recognition via self-retrieval and multi-model voting.