Ning Lu (卢宁)
Portrait
Logo PhD Student @ Hong Kong University of Science and Technology
I am currently pursuing a Ph.D. in CSE at Hong Kong University of Science and Technology (HKUST), where I focus on the Safety of Language Models.

Now I am interning at ByteDance Seed, focusing on expanding the capability boundaries of Multimodal LLMs through Agentic Reinforcement Learning.

Google Scholar GitHub
Education
  • Hong Kong University of Science and Technology
    Hong Kong University of Science and Technology
    PhD in Computer Science and Engineering
    Sep. 2021 - Present
  • Southern University of Science and Technology
    Southern University of Science and Technology
    Ranked 916th in Shandong Province Gaokao
    BSc in Computer Science and Engineering
    Sep. 2016 - Jul. 2020
Experience
  • ByteDance, Seed
    ByteDance, Seed
    Research Intern, focusing on Agentic RL on Multimodal LLM.
    Sep. 2025 - Present
  • ByteDance, Data-Douyin
    ByteDance, Data-Douyin
    Research Intern, focusing on LLM RL.
    Apr. 2025 - Aug. 2025
  • Huawei, Xiaoyi Terminal
    Huawei, Xiaoyi Terminal
    Explore the LLM's process reward capabilities through problem-solving RL.
    Feb. 2025 - Apr. 2025
  • Huawei, 2012 Lab
    Huawei, 2012 Lab
    Research Intern, focusing on fault-torlerant large language model pre-training
    June 2024 - Oct. 2024
Honors & Awards
  • Outstanding Entrance Scholarship
    2016
  • Outstanding Graduate of the Computer Science Department
    2020
News
2025
My paper was accepted to NeurIPS 2025! We demonstrates that pure RL training focused on problem-solving can implicitly enhance the PRM ability of LLM. Read paper here!
Sep 20
Is Process Reward Model (PRM) Really Necessary? Check out my new paper analyzing the role of PRMs in reasoning tasks. Read paper here!
May 16
My paper was accepted to ICML 2025! We propose Safe Delta, a method that preserves safety when fine-tuning LLMs on diverse datasets. Read paper here!
May 02
My paper was accepted to ICDE 2025! It’s the first to propose a backdoor attack in graph data condensation.
Mar 11
Selected Publications (view all )
Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

Zhangying Feng, Qianglong Chen, Ning Lu, Yongqian Li, Siqi Cheng, Shuangmu Peng, Duyu Tang, Shengcai Liu, Zhirui Zhang

Conference on Neural Information Processing Systems (NeurIPS) 2025

[Paper]

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

Zhangying Feng, Qianglong Chen, Ning Lu, Yongqian Li, Siqi Cheng, Shuangmu Peng, Duyu Tang, Shengcai Liu, Zhirui Zhang

Conference on Neural Information Processing Systems (NeurIPS) 2025

[Paper]

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Ning Lu, Shengcai Liu, Jiahao Wu, Weiyu Chen, Zhirui Zhang, Yew-Soon Ong, Qi Wang, Ke Tang

International Conference on Machine Learning (ICML) 2025

[Paper] [Code]

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Ning Lu, Shengcai Liu, Jiahao Wu, Weiyu Chen, Zhirui Zhang, Yew-Soon Ong, Qi Wang, Ke Tang

International Conference on Machine Learning (ICML) 2025

[Paper] [Code]

Backdoor graph condensation
Backdoor graph condensation

Jiahao Wu, Ning Lu, Zeiyu Dai, Kun Wang, Wenqi Fan, Weiyu Chen, Shengcai Liu, Qing Li, Ke Tang

IEEE International Conference on Data Engineering (ICDE) 2025 Oral

[Paper] [Code]

Backdoor graph condensation

Jiahao Wu, Ning Lu, Zeiyu Dai, Kun Wang, Wenqi Fan, Weiyu Chen, Shengcai Liu, Qing Li, Ke Tang

IEEE International Conference on Data Engineering (ICDE) 2025 Oral

[Paper] [Code]

Large Language Models can be Guided to Evade AI-generated Text Detection
Large Language Models can be Guided to Evade AI-generated Text Detection

Ning Lu, Shengcai Liu, Rui He, Qi Wang, Yew-Soon Ong, Ke Tang

Transactions on Machine Learning Research (TMLR) 2024

[Paper] [Code]

Large Language Models can be Guided to Evade AI-generated Text Detection

Ning Lu, Shengcai Liu, Rui He, Qi Wang, Yew-Soon Ong, Ke Tang

Transactions on Machine Learning Research (TMLR) 2024

[Paper] [Code]

Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack
Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack

Shengcai Liu, Ning Lu, Cheng Chen, Ke Tang

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TALSP, CCF-B) 2021

[Paper] [Code]

Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack

Shengcai Liu, Ning Lu, Cheng Chen, Ke Tang

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TALSP, CCF-B) 2021

[Paper] [Code]

All publications