Zirui Zhu

I am a PhD candidate in Computer Science at the National University of Singapore, where I am fortunate to be advised by Prof. Yang You. Before that, I received my B.Eng. in Electronics Engineering from Tsinghua University in 2022, where I was grateful to work with Prof. Yong Li and Prof. Xu Chen.

Research Interests: I build resource-aware methods that make foundation models work at large scale—such as keyframe selection for long video understanding under tight compute budgets. I also study efficient LLM post-training, spanning large-batch optimization, low-cost adaptation (PEFT/zeroth-order), and reward modeling. I have also worked on recommendation systems and tactile sensing in earlier stages of my research.

I am open to research collaborations from both industry and academia. I am also seeking Summer 2026 research internships with the possibility of full-time conversion—feel free to reach out.

Email / Scholar / Github / LinkedIn

Experience

Research Intern, TikTok Pte. Ltd, Singapore, Mar 2025 – Present
Research Intern, 01.AI, Beijing, China, May 2024 – Jul 2024
Research Intern, Kuaishou Technology, Beijing, China, Sep 2021 – Feb 2022
Remote Research Assistant, The Robotics Institute, CMU, Jun 2021 – Mar 2022
Remote Research Assistant, BAIR Lab, UC Berkeley, Nov 2020 – Jun 2021
Research Assistant, Tsinghua University, Beijing, China, Apr 2019 – Sep 2020

Publications

Representative papers are highlighted.

	FOCUS: Efficient Keyframe Selection for Long Video Understanding Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu, Kanchan Sarkar, Zhenheng Yang, Yang You ICLR, 2026 paper / code
	SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning Yong Liu, Di Fu, Shenggan Cheng, Zirui Zhu, Yang Luo, Minhao Cheng, Cho-Jui Hsieh, Yang You ICML, 2025 paper
	POME: Post Optimization Model Edit via Muon-style Projection Yong Liu, Di Fu, Yang Luo, Zirui Zhu, Minhao Cheng, Cho-Jui Hsieh, Yang You arXiv, 2025 paper / code
	MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training Yang Luo, Zangwei Zheng, Ziheng Qin, Zirui Zhu, Yong Liu, Yang You ICML, 2025 paper / code
	Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning Yong Liu, Zirui Zhu, Chaoyu Gong, Minhao Cheng, Cho-Jui Hsieh, Yang You NeurIPS, 2025 paper / code
	Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization Zirui Zhu, Yong Liu, Zangwei Zheng, Huifeng Guo, Yang You WWW, 2024 paper / code
	How Does the Textual Information Affect the Retrieval of Multimodal In-Context Learning? Yang Luo, Zangwei Zheng, Zirui Zhu, Yang You EMNLP, 2024 paper / code
	Inhomogeneous Social Recommendation with Hyper-graph Convolutional Networks Zirui Zhu, Chen Gao, Xu Chen, Nian Li, Depeng Jin, Yong Li ICDE, 2022 paper / code
	Predicting Grasp Stability with Sim2Real Transfer from Tactile Sensing Zilin Si, Zirui Zhu, Arpit Agarwal, Stuart Anderson, Wenzhen Yuan IROS, 2022 paper / code

Adapted from the template by Jon Barron.