Hello, I am Zeru, a first year Ph.D. student in Computer Science at Rutgers University. I am honored to be guided by Prof.Ruixiang Tang. I received my B.E. degree in Software Engineering at Dalian University of Technology
My research interests mainly focus on:
- LLM/VLM Reasoning and Post-training: I am highly interested in post-training for LLMs and VLMs. My focus is on developing more effective reinforcement learning algorithms, as well as leveraging simple and interpretable methods, to improve reasoning capabilities through post-training.
- Agentic AI: I am also interested in Agentic AI, especially in the design of agent memory. I am particularly drawn to a storage centric perspective, where memory is treated as a first-class component. My goal is to build principled memory systems that can significantly enhance agents’ capabilities in complex reasoning and real world problem solving.
My CV is here: Zeru’s CV
I am always open to research collaborations. If you are interested in my previous work or would like to discuss potential ideas, please feel free to contact me.
🔥 News
- 2026.05: Please check our preprint about multimodal agent memory MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
- 2026.05: 🎉🎉 Honored as Top Reviewer for ICML 2026.
- 2026.04: 🎉🎉 One first author paper has been accepted by ICML 2026, thanks to my all collaborators!.
- 2026.04: 🎉🎉 I will join NVIDIA as a research intern in 2026 summer. Welcome to reach out for collaboration and discussion.
- 2025.10: 🎉🎉 I am honered to be selected as a Rutgers Climate and Energy Institute (RCEI) Fellowship. Thanks to my professor!
- 2025.10: Please check our preprint about Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
- 2025.09: I have been invited to be a reviewer for ICLR 2026.
- 2025.09: 🎉🎉 One paper has been accepted by IEEE TCSVT (IF=11.1), thanks to my all collaborators!
- 2025.08: 🎉🎉 One paper has been accepted by EMNLP 2025(Main), thanks to my all collaborators!
- 2025.03: 🎉🎉 I will join Rutgers University as a PhD student in 2025 Fall, supervised by Prof. Ruixiang Tang!
- 2025.01: 🎉🎉 Our work From Commands to Prompts: LLM-based Semantic File System is accepted by ICLR 2025, many thanks to my collaborators!
- 2024.11: 🎉🎉 I get China National Scholarship.
📷 Selected Publication
(* indicates equal contribution)
Agentic AI
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
TL;DR: MemEye is a vision-centric long-term memory benchmark that evaluates agents’ ability to remember, update, and reason over visual information across long-running, multi-session image-grounded interactions.
Minghao Guo*, Qingyue Jiao*, Zeru Shi*, Yihao Quan, Boxuan Zhang, Danrui Li, Liwei Che, Wujiang Xu, Shilong Liu, Zirui Liu, Mubbasir Kapadia, Vladimir Pavlovic, Jiang Liu, Mengdi Wang, Yiyu Shi, Dimitris N. Metaxas, Ruixiang Tang
From Commands to Prompts: LLM-based Semantic File System
[ICLR 2025]
TL;DR: We propose a vector-based agent memory system that enables users to manage and interact with computer files through natural language, eliminating the need for traditional Linux commands.
Zeru Shi*, Kai Mei*, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang
Castle: Causal Cascade Updates in Relational Databases with Large Language Models
[EMNLP 2025, Main]
Yongye Su, Yucheng Zhang, Zeru Shi, Bruno Ribeiro, Elisa Bertino
Online Auditing for Early Failure Prediction in Multi-Agent Systems
Boxuan Zhang *, Jianing Zhu *, Zeru Shi, Dongfang Liu, Ruixiang Tang
Post-training and Reasoning
A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
[ICML 2026]
Zeru Shi, Zhenting Wang, Fan Yang, Qifan Wang, Ruixiang Tang
TL;DR: We explored the actionable mechanistic interpretation of massive values in LLMs and propose a method to mitigate the massive activatons.
Improving Visual Reasoning with Iterative Evidence Refinement
Zeru Shi*, Kai Mei*, Yihao Quan, Dimitris N. Metaxas, Ruixiang Tang
Low-Level Computer Vision
SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement
[IEEE TCSVT, IF=11.1]
TL;DR: We design a meta-learning framework to improve the robustness and performance of homography estimation under challenging environments.
Zeru Shi, Zengxi Zhang, Kemeng Cui, Ruizhe An, Jinyuan Liu, Zhiying Jiang
🎖 Honors and Awards
- 2026.05 ICML 2026 Silver Reviewer Award
- 2025.10 Rutgers Climate and Energy Institute (RCEI) Fellowship, USA
- 2025.6 Dalian excellent undergraduate graduates, China
- 2024.11 National Scholarship, China
- 2023.9 Special scholarship of NOK Corporation, Japan
📖 Educations
- 2021.09 - 2025.06,
Dalian University of Technology, ISE, Liaoning, Undergraduate - 2025.09 - Present,
Rutgers University, Computer Science, New Brunswick, Ph.D.
💻 Internships
- 2026.06 - 2026.08, NVIDIA(Incoming), Santa Clara, CA, USA
- 2024.10 - 2025.04, Shanghai AI Laboratory, Shanghai, China
- 2024.02 - 2024.03, Li Auto.Inc, Beijing, China
🕵️ Services
- Conference Reviewer: ICLR 2026, ICML 2026, ARR, Neurips 2026