Bin Lei

Bin Lei

Ph.D. Student · Large Language Model Agents, Code Generation, Computer Use Agent

Hi, I'm Bin Lei. I'm a Ph.D. student at the University of Minnesota (UMN) working on large language models, with research interests spanning LLM agents, code generation, multi-agent systems, and Computer Use Agent.

Recent Focus (2026)

Improving LLM performance on long-horizon tasks, along three directions:

Publications

2026

  1. Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning

    Bin Lei, Yu Li, Prafulla Kumar Choubey, Jiaxin Zhang, Becky Xiangyu Peng, Qinyuan Ye, Kartik Narayan, Caiwen Ding, Silvio Savarese, Chien-Sheng Wu

    arXiv 2026 Paper

  2. Stateful Reasoning via Insight Replay

    Bin Lei, Caiwen Ding, Jiachen Yang, Ang Li, Xin Eric Wang

    arXiv 2026 Paper Code

  3. GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding

    Bin Lei, Nuo Xu, Ali Payani, Mingyi Hong, Chunhua Liao, Yu Cao, Caiwen Ding

    ICML 2026 Paper Code

  4. GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning

    Weitai Kang, Bin Lei, Gang Liu, Caiwen Ding, Yan Yan

    ICLR 2026 Paper

  5. Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

    Le Chen, Nuo Xu, Winson Chen, Bin Lei, Pei-Hung Lin, Dunzhi Zhou, Rajeev Thakur, Caiwen Ding, Ali Jannesari, Chunhua Liao

    ACL 2026 Paper

  6. ULD-Net: Enabling Ultra-Low-Degree Fully Polynomial Networks for Homomorphically Encrypted Inference

    Xi Xie, Ran Ran, Jinming Zhao, Bin Lei, Zhijie Jerry Shi, Wujie Wen, Caiwen Ding

    ICLR 2026 Paper

  7. Observer-Based Data-Driven Consensus Control for Nonlinear Multi-Agent Systems Against Denial-of-Service and False Data Injection Attacks

    Yi Zhang, Bin Lei, Mohammadreza Rajabinezhad, Caiwen Ding, Shan Zuo

    Journal of Dynamic Systems, Measurement, and Control 2026 Paper

2025

  1. InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

    Bin Lei, Weitai Kang, Zhe Zhang, Wenyuan Chen, Xi Xie, Shan Zuo, Mingrui Xie, Ali Payani, Mingyi Hong, et al.

    NeurIPS 2025 Paper Code

  2. LLM-VeriPPA: Power, Performance, and Area Optimization Aware Verilog Code Generation with Large Language Models

    Kaustubh Thorat, Jinming Zhao, Yiqi Liu, Asad Hasan, Hongwu Peng, Xi Xie, Bin Lei, Caiwen Ding

    MLCAD 2025 Paper

2024

  1. MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

    Bin Lei, Yi Zhang, Shan Zuo, Ali Payani, Caiwen Ding

    NeurIPS 2024 Paper Code ★ 94

  2. AutoCoder: Enhancing Code Large Language Model with AIEV-Instruct

    Bin Lei, Yuchen Li, Qiuwu Chen

    arXiv 2024 Paper Code ★ 850

  3. Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage

    Bin Lei, Yuchen Li, Yiming Zeng, Tao Ren, Yi Luo, Tianyu Shi, Zitian Gao, Zeyu Hu, Weitai Kang, Qiuwu Chen

    arXiv 2024 Paper Code

  4. Fortran2cpp: Automating Fortran-to-C++ Migration Using LLMs via Multi-Turn Dialogue and Dual-Agent Integration

    Le Chen, Bin Lei, Dunzhu Zhou, Pei-Hung Lin, Chunhua Liao, Caiwen Ding, Ali Jannesari

    arXiv 2024 Paper

2023

  1. Creating a Dataset for High-Performance Computing Code Translation Using LLMs: A Bridge Between OpenMP Fortran and C++

    Bin Lei, Caiwen Ding, Le Chen, Pei-Hung Lin, Chunhua Liao

    IEEE HPEC 2023 🏆 Outstanding Student Paper Award Paper Code

  2. Neurogenesis Dynamics-Inspired Spiking Neural Network Training Acceleration

    Shaoyi Huang, Haowen Fang, Kaleel Mahmood, Bin Lei, Nuo Xu, Bin Lei, Yue Sun, Dongkuan Xu, Wujie Wen, et al.

    ACM/IEEE DAC 2023 Paper

  3. Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought

    Bin Lei, Chunhua Liao, Caiwen Ding

    arXiv 2023 Paper

  4. CompCodeVet: A Compiler-Guided Validation and Enhancement Approach for Code Dataset

    Le Chen, Arijit Bhattacharjee, Nesreen K. Ahmed, Niranjan Hasabnis, Gal Oren, Bin Lei, et al.

    arXiv 2023 Paper

  5. Towards Zero Memory Footprint Spiking Neural Network Training

    Bin Lei, Sheng Lin, Pei-Hung Lin, Chunhua Liao, Caiwen Ding

    arXiv 2023 Paper

2022

  1. Efficient Traffic State Forecasting Using Spatio-Temporal Network Dependencies: A Sparse Graph Neural Network Approach

    Bin Lei, Shaoyi Huang, Caiwen Ding, Monika Filipovska

    arXiv 2022 Paper