CV

Junfeng Ren

M.S. Student, Southern University of Science and Technology

Shenzhen, China

Research Interests

Spatial Intelligence & World Models

Semantic occupancy Collaborative perception Predictive world modeling

Efficient Transformer Inference

Training-free token merging Content-spatial consistency QKV-level merging

LLM Agent Systems

Agent adaptation Cross-agent harness transfer Context-efficient tool use

Education

  • 2024 - Present

    Shenzhen, China

    M.S. in Electronic Information
    Southern University of Science and Technology
  • 2019 - 2023

    Qingdao, China

    B.S. in Internet of Things Engineering
    Shandong University of Science and Technology

Research Experience

  • Jun 2026 – Present

    Singapore (Remote)

    Remote Research Intern
    National University of Singapore
    Department of Computer Science, School of Computing
    • Research on reliable and efficient LLM agent systems, with a focus on cross-agent harness transfer, context-efficient tool use, and reliability evaluation.
    • Developed research systems for reliable harness adaptation and tool-output selection across heterogeneous LLM agents.
  • 2024 – Present

    Shenzhen, China

    Graduate Researcher (M.S.)
    Southern University of Science and Technology
    Guangdong Provincial Key Laboratory of Advanced Wireless Communication Technology
    • Research on spatial intelligence and efficient Transformer inference for autonomous and embodied systems, including collaborative semantic occupancy prediction, predictive world modeling, and training-free token merging.
    • Developed communication-efficient multi-agent perception and Transformer acceleration methods with an emphasis on compact token representations and redundant-computation reduction.
  • Jul 2023 – Jan 2024

    Qingdao, China

    Research Assistant
    Shandong University of Science and Technology
    IoT Engineering Laboratory
    • Research on resource-constrained embedded and IoT systems, with a focus on real-time scheduling and edge intelligence.
    • Conducted scheduling experiments and co-authored a peer-reviewed conference paper on RMS-based embedded scheduling.

Publications & Manuscripts

Peer-Reviewed Publications

  • Scheduling Optimization Design of IoT Embedded System Based on Improved RMS Algorithm

    Junfeng Ren

    IEEE AIKIIE, 2023.

    Paper

Manuscripts Under Review / Submitted

  • Learning to Merge Tokens for Communication-Efficient Collaborative Occupancy Prediction

    Junfeng Ren

    Submitted to NeurIPS 2026, 2026.

    Project

  • FedHarness: Federated Harness Evolution for LLM Agents

    Junfeng Ren

    Submitted to AAAI 2027, 2026.

    Project

  • CriticShift: Reliability-Aware Tool-Output Selection for LLM Agents

    Junfeng Ren

    Submitted to AAAI 2027, 2026.

    Project

  • CAMerge: Context-Aware Token Merging for Efficient Semantic Segmentation

    Junfeng Ren

    Submitted to WACV 2027, 2026.

    Project

  • Bandwidth-Aware Adaptive Token Communication for Collaborative Occupancy Prediction

    Junfeng Ren

    Submitted to IEEE ITSC 2026, 2026.

    Project

Manuscripts in Preparation

  • Collaborative 4D Occupancy World Models with Motion-Aware Token Memory

    Junfeng Ren

    Manuscript in preparation, 2026.

    Project

Selected Research Projects

Spatial Intelligence & World Models

Efficient Transformer Inference

LLM Agent Systems

  • FedHarness-RB

    Reliable cross-agent transfer of executable harness improvements through target-side validation and selective deployment, reducing negative transfer across heterogeneous LLM agents.

    Project

  • CriticShift

    Reliability-aware tool-output selection that preserves task-critical evidence while reducing unnecessary context for tool-using LLM agents.

    Project

Selected Engineering Projects

Technical Skills

Programming & Systems: Python, C/C++, CUDA, Linux
Machine Learning: PyTorch, Transformers, 3D perception, LLM agent systems

Languages

Chinese : Native
English : CET-6; IELTS 6.5