Biography

I am a Research Fellow at Monash University, working with Prof. Hamid Rezatofighi. My research focuses on visual reasoning for physical-grounded systems, including compositional visual reasoning, multimodal reasoning, agentic AI, and high-level visual decision-making. I am interested in building active reasoners that can perceive, reason, plan, and act in the physical world.

At the application level, my work connects vision-language reasoning with robotics, autonomous systems, unmanned device control, construction-site safety, and robust perception under challenging real-world conditions. Earlier in my research path, I worked on time-series data analysis and temporal modeling, including hierarchical transformer models for session-aware knowledge tracing and forecasting.

News

  • Our papers accepted for ECCV'26 ×2 !
  • Serving on the Program Committee for ICONIP'26 !
  • We got one US patent for agentic AI workflow optimization and tool-use training !
  • Our paper accepted for CVPR'26 ×1 !
  • Our paper accepted for ICLR'26 ×1 !
  • Our papers accepted for ICCV'25 ×2 !
  • Research Intern at NEC Laboratories America, San Jose, 2025 !
  • Our paper accepted for WACV'25 ×1 !
  • Our paper accepted for ECCV'24 ×1 !
  • Our paper accepted for ISMAR'24 ×1 !
  • Our paper accepted for PESGM'24 ×1 !
  • Our paper accepted for KBS'24 ×1 !

Contact

fucai.ke@monash.edu LinkedIn Twitter/X GitHub

Selected Publications Google Scholar

  1. VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations.
    Fucai Ke, Boying Li, Zhixi Cai, Long Chen, Weiqing Wang, Pari Delir Haghighi, Gholamreza Haffari, Hamid Rezatofighi.
    ECCV, 2026. PaperProject
  2. WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models.
    Wanjun Du, Zifeng Yuan, Tingting Chen, Fucai Ke, Beibei Lin, Shunli Zhang.
    ECCV, 2026. Paper
  3. DPL: Decoupled Prototype Learning for Robust Vision-Language Transformers to Missing Modalities.
    Jueqing Lu, Yuanyuan Qi, Xiaohao Yang, Shuaicheng Niu, Fucai Ke, Shujie Zhou, Wei Tan, Jionghao Lin, Wray Buntine, Hamid Rezatofighi, Lan Du.
    CVPR, 2026. Paper
  4. MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning.
    Zhixi Cai, Fucai Ke, Kevin Leo, Sukai Huang, Maria Garcia de la Banda, Peter J. Stuckey, Hamid Rezatofighi.
    ICLR, 2026. PosterCode
  5. Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents.
    Sukai Huang, Chenyuan Zhang, Fucai Ke, Zhixi Cai, Gholamreza Haffari, Lizhen Qu, Hamid Rezatofighi.
    Under review, 2026. Paper
  6. Explain Before You Answer: A Survey on Compositional Visual Reasoning.
    Fucai Ke, Joy Hsu, Zhixi Cai, Zixian Ma, Xin Zheng, Xindi Wu, Sukai Huang, Weiqing Wang, Pari Delir Haghighi, Gholamreza Haffari, Ranjay Krishna, Jiajun Wu, Hamid Rezatofighi.
    Under review, 2025. PaperProject
  7. DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning.
    Fucai Ke, Vijay Kumar B G, Xingjian Leng, Zhixi Cai, Zaid Khan, Weiqing Wang, Pari Delir Haghighi, Hamid Rezatofighi, Manmohan Chandraker.
    ICCV, 2025. PaperProject
  8. NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning.
    Zhixi Cai, Fucai Ke, Simindokht Jahangard, Maria Garcia de la Banda, Reza Haffari, Peter J. Stuckey, Hamid Rezatofighi.
    ICCV, 2025. PaperCode
  9. Position: Prospective of Autonomous Driving-Multimodal LLMs World Models Embodied Intelligence AI Alignment and Mamba.
    Fucai Ke et al.
    WACV, 2025. Paper
  10. AR-Facilitated Safety Inspection and Fall Hazard Detection on Construction Sites.
    Jiazhou Liu, Aravinda S Rao, Fucai Ke, Tim Dwyer, Benjamin Tag, Pari Delir Haghighi.
    ISMAR, 2024.
  11. Divide-Conquer Transformer Learning for Predicting Electric Vehicle Charging Events Using Smart Meter Data.
    Fucai Ke, Hao Wang.
    PESGM, 2024.
  12. HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning.
    Fucai Ke, Zhixi Cai, Simindokht Jahangard, Weiqing Wang, Pari Delir Haghighi, Hamid Rezatofighi.
    ECCV, 2024. PaperCode
  13. HiTSKT: A Hierarchical Transformer Model for Session-aware Knowledge Tracing.
    Fucai Ke, Weiqing Wang, Weicong Tan, Lan Du, Yuan Jin, Yujin Huang, Hongzhi Yin.
    Knowledge-Based Systems, 2024. PaperCode

Research Experience

  • Physical-grounded visual reasoning and agentic AI Research on active visual reasoners, compositional visual reasoning, multimodal tool use, and LLM-agent collaboration for real-world perception and control.
  • High-level visual decision-making Decision-making pipelines for robotics, autonomous systems, unmanned device control, and safety-critical physical environments.
  • Time-series data analysis Earlier work on temporal modeling, forecasting, smart-meter data analysis, and hierarchical transformer models for session-aware knowledge tracing.

Academic Experience

  • Program Committee: ICONIP
  • Conference Reviewer: CVPR, ICLR, NeurIPS, ICCV, ECCV, ICML, IROS
  • Journal Reviewer: IEEE TIP, IEEE TPAMI, ACM TIST, Knowledge-Based Systems, Neural Networks