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
Selected Publications Google Scholar
-
VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations.
ECCV, 2026. PaperProject -
WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models.
ECCV, 2026. Paper -
DPL: Decoupled Prototype Learning for Robust Vision-Language Transformers to Missing Modalities.
CVPR, 2026. Paper -
MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning.
ICLR, 2026. PosterCode -
Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents.
Under review, 2026. Paper -
Explain Before You Answer: A Survey on Compositional Visual Reasoning.
Under review, 2025. PaperProject -
DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning.
ICCV, 2025. PaperProject -
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning.
ICCV, 2025. PaperCode -
Position: Prospective of Autonomous Driving-Multimodal LLMs World Models Embodied Intelligence AI Alignment and Mamba.
WACV, 2025. Paper -
AR-Facilitated Safety Inspection and Fall Hazard Detection on Construction Sites.
ISMAR, 2024. -
Divide-Conquer Transformer Learning for Predicting Electric Vehicle Charging Events Using Smart Meter Data.
PESGM, 2024. -
HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning.
ECCV, 2024. PaperCode -
HiTSKT: A Hierarchical Transformer Model for Session-aware Knowledge Tracing.
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