Gengze Zhou

University of Adelaide

Papers

2

Total Citations

33

H-Index

2

About

Gengze Zhou is an emerging researcher at the forefront of embodied artificial intelligence, with a focused specialization in vision-and-language navigation (VLN) and large vision-language models (VLMs). His work addresses one of the most compelling challenges in modern AI: enabling autonomous agents to navigate unfamiliar environments by understanding and following natural language instructions. Zhou's research tackles the critical problem of generalization — specifically, how agents can transfer learned navigational skills to out-of-distribution scenes and bridge the gap between simulated training environments and real-world deployment. His most notable contribution, **NavGPT-2**, has garnered 31 citations since its 2024 publication, demonstrating significant early impact by unlocking sophisticated navigational reasoning capabilities within large vision-language models. His complementary work, **NaVid**, explores video-based VLM approaches to step-by-step navigation planning, further expanding the toolkit available for embodied AI research. Together, these contributions position Zhou as a promising voice in a rapidly evolving field where robotics, computer vision, and natural language processing converge. Researchers working on autonomous agents, human-robot interaction, or multimodal AI will find his work particularly relevant and forward-looking.

Research Focus

Key Achievements

2
H-Index
2
Papers
33
Total Citations
17
Avg Citations/Paper
🏆 Most Cited Paper
NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
31 citations · 2024
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 11
🏛 Institutions: University of Adelaide

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago