Longfei Liang
Papers
2
Total Citations
2
H-Index
1
About
Longfei Liang is a rising researcher at the forefront of embodied AI and spatial intelligence, whose work bridges the gap between 3D scene understanding and autonomous navigation. His key research areas include neural representations for robotics, topometric mapping, and open-vocabulary visual grounding. In his highly cited work "Topo-Field: Topometric Mapping With Brain-Inspired Hierarchical Layout-Object-Position Fields," Liang introduces a novel framework that integrates hierarchical scene elements—layouts, objects, and their spatial relationships—into a unified representation, enabling mobile robots to achieve comprehensive contextual awareness beyond traditional geometric mapping. This brain-inspired approach enhances robot navigation in complex environments. Complementing this, his paper "A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding" pioneers the use of large language models to interpret free-form language queries for precise 3D object localization, a critical capability for autonomous systems. By fusing neural fields with semantic reasoning, Liang’s contributions advance the frontier of how machines perceive and interact with the physical world. His work, though recent, has already garnered attention for its innovative integration of cognitive principles with deep learning, positioning him as a promising voice in next-generation robotics and augmented reality.
Research Focus
Key Achievements
Top Papers
- 1
- 2