Zonglin Di

,

Zonglin Di is a PhD candidate at UCSC.

Bio last updated: February 23, 2026

Papers

Thumbnail for: CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation

CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation

Xia Su, Ruiqi Chen, Benlin Liu, Jingwei Ma, Zonglin Di, Ranjay Krishna, Jon E. Froehlich

Proceedings of CVPR 2026 | Acceptance Rate: 25.4% (4090 / 16092)

PDF arXiv Cite CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation