Gengze Zhou's picture

Gengze Zhou

ZGZzz

·

https://gengzezhou.github.io/

AI & ML interests

Embodied Ai, Vision-and-Language Navigation, Computer vision, Multimodality Learning, LLM

Recent Activity

updated a dataset 2 days ago

ZGZzz/hm3d_generate

published a dataset 2 days ago

ZGZzz/hm3d_generate

upvoted a paper 3 months ago

Self-Evaluation Unlocks Any-Step Text-to-Image Generation

View all activity

Organizations

None yet

Papers 7

arxiv:2512.14691

arxiv:2512.06421

arxiv:2412.05552

arxiv:2407.12366

models 5

ZGZzz/SAME

Visual Question Answering • Updated Dec 17, 2025 • 8

ZGZzz/SAR

Text-to-Image • Updated Dec 17, 2025

ZGZzz/NavGPT2-FlanT5-XXL

Updated Sep 10, 2024

ZGZzz/albef-text

Feature Extraction • 66.4M • Updated Sep 1, 2024 • 1

ZGZzz/NavGPT2-FlanT5-XL

Updated Aug 26, 2024

datasets 5

ZGZzz/hm3d_generate

Updated 2 days ago • 34

ZGZzz/R2R_SFT_womap

Preview • Updated Apr 7, 2025 • 6

ZGZzz/VersNav

Preview • Updated Nov 1, 2024 • 392 • 1

ZGZzz/NavGPT-R2R

Updated Aug 12, 2024 • 311 • 1

ZGZzz/NavGPT-Instruct

Preview • Updated Aug 11, 2024 • 42 • 1