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 about 5 hours ago

ZGZzz/hm3d_generate

published a dataset about 6 hours 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

authored 2 papers 3 months ago

MMGR: Multi-Modal Generative Reasoning

Paper • 2512.14691 • Published Dec 16, 2025 • 121

Rethinking Training Dynamics in Scale-wise Autoregressive Generation

Paper • 2512.06421 • Published Dec 6, 2025 • 7

authored 5 papers over 1 year ago

SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts

Paper • 2412.05552 • Published Dec 7, 2024 • 6

WebVLN: Vision-and-Language Navigation on Websites

Paper • 2312.15820 • Published Dec 25, 2023

NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

Paper • 2402.15852 • Published Feb 24, 2024

NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models

Paper • 2305.16986 • Published May 26, 2023

NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models

Paper • 2407.12366 • Published Jul 17, 2024 • 4