Gengyuan Zhang PRO

gengyuanmax

·

gengyuanmax

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

Rethinking Multi-Image Re-Representation in Multi-Image Understanding

authored a paper 1 day ago

A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models

authored a paper 1 day ago

Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning

View all activity

Organizations

Papers 8

arxiv:2609.39363

arxiv:2506.18472

arxiv:2409.20365

arxiv:2409.19149

spaces 1

MosaicGym

Apply image tools and preview results instantly

models 2

gengyuanmax/MosaicLLM-8B

Image-Text-to-Text • 9B • Updated 4 days ago • 21

gengyuanmax/MosaicAgent-8B

Image-Text-to-Text • 9B • Updated 4 days ago • 28

datasets 4

gengyuanmax/MosaicBench

Viewer • Updated 4 days ago • 560 • 356

gengyuanmax/ICQ-Highlight

Viewer • Updated Jun 13, 2024 • 6.19k • 128 • 1

gengyuanmax/composed_vmr

Updated Apr 15, 2024 • 1

gengyuanmax/WikiTiLo

Preview • Updated Nov 8, 2023 • 5