zhangtao

zhangtao-whu

·

https://github.com/zhang-tao-whu

zhang-tao-whu

AI & ML interests

segmentation

Recent Activity

upvoted a paper 11 days ago

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

upvoted a paper 20 days ago

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

upvoted a paper 21 days ago

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

View all activity

Organizations

zhangtao-whu 's models 13

zhangtao-whu/vectorllm-hf

zhangtao-whu/DW

Updated Jul 8, 2025

zhangtao-whu/ocr_vqa

Updated Jun 9, 2025 • 3

zhangtao-whu/ocr_vqa_text

Updated Jun 9, 2025

zhangtao-whu/internvl3_merge_model

8B • Updated May 9, 2025 • 2

zhangtao-whu/r1

Updated Apr 26, 2025

zhangtao-whu/st_pth

Updated Mar 7, 2025

zhangtao-whu/gpcv_pth

Updated Mar 3, 2025

zhangtao-whu/capcls1.0_1024M_imgfull_withpt_lr5e-4-0_rp0.1_iter62500_hf

Updated Feb 9, 2025

zhangtao-whu/P2PFormer

Updated Dec 3, 2024 • 2

zhangtao-whu/OMG-LLaVA

Updated Jul 3, 2024 • 7

zhangtao-whu/PCM

Updated Mar 25, 2024

zhangtao-whu/DVIS_Plus

Updated Jan 31, 2024 • 2