Zesen Cheng's picture

Zesen Cheng

ClownRat

·

https://clownrat6.github.io/

AI & ML interests

multi-modal foundation model; Segmentation, Detection, and Tracking;

Recent Activity

upvoted a paper about 1 month ago

Reinforcement Learning on Pre-Training Data

updated a model about 2 months ago

DAMO-NLP-SG/VideoLLaMA2.1-7B-16F

liked a model 3 months ago

rednote-hilab/dots.vlm1.inst

View all activity

Organizations

Collections 1

Papers 15

arxiv:2503.14428

arxiv:2502.13923

arxiv:2501.13106

arxiv:2501.00599

models 5

ClownRat/VideoLLaMA2.1-7B-16F

Text Generation • 8B • Updated Jan 6

ClownRat/resnet-50-torchvision

23.6M • Updated Dec 25, 2024 • 1

ClownRat/mask2former-resnet-50-coco-instance

44.1M • Updated Dec 25, 2024 • 51

ClownRat/resnet-101-torchvision

42.6M • Updated Dec 23, 2024

ClownRat/mask2former-resnet-101-coco-instance

63.1M • Updated Dec 17, 2024 • 17

datasets 2

ClownRat/YoutubeVIS-2019

Updated Jan 26 • 5

ClownRat/COCO2017-Instance

Viewer • Updated Dec 11, 2024 • 123k • 12 • 1