Alara Dirik's picture

Alara Dirik

adirik

·

alaradirik

AI & ML interests

None yet

Recent Activity

upvoted a paper about 12 hours ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

upvoted a paper 6 days ago

Repurposing Geometric Foundation Models for Multi-view Diffusion

liked a model 7 days ago

facebook/map-anything

View all activity

Organizations

Articles 5

Article

48

A Dive into Text-to-Video Models

Article

6

New ViT and ALIGN Models From Kakao Brain

View all Articles

Papers 3

arxiv:2512.04222

arxiv:2504.14219

arxiv:2112.08493

spaces 8

OWL-ViT Demo

Image-Guided OWL-ViT Demo

ALIGN Zero Shot Image Classification

StyleMC Demo

EfficientFormer

Change It

models 3

adirik/flux-cinestill

Text-to-Image • Updated Aug 24, 2024 • 74 • • 52

adirik/video-mask2former-swin-tiny-youtubevis-2021-instance

Updated Mar 17, 2023

adirik/maskformer-swin-base-sceneparse-instance

Updated Jan 30, 2023 • 5 • 1

datasets 1

adirik/fashion_image_caption-100

Viewer • Updated Aug 29, 2023 • 100 • 16 • 1