65 20 25

Miquel Farré

mfarre

AI & ML interests

I like everything video

Recent Activity

upvoted an article about 1 hour ago

SmolLM3: smol, multilingual, long-context reasoner

upvoted an article 6 days ago

TimeScope: How Long Can Your Video Large Multimodal Model Go?

upvoted a paper 26 days ago

Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

View all activity

Organizations

Articles 6

Article

286

SmolVLM2: Bringing Video Understanding to Every Device

Article

182

Remove backgrounds from images

Configuration error

Moore AnimateAnyone

🏃

Running

Rishicleaner

🏆

rishicleaner

models 2

mfarre/SmolVLM2-500M-Video-Instruct-emotions

Image-Text-to-Text • 0.5B • Updated Feb 20 • 3

mfarre/Video-LLaVA-7B-hf-CinePile

Video-Text-to-Text • Updated Aug 24, 2024 • 3 • 29

datasets 6

mfarre/servedfiles

Viewer • Updated Apr 9 • 8 • 8.2k

mfarre/vlcexamples

Viewer • Updated Mar 5 • 4 • 12

mfarre/simplevideoshorts

Viewer • Updated Oct 25, 2024 • 66.4k • 50

mfarre/simplevideo3

Updated Oct 22, 2024 • 21

mfarre/simplevideo2

Viewer • Updated Oct 9, 2024 • 112k • 59 • 1

mfarre/simplevideo

Viewer • Updated Oct 7, 2024 • 5 • 103

Miquel Farré

AI & ML interests

Recent Activity

Organizations

Articles 6

SmolVLM2: Bringing Video Understanding to Every Device

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

Papers 2

spaces 3 Sort: Recently updated

Background Removal

Moore AnimateAnyone

Rishicleaner

models 2 Sort: Recently updated

datasets 6 Sort: Recently updated

spaces 3

models 2

datasets 6