Picture

Mannat Singh @mannat_singh

Research Engineer, GenAI, @Meta. Manhattan, NY Joined December 2010
  • Tweets
    65
  • Followers
    393
  • Following
    189
  • Likes
    5K
Mannat Singh retweeted
AIatMeta Profile Picture

AI at Meta @AIatMeta

12 months ago

As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Video Bench…

mannat_singh Profile Picture

Mannat Singh @mannat_singh

a year ago

Llama 3.1 is out! Through adapters we've made it multimodal, supporting images, videos, speech! Was a fun journey adding video understanding capabilities with @_rohitgirdhar_, @filipradenovic , @imisra_ and the whole MM team! P.S. MM models are WIP (not part of the release).

AIatMeta Profile Picture

AI at Meta @AIatMeta

a year ago

Llama 3.1 is out! Through adapters we've made it multimodal, supporting images, videos, speech! Was a fun journey adding video understanding capabilities with @_rohitgirdhar_, @filipradenovic , @imisra_ and the whole MM team! P.S. MM models are WIP (not part of the release).

mannat_singh Profile Picture

Mannat Singh @mannat_singh

a year ago

Feels great to have been recognized as an outstanding reviewer for CVPR this year 🤩

CVPR Profile Picture

#CVPR2026 @CVPR

a year ago

Feels great to have been recognized as an outstanding reviewer for CVPR this year 🤩

mannat_singh Profile Picture

Mannat Singh @mannat_singh

2 years ago

Now added ViT-6.5B MAE + MAWS models, and ImageNet-1k finetuned checkpoints. Strong foundational models at all sizes: <100M to >6.5B params. Best public perf on ImageNet-1k linear/finetuned, ImageNetv2, ImageNet-ReaL, low-shot ImageNet-1k & iNaturalist-18. github.com/facebookresear…

mannat_singh Profile Picture

Mannat Singh @mannat_singh

2 years ago

Now added ViT-6.5B MAE + MAWS models, and ImageNet-1k finetuned checkpoints. Strong foundational models at all sizes: <100M to >6.5B params. Best public perf on ImageNet-1k linear/finetuned, ImageNetv2, ImageNet-ReaL, low-shot ImageNet-1k & iNaturalist-18. github.com/facebookresear…

Mannat Singh retweeted
_rohitgirdhar_ Profile Picture

Rohit Girdhar @_rohitgirdhar_

2 years ago

Excited to share what we've been up to this year: Emu Video! A SOTA video generation system from text or images. In spirit of the upcoming holidays, here's a holiday greeting featuring a cute little penguin Frosty, powered by Emu Video! (🔊 on) emu-video.metademolab.com #emuvideo

AIatMeta Profile Picture

AI at Meta @AIatMeta

2 years ago

Excited to share what we've been up to this year: Emu Video! A SOTA video generation system from text or images. In spirit of the upcoming holidays, here's a holiday greeting featuring a cute little penguin Frosty, powered by Emu Video! (🔊 on) emu-video.metademolab.com #emuvideo https://t.co/vZtiARO8iG

Trends for United States

#GateioTokenOfLove
2.145 posts
Snit
Halloween
142 B posts
Schumer
459 B posts
#JiminxDior
925 B posts
Luke Hughes
1.282 posts
Dillon Gabriel
7.647 posts
Happy Uptober
13,6 B posts
#Wednesdayvibe
maisie
1.257 posts
New Month
285 B posts
Shedeur
7.093 posts
GiveRep V1
#BreastCancerAwareness
1.894 posts
Pfizer
138 B posts
Hump Day
13,7 B posts
Good Wednesday
22,9 B posts
Medicaid
106 B posts
Yom Kippur
20,6 B posts
#WednesdayMotivation
2.366 posts

You might like

Research Scientist at Meta GenAI
Rohit Girdhar
@_rohitgirdhar_
2K Followers
Conversational Superintelligence @Meta Previously Led Native Audio Generation Gemini 2.5, Native Audio Gemini 1.5 @GoogleDeepmind
Ankur Bapna
@ankurbpn
1K Followers
Research @Meta Superintelligence Lab; previously multimodal @OpenAI, research:
Bowen Cheng
@bowenc0221
4K Followers