Satya Narayan Shukla @ImSNShukla

Senior Research Scientist @MetaAI | PhD @UMassAmherst | Prev @MSFTResearch, @facebookai and @Bosch_AI | BTech @IITKgp satyanshukla.github.io New York Joined November 2013

Tweets

34
Followers

435
Following

663
Likes

774

Satya Narayan Shukla @ImSNShukla

2 months ago

Due to popular demand, we have open-sourced the code and data for MetaQuery.

Xichen Pan @xichen_pan

2 months ago

Due to popular demand, we have open-sourced the code and data for MetaQuery.

1 23 134 18K 50

0 0 4 369 1

Satya Narayan Shukla @ImSNShukla

5 months ago

Check out our latest work on training unified understanding and generation models. We show that frozen MLLMs can seamlessly transfer knowledge, reasoning, and in-context learning from text to pixel output.

Xichen Pan @xichen_pan

5 months ago

9 67 417 68K 301

Download Image

0 0 4 331 0

Saining Xie @sainingxie

5 months ago

Our take on a 4o-style AR + diffusion unified model: Transferring knowledge from an AR LLM to generation is easier than expected--you don't even need to touch the LLM. The right bridge between output modalities can unlock cool capabilities like knowledge-augmented generation!

Xichen Pan @xichen_pan

5 months ago

9 67 417 68K 301

Download Image

5 29 263 20K 106

Lucas Bandarkar @LucasBandarkar

a year ago

We presented Belebele at ACL 2024 this week! (Thx to @LiangDavis and @ImSNShukla) A year on from its release, it’s been really cool to see the diversity of research projects that have used it. The field is in dire need of more multilingual benchmarks !

AI at Meta @AIatMeta

a year ago

1 2 25 9K 5

Download Image

0 6 23 1K 0

Satya Narayan Shukla @ImSNShukla

a year ago

Check out our recent CVPR paper on improving spatial reasoning in Visual-LLMs.

Kanchana Ranasinghe @kahnchana

a year ago

Check out our recent CVPR paper on improving spatial reasoning in Visual-LLMs.

1 5 22 2K 2

Download Image

0 0 7 193 0

Kanchana Ranasinghe @kahnchana

a year ago

Our paper on “Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs” accepted to CVPR ‘24. Arxiv: arxiv.org/abs/2404.07449

3 5 41 2K 9

Download Image

Satya Narayan Shukla @ImSNShukla

3 years ago

Come join us today for the ‘Learning from time series for health’ workshop at #NeurIPS2022 Room 392

Tom Hartvigsen @tom_hartvigsen

3 years ago

Come join us today for the ‘Learning from time series for health’ workshop at #NeurIPS2022 Room 392

2 1 33 0 4

Download Image

0 1 3 0 0

AI at Meta @AIatMeta

3 years ago

We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts. Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results.

823 2K 8K 0 841

Download Video

Tom Hartvigsen @tom_hartvigsen

3 years ago

By popular demand, we've extended the submission deadline for the #NeurIPS2022 Workshop on Learning from Time Series for Health to September 30th!

0 3 12 0 2

Satya Narayan Shukla @ImSNShukla

3 years ago

10 days to submit to our #NeurIPS workshop "Learning from Time Series for Health". Checkout our website: timeseriesforhealth.github.io Can't wait to see your amazing work and meet you in person in December!

0 2 11 0 1

Satya Narayan Shukla @ImSNShukla

3 years ago

Excited to share that our workshop proposal on "Learning from Time Series for Health" got accepted to @NeurIPSConf 2022.

Tom Hartvigsen @tom_hartvigsen

3 years ago

Excited to share that our workshop proposal on "Learning from Time Series for Health" got accepted to @NeurIPSConf 2022.

6 47 554 0 93

0 0 3 0 0

Satya Narayan Shukla @ImSNShukla

4 years ago

I'll be presenting this work at #KDD2021 in the research paper session on 08/17 at 1:30 pm EST and in the poster session on 08/18 at 5:30 pm EST. Please feel free to drop by if you're attending, or ping me if you have any questions!