Ishan Misra (@imisra

Ishan Misra

301 posts

Ishan Misra

@imisra_

TBD Labs@Meta. Muse Image/Video. Past: Tech Lead of Movie Gen, MIT TR35, Llama3, Emu Video, ImageBind, DINO. Tweets and opinions are my own.

United States

Joined June 2020

Pinned
Ishan Misra
@imisra_
3h
Meet Muse Image, our most advanced image model yet. It's agentic: it reasons, searches the web for the knowledge it needs, uses tools, and refines its own generations before returning a result. This was such a fun project to work on!! Details in 🧵
7.3K
Ishan Misra
@imisra_
Oct 4, 2024
So, this is what we were up to for a while :) Building SOTA foundation models for media -- text-to-video, video editing, personalized videos, video-to-audio One of the most exciting projects I got to tech lead at my time in Meta!
AI at Meta
@AIatMeta
Oct 4, 2024
🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in
00:00
131K
Ishan Misra
@imisra_
Oct 4, 2024
We released 92 pages worth of detail including how to benchmark these models! Super critical for the scientific progress in this field :) We'll also release evaluation benchmarks next week to help the research community 💪
Soumith Chintala
@soumithchintala
Oct 4, 2024
yes, Meta released a full scientific paper on MovieGen, with a lot of details that'll help the field move forward.
74K
Ishan Misra
@imisra_
Nov 16, 2023
World meet #emuvideo For the past year, our team has been pushing on video generation. The result? Emu Video that generates high quality videos from text or images. SOTA performance vs. commercial products and academic papers. Check it out emu-video.metademolab.com
00:00
00:33
AI at Meta
@AIatMeta
Nov 16, 2023
Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ bit.ly/47THS1l These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵
132K
Ishan Misra
@imisra_
Jun 30, 2022
Thank you @MetaAI ! Would not have been possible without the awesome collaborators and mentors at FAIR (Meta) and CMU! And thanks to @techreview for the award :)
AI at Meta
@AIatMeta
Jun 30, 2022
Congratulations to our very own Meta AI researcher @imisra_ for being named one of @TechReview’s #35InnovatorsUnder35! Ishan has been one of our leaders in advancing self-supervised learning. technologyreview.com/innovator/isha…
Ishan Misra
@imisra_
Jul 31, 2021
Thanks for having me @lexfridman ! It was a great experience :)
Lex Fridman
@lexfridman
Jul 31, 2021
Here's my conversation with Ishan Misra (@imisra_), research scientist at FAIR, working on self-supervised visual learning: getting machines to understand images & video with little help from humans. This is one of the most exciting topics in AI today. youtube.com/watch?v=FUS6ce…
Ishan Misra
@imisra_
May 9, 2023
We released ImageBind - a multimodal model for six different modalities trained using self-supervised learning. Mark announced it in his video facebook.com/4/videos/95771… Also, thanks, @_akhaliq for sharing :)
AK
@_akhaliq
May 9, 2023
ImageBind: Holistic AI learning across six modalities ImageBind learns a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. It enables novel emergent applications ‘out-of-the-box’ including cross-modal retrieval, composing
GIF
40K
Ishan Misra
@imisra_
Apr 18, 2024
Check out the generative vision related release too meta.ai/?icebreaker=im… Imagine Flash generates the image as you type You can also "Animate" your images! (technique based on Emu Video emu-video.metademolab.com) Kudos to the team for putting this out :)
134K
Ishan Misra
@imisra_
Oct 6, 2023
Super cool library for SSL!! @LightlyAI
17K
Ishan Misra
@imisra_
Jul 27, 2022
Latest work in SSL learns with 100x fewer labeled images than previous SOTA like MAE, DINO Huge shout out to @mido_assran and Nicolas Ballas for really pushing the boundaries of SSL!
AI at Meta
@AIatMeta
Jul 26, 2022
Tired of manually annotating vast quantities of data to achieve good performance? Our Masked Siamese Networks (MSN) is a self-supervised framework for learning image representations. So what does that mean?
Ishan Misra
@imisra_
Oct 17, 2024
Two exciting updates on Movie Gen (1) MovieGenBench containing thousands of *random* generations for benchmarking for video/audio tasks :) (2) Folks in Hollywood (Casey Affleck, Blumhouse productions) took Movie Gen for a spin: ai.meta.com/blog/movie-gen…
AI at Meta
@AIatMeta
Oct 17, 2024
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
00:00
14K
Ishan Misra
@imisra_
Nov 28, 2022
Attending #NeurIPS2022 this year. Super excited to see the awesome research! Organizing the 3rd SSL workshop sslneurips22.github.io at NeurIPS (1st time in-person) on December 3
Ishan Misra
@imisra_
Aug 3, 2021
Thank you @facebookai and @ylecun :)
AI at Meta
@AIatMeta
Aug 2, 2021
FAIR research scientist, Ishan Misra (@imisra_) sat down with @lexfridman to demystify self-supervised learning & its impact in #AI: youtube.com/watch?v=FUS6ce…. Read the blog post that inspired the conversation: ai.facebook.com/blog/self-supe…
Ishan Misra
@imisra_
Nov 10, 2022
It’s been one of the toughest days at work. Praying for my wonderful ex-colleagues. Please let me know if I can help.