Co-CEO @yutori_ai. yutori.com. Previously: Senior Director, GenAI & FAIR at Meta, Associate Professor at Georgia Tech.
San Francisco, CA
- Tweets 4,574
- Following 132
- Followers 27,243
- Likes 7,664
Pinned Tweet
We gave some of our partners early access to n1.5 — the most capable computer use model for the web.
It is in production at FAANG scale as we speak, replacing a computer use model from a frontier lab.
If your product can benefit from web automation — extracting structured data from dynamic webpages, filling forms, completing workflows on the web, testing vibe coded web apps — you should try out @yutori_ai's Navigator n1.5!
Save your GPT / Claude / Gemini capacity for something else :)
4
6
25
7,981
Very excited to introduce Humans of AI: Stories, Not Stats!
In this series, I interview AI researchers to get to know them better as people.
Starting next week, I will release two interviews every week as videos and podcast episodes. (Link 👇)
27
290
1,800
Update: I left Meta yesterday. After 7.5 years.
I am sad, nervous, and excited.
Sad because I'll miss Meta! I've felt tremendously valued my entire time at Meta (first in FAIR and recently in GenAI). I'll miss the people and being in the thick of things.
Nervous because who in their right mind walks away from the job I had in times like these (leading research efforts in generative media and multimodal LLMs)?!
And excited for new experiences :) Stay tuned for when I have more to share!
90
26
1,444
247,137
Introducing Make-A-Video3D! Generating 3D dynamic (mini) scenes from input text.
That is, text --> 4D!
Needs no 4D data (i.e., no dynamic 3D data), no static 3D data, no paired text-video data.
Paper: arxiv.org/abs/2301.11280
Website: make-a-video3d.github.io/
27
266
1,330
305,728
Anyone else worried that after watching so many recorded talks at 2x the speed, you'll be impatient when we go back to watching talks in real-time?
42
36
1,106
Introducing AI Paygrades (aipaygrad.es)! Statistics of industry offers for AI jobs. The goal is to reduce information assymetry so candidates can make informed decisions and negotiate better. Submit your information and spread the word! With @abhshkdz.
41
221
1,126
Yes, it’s here :) Zero-shot text-to-video generation!
Introducing Make-A-Video.
The new SOTA, by a large margin, in text-to-video generation. And it doesn’t use any paired text-video data!
Examples, paper, and a sign up sheet at makeavideo.studio/ @MetaAI
Prompts 👇
23
143
979
My first blog post! Several people have asked me for time management advice over the years. I was encouraged to believe that there is a good chance others might find the advice useful too :) Hence this post. Thoughts are welcome!
medium.com/@deviparikh/calen…
34
205
909
I have a system to plan writing papers for conference deadlines. My students and some collaborators know about it. With the ICLR 2020 deadline coming up, I thought this might be a good time to share this with a wider audience.
link.medium.com/XASmjK6ftZ
9
223
887
Nine sets of "two kangaroos busy cooking dinner in a kitchen" 🙂
Generated by Make-A-Video.
(Montage courtesy Yaniv; This kangaroo example had become our go-to example in the last few days to the deadline :))
#MetaAIMakes
11
146
809
I am looking for interns in the AI for Creativity space. If you are an ML/AI graduate student, have done some work in the past in AI for Creativity, and are interested in an internship at FAIR during Summer 2021, please get in touch with me.
34
160
801
NeurIPS 💯🎉!
“all come all served”
Registration is $25 for students and $100 for non-students.
Tutorials, keynotes and oral pre-recorded presentations accessible without a registration. Video recordings of the poster presentations will be released after the conference.
Read about changes to conference registration this year, which opens just days from now!
medium.com/@NeurIPSConf/neur…
6
156
677
This is some advice I had shared with my lab on how to shorten your paper to fit the page limit. With the #CVPR20 deadline coming up, I thought I'd share it widely.
medium.com/@deviparikh/short…
7
134
484
Stefan Lee (@stefmlee), Dhruv Batra (@DhruvBatraDB), and I wrote up a blog post on some tips and principles we tend to follow when writing rebuttals. May be helpful for the upcoming #ECCV2020 rebuttal deadline :)
medium.com/@deviparikh/how-w…
11
135
461
Excited to share a sneak peek into what we've been building at Yutori!
What you see below is our trained model and internal prototype — multiple agents running in parallel in the background, completing tasks of varying complexity, relevant information and cues to step in being surfaced to the user.
More examples 👇
This is barely scratching the surface of what agents can do for you day-to-day.
Follow along at @yutori_ai — more to come soon!
45
51
467
221,257
Finally, a step towards generic vision+language models! One model that can answer questions, draw a box around an object described in a phrase, score an image-caption match, etc. 👆🏽performance on 12 datasets with 1/12th the parameters! SOTA on 7 of 12 datasets after fine-tuning.
7
86
436
AI augmenting human creativity is exciting! Generative models are attractive for that. But users need to have more control.
Make-A-Scene does just that (in addition to being SOTA)!
Also check out the video of a lovely story Oran wrote and illustrated with this approach! 👇
11
37
377
.@DhruvBatraDB and I got tenure! Thank you @ICatGT @gtcomputing @mlatgt. Most of all, thanks to our students, postdocs and research scientists in the CVMLP labs -- first at Virginia Tech, and now at Georgia Tech -- for all the wonderful work over the years! You make this home.
29
13
374
Finished reviewing NeurIPS papers! Yay!
Exciting stuff!
A (hopefully useful) tip based on recurring frustrations I encountered: Make sure everything you say in the paper is completely understandable based on what has been said in the paper so far.
Couple of specific examples:
2
45
361
More Origami.
This one took me 12 hours to fold (including some debugging when things weren't quite lining up right towards the end :)).
May not have been the best idea to do it all in one day :)
2
11
365
My ICLR keynote (and all other conference content) is now publicly available: iclr.cc/virtual_2020/speaker…
2
56
357
Episode 1 is out! Dhruv Batra (@DhruvBatraDB) on Humans of AI: Stories, Not Stats.
Video: piped.video/kWg0we9NCZ8
Podcast: anchor.fm/humanstoriesai/epi…
All episodes so far: humanstories.ai
10
38
350
As ML roles grow, we need scalable ways to test candidates' practical ML skills even before interviews. (CS coding tests don't correlate well with ML skills.)
Introducing caliper.ai — create challenges, invite candidates, see how they do!
Would this be of interest?
9
84
348
Pretty sure everything I've accomplished in life comes down to five things:
1. I don’t like being redundant / a no-op
2. If I am curious about something, I can’t not do it
3. If there's an obvious next step, I can't not add it to my to-do list
4. I am addicted to taking things off my to-do list
5. I get a lot done per hour and put in a lot of hours when needed
7
6
348
43,499
How's this for a plan? We
—Do our jobs well
—Be reliable
—Execute (align our actions with our goals)
—Remember that the world is nuanced
—Assume good intent
—Listen (whether or not we think we're heard)
—Be kind
—Be less peaky in our priors so evidence can play a role
Happy 2019!
6
46
332
Presenting ViLBERT! It learns visiolinguistic representations that transfer well. SOTA on VQA, captioning, referring expressions, visual commonsense reasoning -- all with minor additions to the base architecture.
arxiv.org/pdf/1908.02265.pdf
Work led by @jiasenlu and @stefmlee.
7
84
328
Doesn't seem like the best time, but even before all things 2020, I've been apprehensive about sharing this. So here we are :)
This is my data point as a woman in AI.
Any reactions, stories, perspectives, feedback, or questions are very welcome.
medium.com/@deviparikh/my-da…
13
28
327
Said videos :)
Yes, text went in, pixels came out, and they look like this :)
Make-A-Video from @MetaAI
Yes, it’s here :) Zero-shot text-to-video generation!
Introducing Make-A-Video.
The new SOTA, by a large margin, in text-to-video generation. And it doesn’t use any paired text-video data!
Examples, paper, and a sign up sheet at makeavideo.studio/ @MetaAI
Prompts 👇
6
55
283
New ML journal!
As Hugo says in the thread (and note the last one in particular)
- Uses OpenReview
- Focuses on conference-length publications
- Has no submission deadlines
- Aims for a fast turnaround
- Acceptance based on matched claims and evidence, not potential impact
Today, @RaiaHadsell, @kchonyc and I are happy to announce the creation of a new journal: Transaction on Machine Learning Research (TMLR)
Learn more in our post: medium.com/@hugo_larochelle_…
3
19
281
(I know the timing is not great, but this was recorded a couple of months ago.)
Episode 17 is out! Jeff Dean (@JeffDean) on Humans of AI: Stories, Not Stats.
Video: piped.video/Tw2ntkjCo7E
Podcast: anchor.fm/humanstoriesai/epi…
All episodes so far: humanstories.ai
6
10
288
One year ago, @abhshkdz and I left Meta to start Yutori.
Ten months ago, @DhruvBatraDB joined us :)
Nine months ago, we crystallized our vision.
Two months ago, we released a sneak peak into what we’ve been building.
Today, can’t be more excited to fully unveil @yutori_ai’s mission, ambitious vision, world-class team, and stellar backers!
Join our waitlist for early access to our product in the coming days and weeks! 👇🏼
18
37
292
63,317
Crowdsourced generative art gallery 👇🏽
This is art created and described by 66 anonymous individuals on Amazon Mechanical Turk. They used a “Create Your Own” tool from cc.gatech.edu/~parikh/art.ht… to make these. I'll post one ~every week.
#generativeart #creativecoding #crowdsourced
5
44
252
Any guesses on how many papers will be submitted to #iccv2021 with "Transformers" in the title? :)
16
8
242
Day 1 of a first-in-at-least-18-years, 40-day, entirely-unplugging-from-work break! The calmest early Thursday afternoon in a while :)
11
1
244
20,542
🎉🎉🎉 We gave artists and non-artists access to Make-A-Scene! Here's what they created and thought of it: ai.facebook.com/blog/greater…
Make-A-Scene lets you sketch an image composition in addition to describing it, making it a more powerful tool for creative expression.
@MetaAI
8
41
240
All the talks are now online!
A big thank you to all the speakers for the amazing talks! Many attendees told us that they got a lot out of the talks and discussions, and many who missed the event have been pinging us for links to the slides and talks :)
cc.gatech.edu/~parikh/citize…
4
86
225
In these interviews, we will try to see the human behind the work :)
We talk about who they are as a person, what their life is like, what they think about, are insecure about, get excited about. The story of their day-to-day life.
Stay tuned at humanstories.ai!
4
25
217
Thank you to the award committee and the broader vision community for the recognition. After all these (21!) years and so many conferences across sub-disciplines in AI, the vision community continues to feel like home.
What makes this extra special is that the original VQA paper, where we first introduced the VQA task and v1 of the dataset, was published at ICCV, exactly 10 years ago!
“We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer….” It is quite simply ridiculous how far the field has come since!
Congratulations to all the VQA authors, and the VQA challenge + workshop organizers over the years! GG :)
#ICCV2025
15
12
215
28,926
So much relief all around. So much hope. So much positivity. It's been a while :)
It's crazy how inspiring just basic decency and coherence in thought feels...
1
7
214
🎉FAIR and Meta Open Arts in Times Square!🎉
Sofia Crespo's FAIR Artists in Residence project, Critically Extant, is being featured in Times Square Arts Midnight Moment every night this month.
@MetaAI @soficrespo91
If you're in New York, go check it out 🙂
5
31
201
Episode 6 is out! Jitendra Malik on Humans of AI: Stories, Not Stats.
Video: piped.video/RqUBLSqiowE
Podcast: anchor.fm/humanstoriesai/epi…
All episodes so far: humanstories.ai
2
23
198
Very excited to announce Emu Edit and Emu Video!
Tell Emu Edit how you want an image edited and it will do precisely that.
Tell Emu Video what you want to see and it will generate a high quality video.
(Be sure to watch till the end!)
Links to a bunch of examples + papers👇
7
28
195
76,329
I don't like small talk. I like real connections. So I often "do questions" where everyone answers a question on the table. Meaningful discussions tend to follow.
It can be a struggle to think of questions though. So I made a website to help with that :)
cc.gatech.edu/~parikh/questi…
5
36
193
Few things feel as good as (in no particular order):
1. A piece of your code doing what you want it to.
2. An empty inbox and to-do list.
3. High-bandwidth, successful communication of nuanced thoughts with a fellow human being.
3
17
195
Check out our demo of a single model for 8 different vision+language tasks! Give it an image + a question, it will answer it. Give it an image + a caption, it will score it. Give it an image + a phrase, it will draw a box around where that object is. Etc. vilbert.cloudcv.org
9
43
191
It's here!
Introducing Scouts by Yutori. Scouts is like having a team of agents monitoring the web for information that matters to you.
We're letting more users in everyday. Join the waitlist!
We're excited to launch Scouts — always-on AI agents that monitor the web for anything you care about.
8
15
199
33,569
Humans of AI: Stories, Not Stats (at least this "season") is a wrap! I thoroughly enjoyed these 18 conversations. I hope you found these to be valuable. A huge thank you to all the 18 guests for taking the time to do these!
humanstories.ai
6
8
187
Anyone else jet lagged because of daylight savings? Anyone else can’t believe it is a thing to just move all clocks forward and backward twice a year?!
8
1
178
OpenAI's announcement of Operator on Thursday was a great excuse for us to come out of stealth to show off the AI agents tech we've been building at Yutori. Which means I can now say out loud — we're hiring!
Our current top hiring priorities are an awesome founding frontend engineer, followed by backend and full-stack engineers, followed by designers and AI scientists/engineers.
Apply, and spread the word! @yutori_ai
Link👇
Excited to share a sneak peek into what we've been building at Yutori!
What you see below is our trained model and internal prototype — multiple agents running in parallel in the background, completing tasks of varying complexity, relevant information and cues to step in being surfaced to the user.
More examples 👇
This is barely scratching the surface of what agents can do for you day-to-day.
Follow along at @yutori_ai — more to come soon!
9
22
175
64,541
I started seeing some activity on this blog post -- so figured that's a good reminder to re-share this given the upcoming #CVPR2021 rebuttal deadline :)
Keep in mind that this is just what we (@stefmlee, @DhruvBatraDB, and I) tend to follow, YMMV.
medium.com/@deviparikh/how-w…
3
37
174
👋🏼 Emu
Turns out, a VERY small amount of EXTREMELY high quality fine-tuning data makes a HUGE difference in the quality of images generated using text-to-image models, without compromising on the generality of visual concepts they can depict.
Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
paper page: huggingface.co/papers/2309.1…
Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text. However, these pre-trained models often face challenges when it comes to generating highly aesthetic images. This creates the need for aesthetic alignment post pre-training. In this paper, we propose quality-tuning to effectively guide a pre-trained model to exclusively generate highly visually appealing images, while maintaining generality across visual concepts. Our key insight is that supervised fine-tuning with a set of surprisingly small but extremely visually appealing images can significantly improve the generation quality. We pre-train a latent diffusion model on 1.1 billion image-text pairs and fine-tune it with only a few thousand carefully selected high-quality images. The resulting model, Emu, achieves a win rate of 82.9% compared with its pre-trained only counterpart. Compared to the state-of-the-art SDXLv1.0, Emu is preferred 68.4% and 71.3% of the time on visual appeal on the standard PartiPrompts and our Open User Input benchmark based on the real-world usage of text-to-image models. In addition, we show that quality-tuning is a generic approach that is also effective for other architectures, including pixel diffusion and masked generative transformer models.
3
15
159
54,070
An interesting project!
hownormalami.eu/press/
-----
I am 50% normal. Test yourself at hownormalami.eu #HowNormalAmI
9
40
150
I gave a bit of an unusual keynote talk at #iclr2024 last month. I shared five stories from my 20-year journey in AI so far.
It had felt like a bit of a gamble. I wasn’t sure how it would be received.
But from the feedback I got in the days and weeks after, it seems like at least some folks found it to be quite valuable. (Hard to know what %, the ones who thought it was a terrible idea are less likely to reach out, or may have skipped the talk entirely :))
The stories were about
1. Following through on all exciting threads
2. Learnt reward functions
3. Fleeting opportunities
4. Multidimensional impact landscapes
5. Curiosity for new experiences
The talk is now publicly available: iclr.cc/virtual/2024/invited…
4
12
155
23,745
Episode 8 is out! Joelle Pineau on Humans of AI: Stories, Not Stats.
Video: piped.video/U3VL-RFbjJM
Podcast: anchor.fm/humanstoriesai/epi…
All episodes so far: humanstories.ai
1
14
152
A playground for audio-video-text understanding and generation — a good way to explore problems in multimodal AI without needing a ton of compute and humungous datasets!
Paper, data, code, baselines available mugen-org.github.io/
3
32
152
I built this simple drawing tool that enforces symmetry (on top of a sketching UI Larry Zitnick had built).
It is surprisingly fun :) Give it a shot! And of course, share anything you make :)
I'll start :)
cc.gatech.edu/~parikh/create…
5
15
157
Episode 7 is out! Hugo Larochelle (@hugo_larochelle) on Humans of AI: Stories, Not Stats.
Video: piped.video/g5Tcvq0nskI
Podcast: anchor.fm/humanstoriesai/epi…
All episodes so far: humanstories.ai
4
18
150
Episode 3 is out! Vladlen Koltun on Humans of AI: Stories, Not Stats.
Video: piped.video/b2_CyYkqzK0
Podcast: anchor.fm/humanstoriesai/epi…
All episodes so far: humanstories.ai
8
17
154
Every day in 2022, I wrote down a couple of lines of salient things from the day. Every Sunday, pulled out a couple of lines of salient things from the week. Same for every month. It's a nice, grounded summary of 2022. Was hoping to get more out of it, but I recommend trying it.
6
7
149
34,230
There's been excitement around #BigSleep by @advadnoun -- CLIP + BigGAN to generate images that match a description.
I was curious how it handles other languages.
I tried "ek khoobsurat phool" -- Hindi for "a beautiful flower" and got this 😮
Link to colab notebook 👇
4
12
149
Yutori means mental spaciousness. Productivity isn't about cramming more and more into your day — it's reclaiming your attention for what matters to you. It's about directing your energy to amplify outcomes that count. It's about creating space for the meaningful things in life.
3
8
146
12,817
❤️… and not ashamed of it :)
(I wish more of my computer vision friends were on X, they’d probably approve :))
19
5
145
41,650
Excited to announce that Cushions is coming to Art Blocks (@artblocks_io) on Jan 7th at 3 pm ET! 🎉
I'll share more about the project over the coming weeks, stay tuned :)
#generative #generativeart #genartclub #cushions #artblocks
14
11
138
I realized that I hate doing things at the last minute partly because then later I *have* to do that thing that's due. I find that suffocating. I do things ahead of time so I can always do what I want. That is, ~ironically?, I do things ahead of time so I can be irresponsible.
5
1
145
#CVPR2020 is happening! I oscillate between "Argh, I miss the in-person energy and activities" and "Ah, it is so nice to have access to all this content + people from the comfort of my home, being able to see and hear everything clearly [i-am-short]".
How is it going for you?
10
2
141
Visual Dialog: code, demo (i.e., a chatbot that can see), AND code for demo: all now available at visualdialog.org!
84
141
Unit Origami
It was easier to fold than I thought it would be before I saw the instructions. Totally worth trying out (even with printer or notebook or magazine paper you might have lying around). Link to instruction video I followed 👇
7
3
143
Looking forward to speaking at this event at @iiit_hyderabad next week!
Zoom link: iiit-ac-in.zoom.us/j/9241545…...
YouTube link: bit.ly/3uRgkXu
3
8
137
For junior faculty, I talk about strategies for growing your lab, setting a culture, investing in compute, being intentional about how you spend time, being resourceful, maximizing sparks of joy, not getting too attached to your first batch of students :)
piped.video/C3cWsZZYx9g
Wonder how to start your faculty career? grow in company? secure PhD offers? Check our #ICCV'21 workshop on Share Stories and Lessons Learned. As a warm-up, we have released some recorded talks from @dimadamen @deviparikh @xinshuoweng @zhoubolei and a few live talks upcoming!
1
17
131
Faster, multi-GPU, multi-image-batched, PyTorch implementation of faster R-CNN. Gets ~36.7 mAP on COCO in ~36 hours on 8 Titan Xs! By @jw2yang4ai and @jiasenlu. github.com/jwyang/faster-rcn…
2
26
134
Introducing a Re-sliced version of Humans of AI: Stories, No Stats!
We are releasing videos that contain answers from all guests to the same question. All thanks to the efforts of @VarshiniSubhash and @mkulkhanna!
Answers to question 1 👉 piped.video/G1lQLJVFiYg
4
12
127
A version of a note I wrote recently on how I sustain and how I approach work-life balance.
deviparikh.substack.com/p/in…
4
18
121
Lana Lazebnik’s short course on “Computer Vision: Looking Back to Look Forward” from when she was visiting Georgia Tech.
Amazing resource! Will give you a fresh perspective over only reading papers from the last few years or months or weeks :)
slazebni.cs.illinois.edu/spr…
36
119
Should we switch from “Can you see my screen?” followed by long pause till someone unmutes and answers to “You should be able to see my screen now. Let me know if not.” and continue talking?
3
6
121
A fun project where Gunjan Aggarwal (@gunjan050) and I automatically generate (simple) music for an input dance!
Examples attached.
Paper: arxiv.org/abs/2107.06252
Video of a live demo: sites.google.com/view/dance2…
5
12
125
Generative models are a class of models that model the distribution of data — p(x). It doesn’t comment on how the data is represented (pixels, language tokens, spatial image tokens, spatiotemporal video tokens, intermediate representations, etc.), or what the specific architectural choices are to build the model, does it?
So then isn’t a lot of the debate on “generative models” vs. “intermediate representations” talking about two orthogonal things, and as a result talking past each other?
Or am I missing something?
CC @ylecun :)
6
9
122
42,294
Very excited about our work on creative sketching!
Two datasets of ~10k sketches with part annotations
DoodlerGAN: A part-based GAN
(Super fun!) Web demo: doodlergan.cloudcv.org/creat…
Paper + code: arxiv.org/abs/2011.10039
Work led by Songwei Ge. With @vedanujg and Larry Zitnick.
2
17
115
Happy Diwali and Happy Halloween folks!
Here’s Meta AI imagining me celebrating both Diwali and Halloween :) And apparently waay younger! :)
4
2
118
6,493
Really good! My favorite (edited) snippet: lead or be led
If you are expecting to be told what to do, then someone will. It might not be the best thing to be doing.
Alternatively, if you show up with a convincing game plan, then people will get out of your way so you can do it.
13
110
Congratulations @DhruvBatraDB! 🎉🎉🎉
whitehouse.gov/briefings-sta…
PECASE is the highest honor bestowed by the US Government to early-career scientists and engineers who show exceptional promise for leadership in science and technology.
3
11
114
Check out Neural Baby Talk (spotlight at #CVPR18) by @jiasenlu and @jw2yang4ai. Code: github.com/jiasenlu/NeuralBa…. Paper: arxiv.org/abs/1803.09845.
2
34
114
Routine in India in the past few days: Wake up, email, one work to-do, breakfast, art to-dos (for upcoming project releases), lunch with family, art (#genuary2022), chit chat with family, dinner, chit chat with family, sleep. Repeat. Expecting >1 work to-dos starting tomorrow :)
113
Everyone on the team @yutori_ai gets a hand-crocheted coaster from me when they join. As Scouts power users are starting to emerge, thinking of doing the same for them :)
5
4
111
6,511
SplitNet decouples perception and policy learning in visual navigation to allow for transfer across tasks and simulators (as a step towards sim2real transfer).
Video: piped.video/watch?v=TJkZcsD2…
Code: github.com/facebookresearch/…
Paper: arxiv.org/abs/1905.07512
25
110
Inspired by this, we converted two lab meetings to let's-teach-each-other-something-non-AI meetings. We covered Origami (theory and practice), Fountain Pens, Coffee, The Cup Song, and Games People Play In The Gym! It was awesome! You should try it in your circle of influence :)
Today we co-opted our regular group mtg into a🦃 teach-in, with drop-in cameos from alumni and friends all over.
Topics we taught us ranged from Queen's Gambit to Bob Ross painting to photography to crypto currency get-riches to a do-calculus tl;dr.
Happy Pandemic Thanksgiving!
6
111
Protip to @CVPR reviewers: Reviews are due Jan 4. You're not going to enjoy reviewing all papers over the weekend between Jan 2nd and 4th. So spread them out between now and when you plan on starting your winter break. You'll be at peace *and* the reviews will likely be better.
1
6
111
Came across this somewhere. Thought it was beautiful.
Low-ego, high-heart. Invisible but present. Rooted but not weighed down.
5
4
110
7,443
A long video generation model that can train on clips that have 10s of frames but can generate videos that have >1000 frames.
Some specific technical details make this possible. Check it out!
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
abs: arxiv.org/abs/2204.03638
project page: songweige.github.io/projects…
15
103
Let a thousand flowers bloom. 10,000 circles.
Jan 1: "Draw 10,000 of something"
genuary.art/prompts#jan1
#genuary #genuary2022 #generative #generativeart #genartclub
3
3
100
Episode 4 is out! Antonio Torralba on Humans of AI: Stories, Not Stats.
Video: piped.video/2ckxpBrVGFY
Podcast: anchor.fm/humanstoriesai/epi…
All episodes so far: humanstories.ai
1
16
108
Dhruv (pre-coffee, ~lethargic, deciding what jacket to wear before stepping out to get coffee and read a book in the park): Alexa, temperature
Alexa: [Starts saying something that we can't hear]
Dhruv: Alexa, increase vol...
Alexa: [Doesn't hear him, keeps mumbling]
Dhruv: Alexa! Increase vol...
Alexa: [Doesn't hear him, keeps mumbling]
Dhruv: ALEXA! INCREASE VOLUME!
Alexa: [Stops talking. Has presumably heard him, has presumably increased volume, but has now forgotten the original task]
Dhruv: Alexa. Temperature yaar!
Alexa: [Says temperature, but at this point we've both cracked up and can't stop laughing 😂]
Dhruv does a few other things, 10 minutes pass, now really ready to put on a jacket and step out
Dhruv: What was the temperature again?
Dhruv: Alexa, temperature
Alexa: [Doesn't hear him...]
Dhruv: Alexa! Temperature
Me: 😂😂😂
Happy Sunday morning folks!
(@DhruvBatraDB)
1
2
104
9,589
Cushions supports more than 5 billion possibilities🚀across 13 features. Curious to see which 200 will be revealed @artblocks on Jan 7th :)
Out of 1000 simulations, on average, two pieces have 4 out of the 13 features in common.
Ropsten mints 8, 17, 24, 44
#generativeart
4
12
103
I quite like the aesthetic of these! Taking children's drawings, down-sampling them, and then increasing their resolution again using Real-ESRGAN (huggingface.co/spaces/akhali…)
2
9
100