Hernan Moraldo
@hmoraldo.bsky.social
Google DeepMind. Generative models for video: Veo, Phenaki.
Reposted by Hernan Moraldo
THIS IS HUGE! Researchers at Stanford University have developed a dual-antibody treatment that remains effective against ALL SARS-CoV-2 variants by targeting a less-mutable part of the virus. This breakthrough could lead to longer-lasting therapies that OUTPACE viral evolution. 🧪🧵⬇️
March 9, 2025 at 4:00 PM
THIS IS HUGE! Researchers at Stanford University have developed a dual-antibody treatment that remains effective against ALL SARS-CoV-2 variants by targeting a less-mutable part of the virus. This breakthrough could lead to longer-lasting therapies that OUTPACE viral evolution. 🧪🧵⬇️
Reposted by Hernan Moraldo
We are hiring on the Generative Media team in London: boards.greenhouse.io/deepmind/job...
We work on Imagen, Veo, Lyria and all that good stuff. Come work with us! If you're interested, apply before Feb 28.
We work on Imagen, Veo, Lyria and all that good stuff. Come work with us! If you're interested, apply before Feb 28.
Research Scientist, Generative Media
London, UK
boards.greenhouse.io
February 21, 2025 at 7:00 PM
We are hiring on the Generative Media team in London: boards.greenhouse.io/deepmind/job...
We work on Imagen, Veo, Lyria and all that good stuff. Come work with us! If you're interested, apply before Feb 28.
We work on Imagen, Veo, Lyria and all that good stuff. Come work with us! If you're interested, apply before Feb 28.
Reposted by Hernan Moraldo
This paper is wild - a Stanford team shows the simplest way to make an open LLM into a reasoning model
They used just 1,000 carefully curated reasoning examples & a trick where if the model tries to stop thinking, they append "Wait" to force it to continue. Near o1 at math. arxiv.org/pdf/2501.19393
They used just 1,000 carefully curated reasoning examples & a trick where if the model tries to stop thinking, they append "Wait" to force it to continue. Near o1 at math. arxiv.org/pdf/2501.19393
February 7, 2025 at 2:53 AM
This paper is wild - a Stanford team shows the simplest way to make an open LLM into a reasoning model
They used just 1,000 carefully curated reasoning examples & a trick where if the model tries to stop thinking, they append "Wait" to force it to continue. Near o1 at math. arxiv.org/pdf/2501.19393
They used just 1,000 carefully curated reasoning examples & a trick where if the model tries to stop thinking, they append "Wait" to force it to continue. Near o1 at math. arxiv.org/pdf/2501.19393
More Veo 2 examples
Prompt: "A snail wearing pants. The snail is riding a bicycle, and has a large moustache." #veo2
Following a comment by thelokasiffers in Twitter
Prompt: "A snail wearing pants. The snail is riding a bicycle, and has a large moustache." #veo2
Following a comment by thelokasiffers in Twitter
December 18, 2024 at 8:50 PM
More Veo 2 examples
Prompt: "A snail wearing pants. The snail is riding a bicycle, and has a large moustache." #veo2
Following a comment by thelokasiffers in Twitter
Prompt: "A snail wearing pants. The snail is riding a bicycle, and has a large moustache." #veo2
Following a comment by thelokasiffers in Twitter
More Veo 2 examples
Prompt: "A cat wearing a suit and a top hat, while driving a tractor. The tractor has lots of hay on top. Cinematic.!"
Prompt: "A cat wearing a suit and a top hat, while driving a tractor. The tractor has lots of hay on top. Cinematic.!"
December 17, 2024 at 12:19 AM
More Veo 2 examples
Prompt: "A cat wearing a suit and a top hat, while driving a tractor. The tractor has lots of hay on top. Cinematic.!"
Prompt: "A cat wearing a suit and a top hat, while driving a tractor. The tractor has lots of hay on top. Cinematic.!"
December 16, 2024 at 9:40 PM
Action scenes (with realistic physics!) with Veo! #veo2
Prompt: "Car going at top speed through a road, until reaching a waterfall. It gets into the waterfall and jumps off a mountain. Cinematic, 35mm film."
Prompt: "Car going at top speed through a road, until reaching a waterfall. It gets into the waterfall and jumps off a mountain. Cinematic, 35mm film."
December 16, 2024 at 9:30 PM
Action scenes (with realistic physics!) with Veo! #veo2
Prompt: "Car going at top speed through a road, until reaching a waterfall. It gets into the waterfall and jumps off a mountain. Cinematic, 35mm film."
Prompt: "Car going at top speed through a road, until reaching a waterfall. It gets into the waterfall and jumps off a mountain. Cinematic, 35mm film."
December 16, 2024 at 9:22 PM
Example video generated with Veo #Veo2
Prompt: The camera follows an octopus flying through a city with very high skyscrapers. A sign says "Veo". Cinematic, 35mm film released in 2024.
Prompt: The camera follows an octopus flying through a city with very high skyscrapers. A sign says "Veo". Cinematic, 35mm film released in 2024.
December 16, 2024 at 8:48 PM
Example video generated with Veo #Veo2
Prompt: The camera follows an octopus flying through a city with very high skyscrapers. A sign says "Veo". Cinematic, 35mm film released in 2024.
Prompt: The camera follows an octopus flying through a city with very high skyscrapers. A sign says "Veo". Cinematic, 35mm film released in 2024.
Veo v2 generates a meeting of animals #Veo2
Prompt: A meeting of a lion, a bear and a giraffe, all of them wearing suits. Photorealistic, cinematic.
Prompt: A meeting of a lion, a bear and a giraffe, all of them wearing suits. Photorealistic, cinematic.
December 16, 2024 at 8:43 PM
Veo v2 generates a meeting of animals #Veo2
Prompt: A meeting of a lion, a bear and a giraffe, all of them wearing suits. Photorealistic, cinematic.
Prompt: A meeting of a lion, a bear and a giraffe, all of them wearing suits. Photorealistic, cinematic.
Proud to see the release of Veo V2! deepmind.google/technologies...
"Veo has achieved state of the art results in head-to-head comparisons of outputs by human raters over top video generation models"
"Veo has achieved state of the art results in head-to-head comparisons of outputs by human raters over top video generation models"
Veo 2
Veo is our state-of-the-art video generation model. It creates high quality video clips that match the style and content of a user's prompts, in resolutions up to 4K resolution.
deepmind.google
December 16, 2024 at 5:15 PM
Proud to see the release of Veo V2! deepmind.google/technologies...
"Veo has achieved state of the art results in head-to-head comparisons of outputs by human raters over top video generation models"
"Veo has achieved state of the art results in head-to-head comparisons of outputs by human raters over top video generation models"
Reposted by Hernan Moraldo
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
December 4, 2024 at 4:01 PM
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
Fascinating account of the history of attention, as told by Dzmitry Bahdanau to Andrej Karpathy x.com/karpathy/sta...
x.com
x.com
December 4, 2024 at 5:26 AM
Fascinating account of the history of attention, as told by Dzmitry Bahdanau to Andrej Karpathy x.com/karpathy/sta...
I love the notations and methods people in different fields invent for their work. For example the Megadeth drummer: "I developed a method for, when listening to a song for the first time, just count, name the parts, count the bars, and (...) have the structure" (youtu.be/tbUYVcaF_l0?... at 2:35)
Megadeth Drummer Hears "Mr. Brightside" For The First Time
YouTube video by Drumeo
youtu.be
December 1, 2024 at 6:52 PM
I love the notations and methods people in different fields invent for their work. For example the Megadeth drummer: "I developed a method for, when listening to a song for the first time, just count, name the parts, count the bars, and (...) have the structure" (youtu.be/tbUYVcaF_l0?... at 2:35)
.kkrieger is one of my favorite feats of engineering. A game released in the same year than Doom 3, with graphics of similar quality, that fits fully into 96kb. youtu.be/DN4Dtio8zKA?...
.kkrieger - Wikipedia
en.m.wikipedia.org
November 30, 2024 at 5:42 PM
.kkrieger is one of my favorite feats of engineering. A game released in the same year than Doom 3, with graphics of similar quality, that fits fully into 96kb. youtu.be/DN4Dtio8zKA?...
I've often used both print-based debugging, and debugger tools in my work. A great middle ground option is printed-out stack traces at key points of a program
November 29, 2024 at 5:10 PM
I've often used both print-based debugging, and debugger tools in my work. A great middle ground option is printed-out stack traces at key points of a program
I always liked Named Tensor Notation, it's a bit unfortunate it isn't used more namedtensor.github.io
Named Tensor NotationNamed Tensor Notation
namedtensor.github.io
November 28, 2024 at 7:08 PM
I always liked Named Tensor Notation, it's a bit unfortunate it isn't used more namedtensor.github.io
It was often concluded from emergent behaviors like that of Flocking / Boids (en.m.wikipedia.org/wiki/Boids) that real creatures probably followed similarly simple algorithms too. But given enough brain complexity and an RL-like learning process, they couldn't learn such cleanly disentangled rules.
Boids - Wikipedia
en.m.wikipedia.org
November 28, 2024 at 6:56 AM
It was often concluded from emergent behaviors like that of Flocking / Boids (en.m.wikipedia.org/wiki/Boids) that real creatures probably followed similarly simple algorithms too. But given enough brain complexity and an RL-like learning process, they couldn't learn such cleanly disentangled rules.
Reposted by Hernan Moraldo
Stop watching videos, start interacting with worlds.
Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
cat-4d.github.io
arxiv.org/abs/2411.18613
Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
cat-4d.github.io
arxiv.org/abs/2411.18613
November 28, 2024 at 2:52 AM
Stop watching videos, start interacting with worlds.
Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
cat-4d.github.io
arxiv.org/abs/2411.18613
Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
cat-4d.github.io
arxiv.org/abs/2411.18613
The article asks "Will AI lead to useful predictions at the expense of deeper scientific understanding?"
Worth thinking about the same question for engineering (e.g. code gen). How do you trade off the short term productivity gains vs. the long term ones given by increased understanding?
Worth thinking about the same question for engineering (e.g. code gen). How do you trade off the short term productivity gains vs. the long term ones given by increased understanding?
New essay by DeepMind about AI for scientific discovery, there's a lot of interesting ideas and citations to others's work here
deepmind.google/public-polic...
deepmind.google/public-polic...
A new golden age of discovery
In this essay, we take a tour of how AI is transforming scientific disciplines from genomics to computer science to weather forecasting. Some scientists are training their own AI models, while...
deepmind.google
November 27, 2024 at 2:23 AM
The article asks "Will AI lead to useful predictions at the expense of deeper scientific understanding?"
Worth thinking about the same question for engineering (e.g. code gen). How do you trade off the short term productivity gains vs. the long term ones given by increased understanding?
Worth thinking about the same question for engineering (e.g. code gen). How do you trade off the short term productivity gains vs. the long term ones given by increased understanding?
Reposted by Hernan Moraldo
New essay by DeepMind about AI for scientific discovery, there's a lot of interesting ideas and citations to others's work here
deepmind.google/public-polic...
deepmind.google/public-polic...
A new golden age of discovery
In this essay, we take a tour of how AI is transforming scientific disciplines from genomics to computer science to weather forecasting. Some scientists are training their own AI models, while...
deepmind.google
November 26, 2024 at 2:13 PM
New essay by DeepMind about AI for scientific discovery, there's a lot of interesting ideas and citations to others's work here
deepmind.google/public-polic...
deepmind.google/public-polic...
I was pretty obsessed with the concept of high amounts of dimensions when I was very young. People from a math club teased me a bit about it... "who cares about that? It's pointless"
Fun to think how in my job now, I'm pretty often thinking in the behavior of very high dimensional objects.
Fun to think how in my job now, I'm pretty often thinking in the behavior of very high dimensional objects.
November 26, 2024 at 1:29 AM
I was pretty obsessed with the concept of high amounts of dimensions when I was very young. People from a math club teased me a bit about it... "who cares about that? It's pointless"
Fun to think how in my job now, I'm pretty often thinking in the behavior of very high dimensional objects.
Fun to think how in my job now, I'm pretty often thinking in the behavior of very high dimensional objects.
The starter packs are a brilliant solution to the bootstrapping problem in social networks. I don't think I ever saw a similar approach before.
For no particular reason, I really like these starter packs:
Google DeepMind: go.bsky.app/GZ4hZzu
Theoretical CS: go.bsky.app/6A6GRSi
ML Theory: go.bsky.app/21nFz12
Differential Privacy: go.bsky.app/A7ABG83
Google DeepMind: go.bsky.app/GZ4hZzu
Theoretical CS: go.bsky.app/6A6GRSi
ML Theory: go.bsky.app/21nFz12
Differential Privacy: go.bsky.app/A7ABG83
Google DeepMind Starter Pack
Join the conversation
go.bsky.app
November 24, 2024 at 7:09 PM
The starter packs are a brilliant solution to the bootstrapping problem in social networks. I don't think I ever saw a similar approach before.