Загрузка видео...

Не удалось загрузить видео

На главную

We are also releasing self-contained lecture notes that explain flow matching and diffusion models from scratch. This goes from "zero" to the state-of-the-art in modern Generative AI. 📖 Read the notes here: Joint work with Ezra Erives.

peholderrieth's profile picture

Peter Holderrieth

5,029 subscribers

475,659 просмотров • 4 месяцев назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

This account posting fake community notes in all my posts needs to be banned from X and removed from Community Notes These notes are wrong and I’ve posted proof in the replies to other people already.
0:19

This account posting fake community notes in all my posts needs to be banned from X and removed from Community Notes These notes are wrong and I’ve posted proof in the replies to other people already.

Ashton Forbes

25,081 просмотров • 1 год назад

Sell art with ZERO fees 🤯 You read that right: ZERO selling fees. When we say we are here to empower artists, we mean it! Keep 100% of the listing price.
0:12

Sell art with ZERO fees 🤯 You read that right: ZERO selling fees. When we say we are here to empower artists, we mean it! Keep 100% of the listing price.

Exchange Art

41,817 просмотров • 3 лет назад

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.
0:19

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.

AK

25,449 просмотров • 2 лет назад

Harness the power of generative AI without just prompting and hoping for the best. From Unbound Slop to Tripo🔜SIGGRAPH2026 to Unreal Engine, we love this workflow for generating 3D models.
0:17

Harness the power of generative AI without just prompting and hoping for the best. From Unbound Slop to Tripo🔜SIGGRAPH2026 to Unreal Engine, we love this workflow for generating 3D models.

Unbound

26,532 просмотров • 3 месяцев назад

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead
0:16

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead

Marvin

24,954 просмотров • 1 месяц назад

Just gave my first academic lecture in French at the amazing conference (OK so I had to read from my translated lecture notes, but still!) Covered chlorine dioxide (“dioxy de chlor”) and DMSO in just under an hour too! Vive La France 🇫🇷
0:16

Just gave my first academic lecture in French at the amazing conference (OK so I had to read from my translated lecture notes, but still!) Covered chlorine dioxide (“dioxy de chlor”) and DMSO in just under an hour too! Vive La France 🇫🇷

Pierre Kory, MD MPA

30,415 просмотров • 10 месяцев назад

That was quick! Valentine's cross update is available NOW in the Skullgirls 2nd Encore Beta on Steam! Why are we making these changes? The short version is: we had to! For the long version, read the full update notes here:
0:14

That was quick! Valentine's cross update is available NOW in the Skullgirls 2nd Encore Beta on Steam! Why are we making these changes? The short version is: we had to! For the long version, read the full update notes here:

Skullgirls

593,092 просмотров • 2 лет назад

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.
0:10

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.

Mihir Prabhudesai

104,934 просмотров • 1 год назад

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation
0:19

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

AK

41,746 просмотров • 3 лет назад

Big news from Boltz - our biggest update yet! 🚀 Today we’re releasing two new state-of-the-art models for protein and small molecule design with extensive wet lab validation and a new API to run all of our models on scalable GPUs wherever you (or your agents) work! 🔥
0:11

Big news from Boltz - our biggest update yet! 🚀 Today we’re releasing two new state-of-the-art models for protein and small molecule design with extensive wet lab validation and a new API to run all of our models on scalable GPUs wherever you (or your agents) work! 🔥

Gabriele Corso

136,586 просмотров • 1 месяц назад

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:
0:20

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,532 просмотров • 2 лет назад

Okay, this is seriously cool. A team from Google DeepMind, including DeepMind Cofounder Shane Legg, published a paper "From AGI to ASI". In the paper, they include instructions for an AI agent to read along with you. You can open the paper in Codex's in-app browser and have GPT-5.5 read it with you and explain all the concepts. This is the future. AI agents will be part of the target audience, and help us to understand anything we want.
0:18

Okay, this is seriously cool. A team from Google DeepMind, including DeepMind Cofounder Shane Legg, published a paper "From AGI to ASI". In the paper, they include instructions for an AI agent to read along with you. You can open the paper in Codex's in-app browser and have GPT-5.5 read it with you and explain all the concepts. This is the future. AI agents will be part of the target audience, and help us to understand anything we want.

Dan McAteer

53,480 просмотров • 1 месяц назад

Introducing benchmark tracking across all of arXiv With thousands of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!
0:17

Introducing benchmark tracking across all of arXiv With thousands of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!

alphaXiv

10,892 просмотров • 7 месяцев назад

Are you worried about AI deep fakes becoming the norm over the next few years? Yesterday this deep fake video of Mr. Beast began circulating. It directed users to a link that could have scammed them. The video is virtually indistinguishable from reality unless you are Mr Beasts’ Mom. So what are the answer on how to stop this? 1) Community notes will be a powerful tool if also combined with machine learning to tag any and all of the fake videos on the platform. 2) If a video is found to be a deep fake via Community notes X should highlight the fact. 3) We need Continued development of good AI to push back on the bad AI. Thoughts?
0:14

Are you worried about AI deep fakes becoming the norm over the next few years? Yesterday this deep fake video of Mr. Beast began circulating. It directed users to a link that could have scammed them. The video is virtually indistinguishable from reality unless you are Mr Beasts’ Mom. So what are the answer on how to stop this? 1) Community notes will be a powerful tool if also combined with machine learning to tag any and all of the fake videos on the platform. 2) If a video is found to be a deep fake via Community notes X should highlight the fact. 3) We need Continued development of good AI to push back on the bad AI. Thoughts?

Brian Krassenstein

69,365 просмотров • 2 лет назад

Version 1.13b just released! Replacing Workspaces with a new way to manage your tabs: Spaces. This update also delivers multiple fixes for more stability and security. Please read the full release notes here
0:16

Version 1.13b just released! Replacing Workspaces with a new way to manage your tabs: Spaces. This update also delivers multiple fixes for more stability and security. Please read the full release notes here

Zen

60,903 просмотров • 1 год назад

Shout-out to the artist community We love art, images, and ideas that make the world feel different, even strange at times. As a team, we are always curious about new art and enjoy sharing the gems we stumble upon with our community. From photography to AI and code-based art, here are some of the works we have loved over the past few weeks. We hope you enjoy them as much as we do! ↓
0:25

Shout-out to the artist community We love art, images, and ideas that make the world feel different, even strange at times. As a team, we are always curious about new art and enjoy sharing the gems we stumble upon with our community. From photography to AI and code-based art, here are some of the works we have loved over the past few weeks. We hope you enjoy them as much as we do! ↓

Fellowship

28,756 просмотров • 3 месяцев назад

We're launching something new: Collaborative Notes The idea: when you request a note, AI drafts one — then the community refines it together through ratings and suggestions. You can watch it get better in real time. It’s a whole new way for the public to work with AI — and each other — to make information more accurate. And a whole new way to contribute to Community Notes. For now, only requests from Top Writers on English-language posts generate Collaborative Notes, and you must have 2+ Writing Impact to make suggestions. We plan to expand that & shape the experience based on your feedback. As usual, it’s open-source:
0:12

We're launching something new: Collaborative Notes The idea: when you request a note, AI drafts one — then the community refines it together through ratings and suggestions. You can watch it get better in real time. It’s a whole new way for the public to work with AI — and each other — to make information more accurate. And a whole new way to contribute to Community Notes. For now, only requests from Top Writers on English-language posts generate Collaborative Notes, and you must have 2+ Writing Impact to make suggestions. We plan to expand that & shape the experience based on your feedback. As usual, it’s open-source:

Community Notes

7,776,005 просмотров • 5 месяцев назад

INDIAN DRONE MOTORS !!! Yes you read that right, Vector Technics from Hyderabad is making Drone motors in India from scratch from steel to the finished product, These motors are also exported Globally, i got to do a rare tour of their factory, video linked in reply
0:17

INDIAN DRONE MOTORS !!! Yes you read that right, Vector Technics from Hyderabad is making Drone motors in India from scratch from steel to the finished product, These motors are also exported Globally, i got to do a rare tour of their factory, video linked in reply

Gareeb Scientist

433,143 просмотров • 11 месяцев назад