正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Announcing Neo-1: the world’s most advanced atomistic foundation model, unifying structure prediction and all-atom de novo generation for the first time - to decode and design the structure of life 🧵(1/10)

Proxima

3,029 subscribers

331,840 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

ESMFold2 and the ESM-C family, now available for use! We’ve partnered with biohub (the ESM team’s new home), to provide day 1 access to their newly open-sourced series of models. The family of models show best-in-class results for structure prediction, de novo design, and protein-language model tasks.

ESMFold2 and the ESM-C family, now available for use! We’ve partnered with biohub (the ESM team’s new home), to provide day 1 access to their newly open-sourced series of models. The family of models show best-in-class results for structure prediction, de novo design, and protein-language model tasks.

Deniz Kavi

15,694 次观看 • 1 个月前

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵

Google DeepMind

1,467,448 次观看 • 2 年前

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:

Hong-Xing (Koven) Yu

66,846 次观看 • 1 年前

The 10 biggest medical research papers from this week (🧵) 1. A high resolution structure of the dopamine transporter - key to Parkinson's, schizophrenia, and addiction Here's what it looks like bound to cocaine, one of its ligands (in orange) (Study:

The 10 biggest medical research papers from this week (🧵) 1. A high resolution structure of the dopamine transporter - key to Parkinson's, schizophrenia, and addiction Here's what it looks like bound to cocaine, one of its ligands (in orange) (Study:

Samuel Hume

186,247 次观看 • 1 年前

Diffusion models are an amazing tool for cofolding, they allow us to predict a protein and the molecule bound to it at once. But they are not exactly fast and require a lot of denoising steps to get accurate predictions. So we distilled ours. Meet DeCAF-Pearl: the first flow map model for all-atom cofolding. Instead of inching along the denoising trajectory, a flow map learns to jump across it. DeCAF-Pearl runs structure generation ~5x faster than Pearl, our SOTA model, while still maintaining the performance of the teacher model. That speed up allows us to run larger experiments and generate more synthetic data to improve our models. Getting there meant reparameterizing into noise-level space to stabilize gradients, committing to clean-structure prediction to keep the rigid-alignment loss biomolecules needed, and building DeCAF-Search, one steering algorithm for every compute budget. For more technical details, read out blog post: And the paper:

Diffusion models are an amazing tool for cofolding, they allow us to predict a protein and the molecule bound to it at once. But they are not exactly fast and require a lot of denoising steps to get accurate predictions. So we distilled ours. Meet DeCAF-Pearl: the first flow map model for all-atom cofolding. Instead of inching along the denoising trajectory, a flow map learns to jump across it. DeCAF-Pearl runs structure generation ~5x faster than Pearl, our SOTA model, while still maintaining the performance of the teacher model. That speed up allows us to run larger experiments and generate more synthetic data to improve our models. Getting there meant reparameterizing into noise-level space to stabilize gradients, committing to clean-structure prediction to keep the rigid-alignment loss biomolecules needed, and building DeCAF-Search, one steering algorithm for every compute budget. For more technical details, read out blog post: And the paper:

Sergey Edunov

36,985 次观看 • 1 个月前

1 week ago, the world’s most advanced AI text-to-video model dropped: Runway Gen-3. I’ve seen people create absolute masterpieces with it. The 11 most jaw-dropping examples:

1 week ago, the world’s most advanced AI text-to-video model dropped: Runway Gen-3. I’ve seen people create absolute masterpieces with it. The 11 most jaw-dropping examples:

Longevity Dad

10,653,343 次观看 • 2 年前

Real-time generation isn’t about predicting the next pixel, it requires understanding the structure and context of a 3D world. That’s the shift. Read more about our real-time game-native diffusion model on our blog. Moonlake's Reverie v0.1.0

Real-time generation isn’t about predicting the next pixel, it requires understanding the structure and context of a 3D world. That’s the shift. Read more about our real-time game-native diffusion model on our blog. Moonlake's Reverie v0.1.0

Moonlake

14,439 次观看 • 7 个月前

1) What do Bitcoiners and 🇿🇦 South African Caves have in common? A 🧵thread on the world’s first example of proof of work and the birth of money:

1) What do Bitcoiners and 🇿🇦 South African Caves have in common? A 🧵thread on the world’s first example of proof of work and the birth of money:

Lyle Hauser

24,458 次观看 • 2 年前

-New Character Model Showcase- 🧵 Part 1: Poo Out of the chosen four, Poo is the one I took the most creative liberties with the design, so he has a few distinct details.

-New Character Model Showcase- 🧵 Part 1: Poo Out of the chosen four, Poo is the one I took the most creative liberties with the design, so he has a few distinct details.

Earthbound Dimensions

10,811 次观看 • 8 个月前

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)

Stability AI

181,479 次观看 • 1 年前

These are the most iconic moments on TV. A thread 🧵 1. This might just be one of the most brutal TV fails of all time

These are the most iconic moments on TV. A thread 🧵 1. This might just be one of the most brutal TV fails of all time

Today In History

21,513,643 次观看 • 11 个月前

The moment we've all been waiting for! 🤖🔥 Introducing you ChainGPT, our first #AI incubation project and a game-changing solution for navigating the complex world of #crypto and #blockchain technology. Their advanced AI model offers a wide range of use cases:👇 (1/2)

The moment we've all been waiting for! 🤖🔥 Introducing you ChainGPT, our first #AI incubation project and a game-changing solution for navigating the complex world of #crypto and #blockchain technology. Their advanced AI model offers a wide range of use cases:👇 (1/2)

Seedify

155,555 次观看 • 3 年前

The Quick Reaction Force is assigned to the #BorelFire tonight to provide structure protection for the communities of Bodfish and Havilah.

The Quick Reaction Force is assigned to the #BorelFire tonight to provide structure protection for the communities of Bodfish and Havilah.

SoCal

12,528 次观看 • 2 年前

The world’s largest sculpture of the markhor, Pakistan’s national animal, has been unveiled in the country’s Kaghan Valley. The 105-foot-high and 38-foot-wide structure took five years to complete.

The world’s largest sculpture of the markhor, Pakistan’s national animal, has been unveiled in the country’s Kaghan Valley. The 105-foot-high and 38-foot-wide structure took five years to complete.

Al Jazeera English

156,364 次观看 • 7 个月前

Not to be dramatic, but this is one of the most beautiful laptops we've ever made. With premium materials, unibody structure and ultra-thin curb appeal, the Dell XPS is a masterclass in minimalist design. 😌

Not to be dramatic, but this is one of the most beautiful laptops we've ever made. With premium materials, unibody structure and ultra-thin curb appeal, the Dell XPS is a masterclass in minimalist design. 😌

Dell Technologies

17,667 次观看 • 6 个月前

1 billion cells. One atlas. Today, Illumina introduces the Billion Cell Atlas, creating the most comprehensive map of human disease biology — and unlocking unparalleled speed and scale in AI for drug discovery. The Atlas will help researchers, including founding participants AstraZeneca, Merck, and Eli Lilly and Company study the effect of switching on and off all 20,000 genes in cells linked to diseases that have been historically difficult to decode. Learn how the Atlas will elucidate the biological pathways behind some of the world’s most devastating diseases: #JPM2026

1 billion cells. One atlas. Today, Illumina introduces the Billion Cell Atlas, creating the most comprehensive map of human disease biology — and unlocking unparalleled speed and scale in AI for drug discovery. The Atlas will help researchers, including founding participants AstraZeneca, Merck, and Eli Lilly and Company study the effect of switching on and off all 20,000 genes in cells linked to diseases that have been historically difficult to decode. Learn how the Atlas will elucidate the biological pathways behind some of the world’s most devastating diseases: #JPM2026

Illumina

34,161 次观看 • 6 个月前

The Sora 2 feed is fascinating, seeing how everyone is using it for the first time. This generation stood out a mile from all the cameos and pokemon, by jesperagain: > 1960s black-and-white BBC report on Sora 2 video generation model launch. Grainy video to match the time

The Sora 2 feed is fascinating, seeing how everyone is using it for the first time. This generation stood out a mile from all the cameos and pokemon, by jesperagain: > 1960s black-and-white BBC report on Sora 2 video generation model launch. Grainy video to match the time

fofr

283,743 次观看 • 9 个月前

Membit 🐰 Epoch 1 starts now! You can now download the world’s first scroll-to-earn extension. Join as a Data Hunter, help shape the future of real-time AI, and earn rewards. 👉 Become a Data Hunter: 🧵 TL;DR 👇

Membit 🐰 Epoch 1 starts now! You can now download the world’s first scroll-to-earn extension. Join as a Data Hunter, help shape the future of real-time AI, and earn rewards. 👉 Become a Data Hunter: 🧵 TL;DR 👇

Band

129,755 次观看 • 11 个月前

1/ Ever wondered how high-end animation comes to life? Here’s a quick breakdown of the process from our most recent piece for OpenSea — from the concepting phase all the way to fluid final render 🧵✨

1/ Ever wondered how high-end animation comes to life? Here’s a quick breakdown of the process from our most recent piece for OpenSea — from the concepting phase all the way to fluid final render 🧵✨

Good Vibes Club 🤙

95,638 次观看 • 1 年前