Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

At we’re building a foundational protein machine learning model that aims to understand everything about macromolecules. We can successfully create a zinc binding site without ever specifying the positions or geometries to the model.

Kathy Y. Wei, Ph.D.

3,714 subscribers

32,260 views • 3 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 Comments

Esaú De la Vega Camarillo3 years ago

@fenguita @miangoar topa

Faith Bakir3 years ago

@MolAnCell Their innovative model's capability to generate a zinc binding site without precise instructions showcases the potential of AI in unlocking hidden insights in macromolecules.

Molecular Animator of the Cell 🧬📺🦠3 years ago

@fenguita 🫢😯😦😧😮😲

Ahmed3 years ago

Wow! Realy awesome! Could you please explain how this animation created? Thank you

Reinaldo F Cristo3 years ago

Perceiving simulations facilitates beliefs and mirroring them through technology. Congratulations! @mellziland

Faith Bakir3 years ago

@MolAnCell Major props to @310_AI for their cutting-edge work in protein science! Their foundational machine learning model is unlocking new realms of knowledge about macromolecules.

Related Videos

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:

DeepLearning.AI

45,348 views • 1 year ago

Microsoft published an image-to-GIF model called Pix2Gif! They claim that the model is better at understand motion, while we’re not talking Sora levels here, it’s certainly a step up compared to the slow-motion outputs we’re currently used to.

Microsoft published an image-to-GIF model called Pix2Gif! They claim that the model is better at understand motion, while we’re not talking Sora levels here, it’s certainly a step up compared to the slow-motion outputs we’re currently used to.

Dreaming Tulpa 🥓👑

14,090 views • 2 years ago

"We are trying to build a new branch of machine learning. An alternative to Deep Learning itself...building something that we call Symbolic Descent." François Chollet joins the Y Combinator Lightcone podcast to share about our research at Ndea and the launch of ARC-AGI-3.

"We are trying to build a new branch of machine learning. An alternative to Deep Learning itself...building something that we call Symbolic Descent." François Chollet joins the Y Combinator Lightcone podcast to share about our research at Ndea and the launch of ARC-AGI-3.

Ndea

65,231 views • 7 months ago

AVERI standards director Patricia Paskov reveals how they benchmarked Gemini without Google DeepMind ever seeing the benchmark or the benchmark owner ever seeing the model: "This is building on a pilot that was done at UK AISI with Anthropic two years ago, with a toy model and a toy benchmark. OpenMined provided the secure enclave in which both went. Neither side saw the other's." "What we did is we built on this, but using a Gemini model. We used a frontier model, and we also used a real benchmark from MLCommons. There are the proper firewalls in place such that these are both going into the secure enclave that OpenMined makes." "It's privacy preserving, and it gives the guarantees of privacy and security to both sides such that you can run the evaluation and spit out the results." "I'm really excited about leveraging stronger engineering tools as solutions to constraints like privacy and security that can unlock opportunities in auditing." AVERI

AVERI standards director Patricia Paskov reveals how they benchmarked Gemini without Google DeepMind ever seeing the benchmark or the benchmark owner ever seeing the model: "This is building on a pilot that was done at UK AISI with Anthropic two years ago, with a toy model and a toy benchmark. OpenMined provided the secure enclave in which both went. Neither side saw the other's." "What we did is we built on this, but using a Gemini model. We used a frontier model, and we also used a real benchmark from MLCommons. There are the proper firewalls in place such that these are both going into the secure enclave that OpenMined makes." "It's privacy preserving, and it gives the guarantees of privacy and security to both sides such that you can run the evaluation and spit out the results." "I'm really excited about leveraging stronger engineering tools as solutions to constraints like privacy and security that can unlock opportunities in auditing." AVERI

MTS

14,540 views • 1 month ago

We’re introducing intrinsic discovery, a new learning method that allows models to explore and learn from open-ended environments without human supervision. Using intrinsic discovery, we trained a world model that surpasses GPT-5.6 Sol at simulating terminal environments.

We’re introducing intrinsic discovery, a new learning method that allows models to explore and learn from open-ended environments without human supervision. Using intrinsic discovery, we trained a world model that surpasses GPT-5.6 Sol at simulating terminal environments.

Induction Labs

69,572 views • 2 months ago

When I worked at a hedge fund, we would spend 100+ hours building complex valuation models. I always felt that was overrated and would build a simple crayon math model on the side. Excited to share TIKR's new Valuation Model Builder. Create a model in less than 60 seconds!

When I worked at a hedge fund, we would spend 100+ hours building complex valuation models. I always felt that was overrated and would build a simple crayon math model on the side. Excited to share TIKR's new Valuation Model Builder. Create a model in less than 60 seconds!

Sahil Khetpal

190,422 views • 1 year ago

Something I really don't like about the current Shadow model is how the eyeliner looks. If we ever get a new Shadow model, I hope they do the eyeliner like the Rio model or the 06 model.

Something I really don't like about the current Shadow model is how the eyeliner looks. If we ever get a new Shadow model, I hope they do the eyeliner like the Rio model or the 06 model.

Omegan

11,062 views • 10 months ago

It's amazing what you can do without machine learning. I've spent hours watching my simple implementation of the Dynamic Window Algorithm, basically a model-predictive control method. Runs live in the browser at this link:

It's amazing what you can do without machine learning. I've spent hours watching my simple implementation of the Dynamic Window Algorithm, basically a model-predictive control method. Runs live in the browser at this link:

Andrew Davison

123,347 views • 4 months ago

Mapping Machine Learning to Physics aims to provide warfighters at the tactical edge “energy-aware” machine learning capability that balances performance with energy use. Seeking abstracts for ideas by Oct. 6.

Mapping Machine Learning to Physics aims to provide warfighters at the tactical edge “energy-aware” machine learning capability that balances performance with energy use. Seeking abstracts for ideas by Oct. 6.

DARPA

12,407 views • 1 year ago

It is a miracle that we can understand and create a model of the universe in our minds, and I can't think of a better way to spend my time here. #wonder #science #thepoetryofreality The full episode is here:

It is a miracle that we can understand and create a model of the universe in our minds, and I can't think of a better way to spend my time here. #wonder #science #thepoetryofreality The full episode is here:

Richard Dawkins

124,660 views • 2 years ago

What would a foundational model of the Earth look like? Here's my conversation with Bruno Santos, who started the Clay foundation -which just released their v1 of a "Foundational model of Earth" to go into what that means Watch:

What would a foundational model of the Earth look like? Here's my conversation with Bruno Santos, who started the Clay foundation -which just released their v1 of a "Foundational model of Earth" to go into what that means Watch:

Max Lenormand

11,783 views • 2 years ago

NEWS: Nvidia has just introduced "Cosmos," a world foundation model created to understand the physical world. The model can generate synthetic data to train robotics.

NEWS: Nvidia has just introduced "Cosmos," a world foundation model created to understand the physical world. The model can generate synthetic data to train robotics.

Sawyer Merritt

254,398 views • 1 year ago

Great sitting down with @BrianTylerCohen to talk about everything from the courage we saw in Minnesota, to how Democrats can be true to our values and get stuff done, to how we’re building a community of changemakers at the The Obama Foundation.

Great sitting down with @BrianTylerCohen to talk about everything from the courage we saw in Minnesota, to how Democrats can be true to our values and get stuff done, to how we’re building a community of changemakers at the The Obama Foundation.

Barack Obama

40,498,483 views • 9 months ago

Super excited about HydraFusion in GitHub Copilot, and what it shows about the shift from model selection to model orchestration. By bringing together multiple models to plan, build, critique, and complete coding tasks, it can deliver outcomes at up to 67% lower cost. It’s a great example of the value of a heterogeneous model ecosystem, and how we’re continuing to advance the cost-to-outcome frontier.

Super excited about HydraFusion in GitHub Copilot, and what it shows about the shift from model selection to model orchestration. By bringing together multiple models to plan, build, critique, and complete coding tasks, it can deliver outcomes at up to 67% lower cost. It’s a great example of the value of a heterogeneous model ecosystem, and how we’re continuing to advance the cost-to-outcome frontier.

Satya Nadella

329,926 views • 2 months ago

We’re excited to share that Nuance Labs has raised a $50M Series A led by Lightspeed, joined by Accel, South Park Commons, NVIDIA, and Define Ventures! Much of human communication happens beyond words. Before we can speak, we learn to read faces, return smiles, follow gestures, and sense when someone is listening. That visual and emotional vocabulary stays with us for life. At Nuance Labs, we’re building a foundation model that understands and responds to the full spectrum of human emotion. A single full-duplex audio-visual model that sees, listens, and responds in real time, with the natural give-and-take of a conversation with a friend or colleague. We believe the best interface with a machine is the one we’ve practiced since birth. Join us!

We’re excited to share that Nuance Labs has raised a $50M Series A led by Lightspeed, joined by Accel, South Park Commons, NVIDIA, and Define Ventures! Much of human communication happens beyond words. Before we can speak, we learn to read faces, return smiles, follow gestures, and sense when someone is listening. That visual and emotional vocabulary stays with us for life. At Nuance Labs, we’re building a foundation model that understands and responds to the full spectrum of human emotion. A single full-duplex audio-visual model that sees, listens, and responds in real time, with the natural give-and-take of a conversation with a friend or colleague. We believe the best interface with a machine is the one we’ve practiced since birth. Join us!

Fangchang Ma

2,012,095 views • 2 months ago

Today we’re excited to share a peek at our next-gen model. Hope you like it 🥹 Imagine a video model you can play like a game, all in real-time. That’s what we’re building. We call it interactive video, and there's no game engine in sight, just a model’s imagination.

Today we’re excited to share a peek at our next-gen model. Hope you like it 🥹 Imagine a video model you can play like a game, all in real-time. That’s what we’re building. We call it interactive video, and there's no game engine in sight, just a model’s imagination.

Odyssey

207,705 views • 1 year ago

Boris Cherny (Boris Cherny) on the Lightcone Podcast about how he approached building Claude Code: "At Anthropic, we don't build for the model of today, we build for the model of six months from now. And that's still my advice to founders that are building on LLMs."

Boris Cherny (Boris Cherny) on the Lightcone Podcast about how he approached building Claude Code: "At Anthropic, we don't build for the model of today, we build for the model of six months from now. And that's still my advice to founders that are building on LLMs."

Y Combinator

81,264 views • 8 months ago