Загрузка видео...

Не удалось загрузить видео

На главную

We found a general recipe for Solves: scale pretraining, then hill-climb with minimal in-house data. For the first time, one fine-tuning example can teach a new behavior that generalizes. Below: 4 folding strategies, learned from one example each and tested on held-out setups.

tonyzzhao's profile picture

Tony Zhao

113,483 subscribers

168,036 просмотров • 19 дней назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.
2:25

Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.

Tony Zhao

1,015,021 просмотров • 19 дней назад

A little example! I learned this dance, and I can do it on one side, then flip and do on the other side immediately after for the next chorus :)
1:24

A little example! I learned this dance, and I can do it on one side, then flip and do on the other side immediately after for the next chorus :)

⚔ twitchy lesbian boy ⚔

11,176 просмотров • 1 год назад

New short course on Pretraining LLMs! Developed with Upstage and taught by their CEO Sung Kim and CSO Lucy Park. While prompting or fine-tuning existing models works well for many general language tasks, pretraining is valuable for specialized domains or languages with limited representation in current models. This course walks you through the LLM pretraining pipeline: 1. Data preparation: Learn to source, clean, and prepare training data using HuggingFace. 2. Model architecture: Configure transformer networks, including modifying existing models. 3. Training: Set up and run training using open-source libraries. 4. Evaluation: Benchmark performance using popular evaluation strategies. As an example use case, you'll also compare the output of a base model with its fine-tuned and further pretrained variants, to see the impact of pretraining on a model's ability to write Python. The course also explores an innovative technique called depth up-scaling, which Upstage used to train their Solar model family, reducing pretraining compute costs by up to 70%. This technique works by first duplicating layers of a smaller pretrained model to form a larger model, and then further pretraining the result. Sign up here!
3:54

New short course on Pretraining LLMs! Developed with Upstage and taught by their CEO Sung Kim and CSO Lucy Park. While prompting or fine-tuning existing models works well for many general language tasks, pretraining is valuable for specialized domains or languages with limited representation in current models. This course walks you through the LLM pretraining pipeline: 1. Data preparation: Learn to source, clean, and prepare training data using HuggingFace. 2. Model architecture: Configure transformer networks, including modifying existing models. 3. Training: Set up and run training using open-source libraries. 4. Evaluation: Benchmark performance using popular evaluation strategies. As an example use case, you'll also compare the output of a base model with its fine-tuned and further pretrained variants, to see the impact of pretraining on a model's ability to write Python. The course also explores an innovative technique called depth up-scaling, which Upstage used to train their Solar model family, reducing pretraining compute costs by up to 70%. This technique works by first duplicating layers of a smaller pretrained model to form a larger model, and then further pretraining the result. Sign up here!

Andrew Ng

85,678 просмотров • 2 лет назад

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at any time to any view at any other time? Introducing 4D-LRM: a Large Space-Time Reconstruction Model that ... 🔹 Predicts 4D Gaussian primitives directly from multi-view tokens (no motion vectors, no HexPlane); 🔹 Uses a clean, minimal Transformer backbone; 🔹 Generalizes with fast, high-quality feedforward rendering at any view and infinite frame rate. Check out more interactive demos and scaling behaviors on our homepage/paper. 👉Website: 👉Paper:
2:30

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at any time to any view at any other time? Introducing 4D-LRM: a Large Space-Time Reconstruction Model that ... 🔹 Predicts 4D Gaussian primitives directly from multi-view tokens (no motion vectors, no HexPlane); 🔹 Uses a clean, minimal Transformer backbone; 🔹 Generalizes with fast, high-quality feedforward rendering at any view and infinite frame rate. Check out more interactive demos and scaling behaviors on our homepage/paper. 👉Website: 👉Paper:

Martin Ziqiao Ma

21,811 просмотров • 1 год назад

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move
3:58

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

OpenLedger

61,662 просмотров • 1 год назад

Ever feel like God can’t forgive your failures? He can and He does. I’m thankful for that! Peter’s life is a beautiful example. It’s just one of the stories in my new book #NothingIsImpossibleWithGod - out one week from today and available for pre-order now!
0:31

Ever feel like God can’t forgive your failures? He can and He does. I’m thankful for that! Peter’s life is a beautiful example. It’s just one of the stories in my new book #NothingIsImpossibleWithGod - out one week from today and available for pre-order now!

Shannon Bream

16,023 просмотров • 5 месяцев назад

A British surgeon tells the BBC what he saw in Gaza. "I can remember one child for example who was 7, Amir... He heard a drone above him, turned round, and then it fired on him. And we had many many reports like that from children and adults."
1:11

A British surgeon tells the BBC what he saw in Gaza. "I can remember one child for example who was 7, Amir... He heard a drone above him, turned round, and then it fired on him. And we had many many reports like that from children and adults."

Paul Graham

376,311 просмотров • 25 дней назад

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.
4:50

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 просмотров • 3 лет назад

For most of history, expertise was scarce, constrained by time and reach: one person, one career, one lifetime. Now, for the first time, we can encode, evaluate, and scale it. We believe the wisdom that once took a lifetime to build shouldn’t take a lifetime to find. Today, we’re excited to announce that AfterQuery has raised a $30M Series A at a $300M valuation and that we’ve since surpassed $100M in annual revenue run rate, to build the data layer of professional AI.
1:21

For most of history, expertise was scarce, constrained by time and reach: one person, one career, one lifetime. Now, for the first time, we can encode, evaluate, and scale it. We believe the wisdom that once took a lifetime to build shouldn’t take a lifetime to find. Today, we’re excited to announce that AfterQuery has raised a $30M Series A at a $300M valuation and that we’ve since surpassed $100M in annual revenue run rate, to build the data layer of professional AI.

Spencer Mateega

273,749 просмотров • 3 месяцев назад

Jay Abernathy's game-breaking speed is standing out this summer in the Cape League. One great example of what his speed can do came in a game on Sunday: Abernathy singled with one out, stole second, stole third, and then came home on a routine ground out to the right side.
0:24

Jay Abernathy's game-breaking speed is standing out this summer in the Cape League. One great example of what his speed can do came in a game on Sunday: Abernathy singled with one out, stole second, stole third, and then came home on a routine ground out to the right side.

D1Baseball

18,835 просмотров • 22 дней назад

Watch King reveals that a random first-time customer bought a $1,700,000 one-of-one AP watch “Random client came in for the first time, nobody, not a referral, at least as far as we know. Never interacted with him, and they asked us for a one-of-one AP, a truly unique piece, and it’s $1.7 million for the watch” “Essentially, I had my team on it, and within three days we found where in the world the watch was. We flew somebody there, we inspected it, we brought it back, we had international armed security, which is a whole thing, and we delivered the watch to the guy at his house, in under a week”
0:33

Watch King reveals that a random first-time customer bought a $1,700,000 one-of-one AP watch “Random client came in for the first time, nobody, not a referral, at least as far as we know. Never interacted with him, and they asked us for a one-of-one AP, a truly unique piece, and it’s $1.7 million for the watch” “Essentially, I had my team on it, and within three days we found where in the world the watch was. We flew somebody there, we inspected it, we brought it back, we had international armed security, which is a whole thing, and we delivered the watch to the guy at his house, in under a week”

Mikli

220,865 просмотров • 2 месяцев назад

The one thing we can always agree on is pizza. For a limited time, get two large one-topping pizzas from Little Caesars Pizza for just $4.99 each with code: PIZZAPIZZA online only.
1:28

The one thing we can always agree on is pizza. For a limited time, get two large one-topping pizzas from Little Caesars Pizza for just $4.99 each with code: PIZZAPIZZA online only.

Trent McDuffie

36,770 просмотров • 11 месяцев назад

📢📢📢 Excited to release ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR25). 🤏🤙✌️With ManipTrans, we can transfer dexterous manipulation skills into robotic hands in simulation and deploy them on a real robot, using a residual policy learned for dex manipulation. 🤖🤖🤖The video below illustrates how the MoCap data can be transferred to Inspire, Shadow, Xhand, Allegro, and Mano. With ManipTrans, we can scale up dex manip data greatly with minimal effort. For more details, please check our -webpage: -code: -huggingface:
1:59

📢📢📢 Excited to release ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR25). 🤏🤙✌️With ManipTrans, we can transfer dexterous manipulation skills into robotic hands in simulation and deploy them on a real robot, using a residual policy learned for dex manipulation. 🤖🤖🤖The video below illustrates how the MoCap data can be transferred to Inspire, Shadow, Xhand, Allegro, and Mano. With ManipTrans, we can scale up dex manip data greatly with minimal effort. For more details, please check our -webpage: -code: -huggingface:

Siyuan Huang

20,918 просмотров • 1 год назад

1/ Presenting #Shoshin, a Minimal Viable Reality with Asynchronous Onchain Strategies, this Saturday, July 22nd in Paris for the first time. . Apply to join the playtest. Click the link below to apply. Acceptance will be sent out on a rolling basis. . Please enable video sound.
1:12

1/ Presenting #Shoshin, a Minimal Viable Reality with Asynchronous Onchain Strategies, this Saturday, July 22nd in Paris for the first time. . Apply to join the playtest. Click the link below to apply. Acceptance will be sent out on a rolling basis. . Please enable video sound.

Topology

46,721 просмотров • 3 лет назад

#TowerofFantasy [The Little Rascal and the Foodie] New Simulacrum Debut #Carrot Ver.4.8 #InterstellarVisitor will be available from 4/8! Follow Tower of Fantasy and Repost for a chance to win Amazon Gift Card and exclusive in-game rewards! Don't miss out! One egg, one carrot! One spoonful of flour, one carrot! Half a carton of milk, one carrot!... Ta-da! Behold—my secret recipe: Super Yummy Carrot Cake! 🎂🥕 One slice for you, one slice for me! One for the Authorizer, one for me! One for Sister Hilda, one for me! And Black Dog… fine, you can have one too—but behave, alright? 😆🐾 HD Version >> #ToF
3:35

#TowerofFantasy [The Little Rascal and the Foodie] New Simulacrum Debut #Carrot Ver.4.8 #InterstellarVisitor will be available from 4/8! Follow Tower of Fantasy and Repost for a chance to win Amazon Gift Card and exclusive in-game rewards! Don't miss out! One egg, one carrot! One spoonful of flour, one carrot! Half a carton of milk, one carrot!... Ta-da! Behold—my secret recipe: Super Yummy Carrot Cake! 🎂🥕 One slice for you, one slice for me! One for the Authorizer, one for me! One for Sister Hilda, one for me! And Black Dog… fine, you can have one too—but behave, alright? 😆🐾 HD Version >> #ToF

Tower of Fantasy

67,515 просмотров • 1 год назад

We’ve added a new, faster way to fine-tune belt tension on your Prusa CORE One. ✨ The new stroboscope-based Manual Belt Tuning helps you find the optimal setting for both belts quickly and precisely - resulting in smoother motion and cleaner prints. Available from firmware 6.4.0. 🦾 Try it out now in Settings → Manual Belt Tuning.
0:43

We’ve added a new, faster way to fine-tune belt tension on your Prusa CORE One. ✨ The new stroboscope-based Manual Belt Tuning helps you find the optimal setting for both belts quickly and precisely - resulting in smoother motion and cleaner prints. Available from firmware 6.4.0. 🦾 Try it out now in Settings → Manual Belt Tuning.

Prusa3D

29,796 просмотров • 9 месяцев назад

Anime.js 4.2.1 is out with a bunch of small fixes and new features: 🐍 Motion Path: Add an offset parameter 👇 Draggable: Add a drag threshold parameter for mouse and touch ✏️ Documentation: You can now export and edit the 450 example demos on CodePen.IO in one click!
0:21

Anime.js 4.2.1 is out with a bunch of small fixes and new features: 🐍 Motion Path: Add an offset parameter 👇 Draggable: Add a drag threshold parameter for mouse and touch ✏️ Documentation: You can now export and edit the 450 example demos on CodePen.IO in one click!

Julian Garnier

42,886 просмотров • 10 месяцев назад

Every blockchain today moves data the same way: one copy at a time, over the public internet... But that’s not how high-performance systems scale. They use multicast: one transmission, many recipients. And DoubleZero brings multicast to blockchains for the first time. See the power of hardware acceleration for packet replication in practice with Jito Shredstream and Anza Turbine below ↓
1:01

Every blockchain today moves data the same way: one copy at a time, over the public internet... But that’s not how high-performance systems scale. They use multicast: one transmission, many recipients. And DoubleZero brings multicast to blockchains for the first time. See the power of hardware acceleration for packet replication in practice with Jito Shredstream and Anza Turbine below ↓

DoubleZero

33,098 просмотров • 7 месяцев назад

One cool thing that I tested today is Particle Network Universal X app. I have USDC on 3 different networks ($SOL, $OP, $ARB) and some ETH on $MODE network. Tested to buy a small amount of CHILLGUY (the meme) using the dust I had in these 4 accounts. So in 1-click I made a swap that aggregated the assets I had spread across these 4 chains and swapped them for a single token on Solana. Chain abstraction solves at least a problem I have been annoyed with for a long time. Made a video below. And yes, I am an investor in Particle Network :)
0:57

One cool thing that I tested today is Particle Network Universal X app. I have USDC on 3 different networks ($SOL, $OP, $ARB) and some ETH on $MODE network. Tested to buy a small amount of CHILLGUY (the meme) using the dust I had in these 4 accounts. So in 1-click I made a swap that aggregated the assets I had spread across these 4 chains and swapped them for a single token on Solana. Chain abstraction solves at least a problem I have been annoyed with for a long time. Made a video below. And yes, I am an investor in Particle Network :)

Route 2 FI

40,473 просмотров • 1 год назад