Загрузка видео...

Не удалось загрузить видео

На главную

How does test-time scaling impact robots? We find that larger models, more thinking, and more context help significantly for some prompts but not others. Like LLMs, we can also train a router to for a better performance/latency tradeoff! Paper:

chelseabfinn's profile picture

Chelsea Finn

100,492 subscribers

24,603 просмотров • 2 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🧵1/n LLMs significantly improve Evolutionary Algorithms for molecular discovery! For 18 different molecular optimization tasks, we demonstrate how to achieve SOTA performance by incorporating different LLMs! Learn more in our new paper! Website: Code)
0:27

🧵1/n LLMs significantly improve Evolutionary Algorithms for molecular discovery! For 18 different molecular optimization tasks, we demonstrate how to achieve SOTA performance by incorporating different LLMs! Learn more in our new paper! Website: Code)

Yuanqi Du

17,899 просмотров • 2 лет назад

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵
1:06

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵

kyutai

53,142 просмотров • 4 месяцев назад

As we face cruelty, corruption, and chaos, may we fight. Fight hard. And fight even harder. But let us not lose ourselves. In fact, let’s find ways to show up more fully and more significantly for others.
0:33

As we face cruelty, corruption, and chaos, may we fight. Fight hard. And fight even harder. But let us not lose ourselves. In fact, let’s find ways to show up more fully and more significantly for others.

Cory Booker

48,783 просмотров • 1 год назад

For 3D pose some use different keypoints, others SMPL and other models. It's a mess! With Neural Localizer Fields, we can choose the output at test time! allowing to train using any. Results are real time and SOTA across the board. István Sárándi
0:25

For 3D pose some use different keypoints, others SMPL and other models. It's a mess! With Neural Localizer Fields, we can choose the output at test time! allowing to train using any. Results are real time and SOTA across the board. István Sárándi

Gerard Pons-Moll

43,531 просмотров • 2 лет назад

It's time the British Museum addresses slavery. We want to see a room at the British Museum for slavery, so it can tell a better story of how we got here and who we are. Find out more:
1:29

It's time the British Museum addresses slavery. We want to see a room at the British Museum for slavery, so it can tell a better story of how we got here and who we are. Find out more:

Good Law Project

70,812 просмотров • 1 год назад

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:
1:03

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 просмотров • 1 год назад

Listen to this victim who was hit by a cyclist ……. Please don’t tell me us cyclists can not cause harm …. We certainly can ……we are seeing more and more cyclists injuring themselves and others creating a HOSTILE ENVIRONMENT for personal gain. We must do better…….
0:57

Listen to this victim who was hit by a cyclist ……. Please don’t tell me us cyclists can not cause harm …. We certainly can ……we are seeing more and more cyclists injuring themselves and others creating a HOSTILE ENVIRONMENT for personal gain. We must do better…….

Ediz

14,153 просмотров • 2 месяцев назад

"I hope stray kids' dream doesn't fade. because inevitably, dreams can't help but fade. it's not as easy as before, there's more things to think about and we've put in some years. every time we did something we went at it like athletes, didn't we? when others would get a better response than us, all of us would get angry and drink together out of frustration. we had a time like that but honestly, doing that now is a bit... a lot of time has passed so it feels like we've adjusted to not having the same vibe as before" oh hyunjin...
0:33

"I hope stray kids' dream doesn't fade. because inevitably, dreams can't help but fade. it's not as easy as before, there's more things to think about and we've put in some years. every time we did something we went at it like athletes, didn't we? when others would get a better response than us, all of us would get angry and drink together out of frustration. we had a time like that but honestly, doing that now is a bit... a lot of time has passed so it feels like we've adjusted to not having the same vibe as before" oh hyunjin...

ellie ✦

65,119 просмотров • 29 дней назад

This conversation is bigger than Adeife.Because if we’re being completely honest with ourselves, are we actually aiming for more? Not just more money. Not just a better lifestyle. But more in terms of what we believe we can become, what we can build, and the kind of impact we can create. Sometimes the problem isn’t that we lack potential. Sometimes we simply stop at the first version of ourselves that works. And sometimes, yes, the environment, exposure, access and circumstances around us can limit what we see as possible. But at some point, we also have to ask ourselves: am I genuinely reaching for more, or have I become comfortable with what I already know? This conversation is about ambition, exposure, survival, opportunity, and what we allow ourselves to believe is possible. And honestly, this is one of the reasons we built YATSA an ecosystem created to give you access to better conversations, people, opportunities, knowledge and resources that can help you grow beyond your current reality. If you’re ready to put yourself in spaces that challenge you, expand your thinking and help you build more, click the link in my bio to register and become part of the YATSA community.
5:09

This conversation is bigger than Adeife.Because if we’re being completely honest with ourselves, are we actually aiming for more? Not just more money. Not just a better lifestyle. But more in terms of what we believe we can become, what we can build, and the kind of impact we can create. Sometimes the problem isn’t that we lack potential. Sometimes we simply stop at the first version of ourselves that works. And sometimes, yes, the environment, exposure, access and circumstances around us can limit what we see as possible. But at some point, we also have to ask ourselves: am I genuinely reaching for more, or have I become comfortable with what I already know? This conversation is about ambition, exposure, survival, opportunity, and what we allow ourselves to believe is possible. And honestly, this is one of the reasons we built YATSA an ecosystem created to give you access to better conversations, people, opportunities, knowledge and resources that can help you grow beyond your current reality. If you’re ready to put yourself in spaces that challenge you, expand your thinking and help you build more, click the link in my bio to register and become part of the YATSA community.

Stella Abiodun

44,712 просмотров • 5 дней назад

when we first started Feastables, we had a lot to learn. we went all in to fix the problems and bring you a better product that not only tastes amazing, but also does good for the world!
1:27

when we first started Feastables, we had a lot to learn. we went all in to fix the problems and bring you a better product that not only tastes amazing, but also does good for the world!

Feastables

28,878 просмотров • 1 год назад

Are you struggling to look after a big Council or housing association home? We can help! We are offering £2,500 to help people move into a smaller, more manageable home – which means we can free up larger homes for families that need them. [1/2]
1:26

Are you struggling to look after a big Council or housing association home? We can help! We are offering £2,500 to help people move into a smaller, more manageable home – which means we can free up larger homes for families that need them. [1/2]

Manchester City Council

23,418 просмотров • 18 дней назад

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!
54:52

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

RoboPapers

27,567 просмотров • 6 месяцев назад

Tonight I’m at a dinner with Mark Crossley and he has just done this quick video with me, he really is a gentleman, we all agree that homelessness should not be a thing in 2025, but the more awareness we have on the subject the more we can help. Please help me to help others by donating in any way you can ❤️❤️❤️
0:25

Tonight I’m at a dinner with Mark Crossley and he has just done this quick video with me, he really is a gentleman, we all agree that homelessness should not be a thing in 2025, but the more awareness we have on the subject the more we can help. Please help me to help others by donating in any way you can ❤️❤️❤️

Streetwise Stu

21,985 просмотров • 11 месяцев назад

What Happens If We Lose? Actually, not much. It will just be a continued decline. Slowly but surely Sweden descends into Brazil. • A bit more immigration. • A bit more bureaucracy. • A bit more taxes. • A bit more crime. A bit more of everything bad for each year. Actually, we are already living in the defeat. Not a day goes by without some horrific crime being committed against Whites. The perpetrator gets a slap on the wrist and is out on the street soon thereafter. That said, it is not over. We can still win. What does winning mean? Winning does not mean that everything is resolved over night. It means that society is steered in a better direction, so things can get a bit better for every year. Remigration. • A smaller but stronger state. • Lower taxes (due to not giving away money to the Third • World and unproductive members of society). • Less crime (thanks to remigration and harder punishments). To win, we need good individuals in positions of power (in political parties and in the legal system, for example). Onwards!
10:24

What Happens If We Lose? Actually, not much. It will just be a continued decline. Slowly but surely Sweden descends into Brazil. • A bit more immigration. • A bit more bureaucracy. • A bit more taxes. • A bit more crime. A bit more of everything bad for each year. Actually, we are already living in the defeat. Not a day goes by without some horrific crime being committed against Whites. The perpetrator gets a slap on the wrist and is out on the street soon thereafter. That said, it is not over. We can still win. What does winning mean? Winning does not mean that everything is resolved over night. It means that society is steered in a better direction, so things can get a bit better for every year. Remigration. • A smaller but stronger state. • Lower taxes (due to not giving away money to the Third • World and unproductive members of society). • Less crime (thanks to remigration and harder punishments). To win, we need good individuals in positions of power (in political parties and in the legal system, for example). Onwards!

The Golden One

51,676 просмотров • 10 дней назад

Should we design a new programming language for LLMs, that LLMs can use more efficiently? Chris Lattner, the creator of Swift and Mojo doesn't think so, and here's why: (cont'd)
1:26

Should we design a new programming language for LLMs, that LLMs can use more efficiently? Chris Lattner, the creator of Swift and Mojo doesn't think so, and here's why: (cont'd)

Gergely Orosz

15,416 просмотров • 9 месяцев назад

"This is a first for us this side to be in a train in Switzerland, a moving train, not just a stationary one, and having the opportunity to have breakfast on a train, but also to have interactions with people in government." - President Cyril Ramaphosa "So we really welcome this, and we look forward to a wonderful exchange. Some of you, if not most of you, have already invested in South Africa, and we are here to appeal for you to invest even more, so don't think that this is a free train ride." - President Cyril Ramaphosa
1:15

"This is a first for us this side to be in a train in Switzerland, a moving train, not just a stationary one, and having the opportunity to have breakfast on a train, but also to have interactions with people in government." - President Cyril Ramaphosa "So we really welcome this, and we look forward to a wonderful exchange. Some of you, if not most of you, have already invested in South Africa, and we are here to appeal for you to invest even more, so don't think that this is a free train ride." - President Cyril Ramaphosa

News Live SA

234,617 просмотров • 9 месяцев назад

WH saying that he has the ambition for INFINITE to go to a higher place to be loved by more people but practically it’s time for them to go down (in popularity)😭Like SG he’ also sensitive about showing us better perfs. Please can we give them a win this comeback?
0:41

WH saying that he has the ambition for INFINITE to go to a higher place to be loved by more people but practically it’s time for them to go down (in popularity)😭Like SG he’ also sensitive about showing us better perfs. Please can we give them a win this comeback?

INFINITE 💛 INSPIRIT

39,373 просмотров • 1 год назад