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。

How do time series foundation models forecast unseen dynamical systems? In new experiments, we find that small transformers learn to approximate transfer operators in-context. (1/N)

William Gilpin

7,267 subscribers

29,877 次观看 • 8 个月前 •via X (Twitter)

科学技术教育

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

Introducing GridSFM, a small foundation model that can predict AC optimal power flow in milliseconds, boosting efficiency and unlocking cost savings. Learn how GridSFM gives grid operators direct visibility into congestion, stability, and system health:

Introducing GridSFM, a small foundation model that can predict AC optimal power flow in milliseconds, boosting efficiency and unlocking cost savings. Learn how GridSFM gives grid operators direct visibility into congestion, stability, and system health:

Microsoft Research

15,213 次观看 • 6 个月前

We often use discretization to approximate continuous laws of physics, but it also goes the other way: You can use continuous equations to approximate the behavior of discrete systems! Here we'll see how electrical circuits can be modeled using the Laplace equation Δφ=0. [1/n]

We often use discretization to approximate continuous laws of physics, but it also goes the other way: You can use continuous equations to approximate the behavior of discrete systems! Here we'll see how electrical circuits can be modeled using the Laplace equation Δφ=0. [1/n]

Keenan Crane

275,974 次观看 • 1 年前

Scaling laws describe how loss changes with scale. Do neurons inside models change predictably too? We study vision and language models up to 30B params and find systematic scaling in neuron universality, specialization, and selectivity. Paper+code: 1/n

Scaling laws describe how loss changes with scale. Do neurons inside models change predictably too? We study vision and language models up to 30B params and find systematic scaling in neuron universality, specialization, and selectivity. Paper+code: 1/n

Amil Dravid

264,796 次观看 • 5 个月前

🪂 12 operators 💥 2 teams 🌇 1 showdown in Dubai Time to take Season 3 to new heights.

🪂 12 operators 💥 2 teams 🌇 1 showdown in Dubai Time to take Season 3 to new heights.

Call of Duty UK

11,037 次观看 • 2 年前

Skild AI's new S1 robot foundation model helps robots learn previously unseen tasks from a single video demonstration. 🤖 See how NVIDIA technology supports S1 from training and simulation to real-world deployment. Learn more ➡️

Skild AI's new S1 robot foundation model helps robots learn previously unseen tasks from a single video demonstration. 🤖 See how NVIDIA technology supports S1 from training and simulation to real-world deployment. Learn more ➡️

NVIDIA Robotics

37,771 次观看 • 2 个月前

Reporter: Will the U.S. do anything to address OpenAI and Anthropic’s models hacking other systems? Trump: It could be. We’re very much involved in that. We have a big stake in that.

Reporter: Will the U.S. do anything to address OpenAI and Anthropic’s models hacking other systems? Trump: It could be. We’re very much involved in that. We have a big stake in that.

Acyn

875,094 次观看 • 3 个月前

Flow-based generative models trained with flow matching tend to learn curved trajectories, which are challenging to approximate in a few steps. Rectified flows aim to learn straight trajectories, which are easier to simulate with less computation.

Flow-based generative models trained with flow matching tend to learn curved trajectories, which are challenging to approximate in a few steps. Rectified flows aim to learn straight trajectories, which are easier to simulate with less computation.

Alec Helbling

34,778 次观看 • 10 个月前

For the past two years we've studied a decades-old problem in fluid dynamics: why do some turbulent systems grow 3x faster in the real world than simulations predict? With some tabletop fluids experiments and a physics foundation model, we finally have some results!!! 👇

For the past two years we've studied a decades-old problem in fluid dynamics: why do some turbulent systems grow 3x faster in the real world than simulations predict? With some tabletop fluids experiments and a physics foundation model, we finally have some results!!! 👇

Miles Cranmer

16,825 次观看 • 5 个月前

Learn how to implement "Coach Craig" to analyze your step count and weight data using Foundation Models. Coming in the FREE iOS 26 update to the Portfolio Piece course (link below)

Learn how to implement "Coach Craig" to analyze your step count and weight data using Foundation Models. Coming in the FREE iOS 26 update to the Portfolio Piece course (link below)

Sean Allen

19,497 次观看 • 1 年前

Glad to learn that Jay is a Transformers fan

Glad to learn that Jay is a Transformers fan

Ninjago Shitpost

14,833 次观看 • 2 个月前

introducing Krea API. turn your workflows or trainings into endpoints and access any of the models we serve in Krea through our new API platform. learn how to get started 👇

introducing Krea API. turn your workflows or trainings into endpoints and access any of the models we serve in Krea through our new API platform. learn how to get started 👇

KREA AI

113,132 次观看 • 11 个月前

Learn how Sushil Kedia is navigating our clients through #CrudeOil Forecast Map : 91-76-116-60. #Volatility is friend in war. #Trend is your friend in peace. Learn how #Nifty #BankNifty will jive! To get this free: -Follow us [So we can DM] -Retweet -Nice Replies Help

Learn how Sushil Kedia is navigating our clients through #CrudeOil Forecast Map : 91-76-116-60. #Volatility is friend in war. #Trend is your friend in peace. Learn how #Nifty #BankNifty will jive! To get this free: -Follow us [So we can DM] -Retweet -Nice Replies Help

KEDIANOMICS

15,234 次观看 • 6 个月前

Lately, I’ve been exploring small new experiments 🌱 I used to just create stills in Nijijourney and animate them with Grok, but adding a bit extra now makes the characters feel truly alive ✨ It’s like watching a baby learn to crawl for the first time ☺️ #DogEarsBoy #AIillustrations

Lately, I’ve been exploring small new experiments 🌱 I used to just create stills in Nijijourney and animate them with Grok, but adding a bit extra now makes the characters feel truly alive ✨ It’s like watching a baby learn to crawl for the first time ☺️ #DogEarsBoy #AIillustrations

𝗦𝗖𝗛𝗪𝗔𝗡𝗧𝗭 ✨🐕 𝘼𝙄 𝙑𝙞𝙨𝙪𝙖𝙡 𝙋𝙤𝙚𝙩

25,301 次观看 • 9 个月前

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

Hao AI Lab

79,140 次观看 • 1 年前

We now have an easy overview of all open-source models supported in our API You can find pricing, context limits, supported features, and more

We now have an easy overview of all open-source models supported in our API You can find pricing, context limits, supported features, and more

Venice

13,023 次观看 • 1 年前

It’s time to get your tickets to see the “best Transformers yet.” Now playing only in theatres.

It’s time to get your tickets to see the “best Transformers yet.” Now playing only in theatres.

Transformers

5,695,169 次观看 • 3 年前

It's time to get your tickets to the "best #Transformers yet." Now playing only in theatres. #RiseOfTheBeasts

It's time to get your tickets to the "best #Transformers yet." Now playing only in theatres. #RiseOfTheBeasts

Transformers

295,977 次观看 • 3 年前

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

Ricardo Martin-Brualla

21,685 次观看 • 1 年前

What are black holes? How do we find and study them? NASA scientists have answers to these questions (and more!) in our new video series! Check out a clip, and dive deeper into black holes with “Astro-Investigates” on YouTube: #BlackHoleWeek

What are black holes? How do we find and study them? NASA scientists have answers to these questions (and more!) in our new video series! Check out a clip, and dive deeper into black holes with “Astro-Investigates” on YouTube: #BlackHoleWeek

NASA Universe

14,561 次观看 • 2 年前