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。

Introducing S1, our new foundation model that learns from one example. It can be taught 10-minute long tasks that it has never seen before, from one video prompt without any fine-tuning. Watch S1 operate in real-time via in-context learning:

Skild AI

20,314 subscribers

3,304,034 次观看 • 2 天前 •via X (Twitter)

科学技术教育新闻政治

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

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,466 次观看 • 2 年前

S1 learns new tasks like a language model. You prompt it with a video demonstration, and it outputs robot actions to complete the task in any environment and in any embodiment.

S1 learns new tasks like a language model. You prompt it with a video demonstration, and it outputs robot actions to complete the task in any environment and in any embodiment.

Skild AI

306,476 次观看 • 2 天前

It can be taught extremely long-horizon tasks, over 10 minutes long. By composing skills learned in pretraining or creating new ones, it can make coffee, pot a plant, fry pancakes, and more – tasks never seen during pretraining.

It can be taught extremely long-horizon tasks, over 10 minutes long. By composing skills learned in pretraining or creating new ones, it can make coffee, pot a plant, fry pancakes, and more – tasks never seen during pretraining.

Skild AI

326,433 次观看 • 2 天前

Introducing PorTAL: Portable Task Adapters for LLMs. A novel recipe to cheaply port fine-tuning between models. It matches per task LoRA accuracy at half the cost, lowering the switching overhead of adapting tasks across LLMs. At Ramp, every new model release used to mean retraining our fine-tunes from scratch. PorTAL learns the task once, then efficiently refits it onto any new base model, even across model families.

Introducing PorTAL: Portable Task Adapters for LLMs. A novel recipe to cheaply port fine-tuning between models. It matches per task LoRA accuracy at half the cost, lowering the switching overhead of adapting tasks across LLMs. At Ramp, every new model release used to mean retraining our fine-tunes from scratch. PorTAL learns the task once, then efficiently refits it onto any new base model, even across model families.

Ramp Labs

171,807 次观看 • 1 个月前

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.

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 次观看 • 3 年前

The first time S1 flipped a pancake, we assumed pancake flipping must have been in its pre-training data. We searched our whole pre-training data and found no examples of flipping. S1 inferred the out-of-distribution task from one video prompt.

The first time S1 flipped a pancake, we assumed pancake flipping must have been in its pre-training data. We searched our whole pre-training data and found no examples of flipping. S1 inferred the out-of-distribution task from one video prompt.

Skild AI

311,501 次观看 • 2 天前

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.

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.

Tony Zhao

170,008 次观看 • 1 个月前

Wonder by Adobe. Real-time interactive 3D world navigation. - minute-long rollouts from one image - I2V, V2V - constant latency - Wan2.1 You can re-shoot any video from new angles.

Wonder by Adobe. Real-time interactive 3D world navigation. - minute-long rollouts from one image - I2V, V2V - constant latency - Wan2.1 You can re-shoot any video from new angles.

Wildminder

16,292 次观看 • 29 天前

🚨NEW: xAI engineers say that by the end of the year you will be able to generate 10-20 minute long videos in one shot without any intervention. The videos will be rendered in real time -- meaning you can interact with you own responsive worlds as you go.

🚨NEW: xAI engineers say that by the end of the year you will be able to generate 10-20 minute long videos in one shot without any intervention. The videos will be rendered in real time -- meaning you can interact with you own responsive worlds as you go.

Autism Capital 🧩

262,833 次观看 • 6 个月前

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that directly generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

126,030 次观看 • 1 年前

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:

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 次观看 • 1 年前

Trump: “During my time in office, a huge Iron Dome will be built over our country, a dome that has never been seen before. Israel has it, why shouldn’t we have it?”

Trump: “During my time in office, a huge Iron Dome will be built over our country, a dome that has never been seen before. Israel has it, why shouldn’t we have it?”

Clash Report

198,596 次观看 • 2 年前

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,330 次观看 • 3 年前

Odds shift fast. Most bettors don’t catch it in time. ⚡️That changes now⚡️ Introducing our powerful new tool that gives you real-time odds & props from every sportsbook in one dashboard. No more missing values. No more slow info. 3-Day Free Trial is live ⬇️⬇️⬇️

Odds shift fast. Most bettors don’t catch it in time. ⚡️That changes now⚡️ Introducing our powerful new tool that gives you real-time odds & props from every sportsbook in one dashboard. No more missing values. No more slow info. 3-Day Free Trial is live ⬇️⬇️⬇️

SharpDuel

115,162 次观看 • 1 年前

This is dots3-note preview from dots studio in a puzzle game it hasn't seen before. No game-specific prompt. It has to work out the controls, objective and new mechanics from the screen. It starts pressing buttons. Open-weight: 280B total / 16B active, 512K context.

This is dots3-note preview from dots studio in a puzzle game it hasn't seen before. No game-specific prompt. It has to work out the controls, objective and new mechanics from the screen. It starts pressing buttons. Open-weight: 280B total / 16B active, 512K context.

Khushboo Verma

37,624 次观看 • 3 天前

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

Wenli Xiao

185,486 次观看 • 10 个月前