Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

True computer use is fully general. FDM-1 uses arrow keys on a computer to steer a car in San Francisco with less than 1 hour of fine-tuning data. The action policy is critical: tuning FDM-1 to drive gets much higher accuracy than tuning just the video encoder on the...

si_pbc's profile picture

Standard Intelligence

10,446 subscribers

72,532 görüntüleme • 8 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

14 Yorum

Standard Intelligence profil fotoğrafı
Standard Intelligence8 ay önce

FDM-1 completes complex tasks and navigates interfaces well enough to use CAD applications. Forking VMs allow us to snapshot when a successful operation completes (extrusion, selection, etc.), letting us apply test-time compute to computer use.

Standard Intelligence profil fotoğrafı
Standard Intelligence8 ay önce

Inspired by VPT (Baker et al), we train an inverse dynamics model (IDM) to predict frame-by-frame computer actions. The IDM leverages 40k hours of contractor data to label 11 million hours of screen recordings—550,000x larger than the largest open-source computer use dataset.

Standard Intelligence profil fotoğrafı
Standard Intelligence8 ay önce

We’ve made two main advances: the ability to train on our 11M+ hour computer action dataset and understand long-context video. Our video encoder can fit nearly two hours of 30FPS, high-resolution video into a 1M token context window, ~50x more efficient than existing SOTA.

Standard Intelligence profil fotoğrafı
Standard Intelligence8 ay önce

Computer use models shouldn't learn from screenshots. We built a new foundation model that learns from video like humans do. FDM-1 can construct a gear in Blender, find software bugs, and even drive a real car through San Francisco using arrow keys.

Standard Intelligence profil fotoğrafı
Standard Intelligence8 ay önce

Here’s the blog post, where you can learn more about how we trained this model:

agniv profil fotoğrafı
agniv8 ay önce

HOLY DUCK

_____ profil fotoğrafı
_____8 ay önce

amazing work! any idea why the baseline for the self driving task starts out worse than random guessing though?

Yuze profil fotoğrafı
Yuze8 ay önce

fascinating work on the context compression part! Wondering if the model would be able to know what is a good quality action at system 2 level. eg. when to raise/fall on playing card games 😀

Yuval Grossman profil fotoğrafı
Yuval Grossman7 ay önce

Can you explain what do you mean here by “tuning the video encoder”?

Samu profil fotoğrafı
Samu8 ay önce

nice

madhavan profil fotoğrafı
madhavan8 ay önce

holy fire

Gary Basin profil fotoğrafı
Gary Basin8 ay önce

> less than 1 hour of fine-tuning data

FallenOne profil fotoğrafı
FallenOne8 ay önce

that's so cool

Haris Poljo profil fotoğrafı
Haris Poljo8 ay önce

@comma_ai

Benzer Videolar

The countdown is on—less than 90 days until championship week at Oakmont! From fine-tuning agronomic practices to dialing in playing conditions, the team is laser-focused on delivering a world-class test of golf.
6:31

The countdown is on—less than 90 days until championship week at Oakmont! From fine-tuning agronomic practices to dialing in playing conditions, the team is laser-focused on delivering a world-class test of golf.

Tyler Bloom

44,486 görüntüleme • 1 yıl önce

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.
1:45:58

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.

h100envy

41,245 görüntüleme • 3 ay önce

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!
2:36

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

503,011 görüntüleme • 3 yıl önce

Moved more of Cyn's systems to her camera computer, visor is now ~60fps Now I begin fine tuning it to behave closer to the show
0:22

Moved more of Cyn's systems to her camera computer, visor is now ~60fps Now I begin fine tuning it to behave closer to the show

DT @LVL UP EXPO 2026

14,675 görüntüleme • 7 ay önce

We found that to match the accuracy that S1 can achieve with just one example of prompting, current VLA models would need to be post-trained with 50-100 hours of data collection followed by fine-tuning!
0:21

We found that to match the accuracy that S1 can achieve with just one example of prompting, current VLA models would need to be post-trained with 50-100 hours of data collection followed by fine-tuning!

Skild AI

295,652 görüntüleme • 2 ay önce

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

61,697 görüntüleme • 1 yıl önce

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.
3:09

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

QVAC

108,928 görüntüleme • 7 ay önce

Who else is tuning in with Rory before he gets back to action? 🍿
0:21

Who else is tuning in with Rory before he gets back to action? 🍿

Sky Sports

69,205 görüntüleme • 6 ay önce

In 1983, singer Barry White urged people to learn how to code. At the time, less than 1% of the population owned a computer.
0:52

In 1983, singer Barry White urged people to learn how to code. At the time, less than 1% of the population owned a computer.

Jon Erlichman

344,967 görüntüleme • 2 yıl önce

Fine-tuning Mistral 7B with LoRA on a 32 GB M1 (laptop!) in MLX Updated example uses less RAM + support for custom datasets 🚀
0:38

Fine-tuning Mistral 7B with LoRA on a 32 GB M1 (laptop!) in MLX Updated example uses less RAM + support for custom datasets 🚀

Awni Hannun

148,211 görüntüleme • 2 yıl önce

intensity, precision, conditioning and passion.. fine tuning the fine tuning 🤼‍♀️
1:27

intensity, precision, conditioning and passion.. fine tuning the fine tuning 🤼‍♀️

Nattie

55,627 görüntüleme • 2 yıl önce

Today we're thrilled to announce the first end-to-end platform for Reinforcement Fine-Tuning. With just a dozen labeled data points, you can outperform #OpenAI o1 and #DeepSeekR1 on complex tasks. Built on the #GRPO methodology that DeepSeek-R1 popularized, our platform delivers exceptional results. In our real-world PyTorch to Triton transpilation case study, we achieved 3x higher accuracy than OpenAI o1 and DeepSeek-R1 when writing GPU code. Check out the thread below to learn how you can adapt an #opensource #LLM to your use cases with unmatched efficiency. #rft
2:55

Today we're thrilled to announce the first end-to-end platform for Reinforcement Fine-Tuning. With just a dozen labeled data points, you can outperform #OpenAI o1 and #DeepSeekR1 on complex tasks. Built on the #GRPO methodology that DeepSeek-R1 popularized, our platform delivers exceptional results. In our real-world PyTorch to Triton transpilation case study, we achieved 3x higher accuracy than OpenAI o1 and DeepSeek-R1 when writing GPU code. Check out the thread below to learn how you can adapt an #opensource #LLM to your use cases with unmatched efficiency. #rft

Predibase by Rubrik

1,022,546 görüntüleme • 1 yıl önce

I got to ask Brett Adcock a couple of questions on Royden's livestream yesterday: - Data scarcity and compute constraint outlook - Pre-training vs. fine-tuning balance Brett believes generalization is the key, and Figure will be the first to solve it.
6:17

I got to ask Brett Adcock a couple of questions on Royden's livestream yesterday: - Data scarcity and compute constraint outlook - Pre-training vs. fine-tuning balance Brett believes generalization is the key, and Figure will be the first to solve it.

The Humanoid Hub

28,915 görüntüleme • 5 ay önce

1. The fine-tuning of the universe is due to either physical necessity, chance, or design. 2. It is not due to physical necessity or chance. 3. Therefore, it is due to design!
6:22

1. The fine-tuning of the universe is due to either physical necessity, chance, or design. 2. It is not due to physical necessity or chance. 3. Therefore, it is due to design!

Reasonable Faith

131,918 görüntüleme • 1 yıl önce

Announcing RoboFuME🤖💨, a system for autonomous & efficient real-world robot learning that 1. pre-trains a VLM reward model and a multi-task RL policy from diverse off-the-shelf demo data; 2. runs RL fine-tuning online with the VLM reward model. 🔗 🧵↓
0:21

Announcing RoboFuME🤖💨, a system for autonomous & efficient real-world robot learning that 1. pre-trains a VLM reward model and a multi-task RL policy from diverse off-the-shelf demo data; 2. runs RL fine-tuning online with the VLM reward model. 🔗 🧵↓

Jingyun Yang

88,312 görüntüleme • 3 yıl önce

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]
0:25

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 görüntüleme • 2 yıl önce