Загрузка видео...

Не удалось загрузить видео

На главную

We used interpretability to scale RL against open-ended tasks, cutting Gemma 12B’s hallucination rate in half by teaching it to self-correct in tandem with our probing harness.

GoodfireAI's profile picture

Goodfire

26,367 subscribers

75,628 просмотров • 6 месяцев 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

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.
2:15

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

438,768 просмотров • 5 месяцев назад

Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. 1/n
1:24

Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. 1/n

Ananye Agarwal

64,546 просмотров • 2 лет назад

1/ Introducing Lynx - the leading hallucination detection model 🚀👀 - Beats GPT-4o on hallucination tasks - Open source, open weights, open data - Excels in real-world domains like medicine and finance We are excited to launch Lynx with Day 1 integration partners: NVIDIA, MongoDB, and Nomic 🔥
0:27

1/ Introducing Lynx - the leading hallucination detection model 🚀👀 - Beats GPT-4o on hallucination tasks - Open source, open weights, open data - Excels in real-world domains like medicine and finance We are excited to launch Lynx with Day 1 integration partners: NVIDIA, MongoDB, and Nomic 🔥

PatronusAI

81,526 просмотров • 2 лет назад

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at
0:34

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at

Yuke Zhu

141,540 просмотров • 2 лет назад

Introducing /orchestrate, a skill that recursively spawns agents to tackle your most ambitious tasks with the Cursor SDK. We’ve used it to: - Autoresearch our internal skills, cutting token use by 20% while improving evals - Cut cold start times on our internal backend by 80%
0:20

Introducing /orchestrate, a skill that recursively spawns agents to tackle your most ambitious tasks with the Cursor SDK. We’ve used it to: - Autoresearch our internal skills, cutting token use by 20% while improving evals - Cut cold start times on our internal backend by 80%

Cursor

535,145 просмотров • 3 месяцев назад

If you want a robot to do something well, you need to know how to talk to it. If you don't, you can learn, with Semantic Action RL! In our paper, Jagdeep Bhatia, Andrew Wagenmaker, Will Chen show how RL over VLA prompts enables new tasks and learns blazing fast in the real world!
1:22

If you want a robot to do something well, you need to know how to talk to it. If you don't, you can learn, with Semantic Action RL! In our paper, Jagdeep Bhatia, Andrew Wagenmaker, Will Chen show how RL over VLA prompts enables new tasks and learns blazing fast in the real world!

Sergey Levine

30,783 просмотров • 1 месяц назад

Train your 🦞OpenClaw🦞 simply by talking to it. Meet OpenClaw-RL. Host your model on our RL server, and your LLM gets optimized automatically. Use it anywhere. Keep it private. Make it more personal every day. We have fully open sourced everything. Come in and have fun!
0:53

Train your 🦞OpenClaw🦞 simply by talking to it. Meet OpenClaw-RL. Host your model on our RL server, and your LLM gets optimized automatically. Use it anywhere. Keep it private. Make it more personal every day. We have fully open sourced everything. Come in and have fun!

Yinjie Wang

99,134 просмотров • 5 месяцев назад

GPT-5.6 Sol has been used to solve open problems in mathematics. So why was it struggling with ARC-AGI-3, a benchmark of 2D puzzle games? We investigated. The harness was not letting it remember what it had learned. We found that enabling two API settings tripled our scores with 6x fewer output tokens.
1:49

GPT-5.6 Sol has been used to solve open problems in mathematics. So why was it struggling with ARC-AGI-3, a benchmark of 2D puzzle games? We investigated. The harness was not letting it remember what it had learned. We found that enabling two API settings tripled our scores with 6x fewer output tokens.

OpenAI

1,211,902 просмотров • 17 дней назад

We must not allow our bases to be used by America in this illegal war against Iran. Instead of upholding International Law this Labour Government, in allowing our bases to be used, has become complicit and equally culpable!
1:29

We must not allow our bases to be used by America in this illegal war against Iran. Instead of upholding International Law this Labour Government, in allowing our bases to be used, has become complicit and equally culpable!

Ayoub Khan MP

13,347 просмотров • 5 месяцев назад

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.
3:26

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.

Kun Lei

91,424 просмотров • 10 месяцев назад

Jack Wilshere talking about how Arsene Wenger used unopposed tasks to train attacking combinations “He used to put loads of mannequins around the edge of the box, in groups of 3 we had to play around the mannequins with one touch” Self organizing patterns but with intent
0:25

Jack Wilshere talking about how Arsene Wenger used unopposed tasks to train attacking combinations “He used to put loads of mannequins around the edge of the box, in groups of 3 we had to play around the mannequins with one touch” Self organizing patterns but with intent

JOGO FUNCIONAL

1,213,215 просмотров • 1 год назад

Super excited to share the last paper of my PhD: "Hallucination in World Models is Predictable and Preventable"✨ We train a 350M-param generative world model on a large dataset w/ 210 tasks and show that we can predict *when* hallucination happens and use that to fix it! 🧵1/n
0:40

Super excited to share the last paper of my PhD: "Hallucination in World Models is Predictable and Preventable"✨ We train a 350M-param generative world model on a large dataset w/ 210 tasks and show that we can predict *when* hallucination happens and use that to fix it! 🧵1/n

Nicklas Hansen

56,287 просмотров • 1 месяц назад

Goal-conditioned RL (GCRL) is great - unsupervised, can use data (in offline mode), flexibility to define tasks at test time. But can we run GCRL on *language data*?? In our new work we show that language GCRL enables sophisticated test-time reasoning for interactive tasks! 🧵👇
0:22

Goal-conditioned RL (GCRL) is great - unsupervised, can use data (in offline mode), flexibility to define tasks at test time. But can we run GCRL on *language data*?? In our new work we show that language GCRL enables sophisticated test-time reasoning for interactive tasks! 🧵👇

Sergey Levine

18,782 просмотров • 1 год назад

India is working on futuristic sectors to power growth and self-reliance. We are going to start a National Deepwater Exploration Mission to harness the potential in this sector. We will also be increasing our efforts in critical minerals.
4:13

India is working on futuristic sectors to power growth and self-reliance. We are going to start a National Deepwater Exploration Mission to harness the potential in this sector. We will also be increasing our efforts in critical minerals.

Narendra Modi

578,786 просмотров • 1 год назад

🔗 You can now learn how to tie the Butterfly Harness step-by-step with our new Harness Guide: This popular arms-free pattern does it all - and yes, you can self-tie it! 📚 Versatile, visually striking, and a solid base for multiple positions, whether on the floor or in suspension. Once you’ve mastered it, the possibilities really open up, from bamboo and strappado variations to front, back, or side suspension.
0:21

Sensitive content

🔗 You can now learn how to tie the Butterfly Harness step-by-step with our new Harness Guide: This popular arms-free pattern does it all - and yes, you can self-tie it! 📚 Versatile, visually striking, and a solid base for multiple positions, whether on the floor or in suspension. Once you’ve mastered it, the possibilities really open up, from bamboo and strappado variations to front, back, or side suspension.

Shibari Study

89,898 просмотров • 4 месяцев назад

I've long wondered if we can make a humanoid robot do a 𝘄𝗮𝗹𝗹𝗳𝗹𝗶𝗽 - and we just made it happen by leveraging 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁 with BeyondMimic tracking! This came after our original OmniRetarget experiments, with only minor tweaks to RL training: relaxing a termination threshold and removing one reward term. The policy achieved a 𝟱/𝟱 success rate in our real-world experiments, showing the strength of high-quality, interaction-preserving motion retargeting combined with BeyondMimic’s minimal RL tracking. Here is the updated arXiv: (In Sec. V. A)
0:20

I've long wondered if we can make a humanoid robot do a 𝘄𝗮𝗹𝗹𝗳𝗹𝗶𝗽 - and we just made it happen by leveraging 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁 with BeyondMimic tracking! This came after our original OmniRetarget experiments, with only minor tweaks to RL training: relaxing a termination threshold and removing one reward term. The policy achieved a 𝟱/𝟱 success rate in our real-world experiments, showing the strength of high-quality, interaction-preserving motion retargeting combined with BeyondMimic’s minimal RL tracking. Here is the updated arXiv: (In Sec. V. A)

Zhen Wu

1,051,448 просмотров • 10 месяцев назад

In our #ICML2023 paper (led by Ghada Sokar and with Rishabh Agarwal and utku ) we highlight the prevalence of dormant neurons in deep RL, and propose a simple method to mitigate it. Quick video summary here, and more details in thread!
1:07

In our #ICML2023 paper (led by Ghada Sokar and with Rishabh Agarwal and utku ) we highlight the prevalence of dormant neurons in deep RL, and propose a simple method to mitigate it. Quick video summary here, and more details in thread!

Pablo Samuel Castro

40,603 просмотров • 3 лет назад

At the Sunday Angelus, Pope Leo XIV recalls Jesus' teaching that we must lose our own life in order to truly find it, which allows us to open ourselves to the joy of love.
0:42

At the Sunday Angelus, Pope Leo XIV recalls Jesus' teaching that we must lose our own life in order to truly find it, which allows us to open ourselves to the joy of love.

Vatican News

28,780 просмотров • 1 месяц назад