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。

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.

Goodfire

24,035 subscribers

74,915 次观看 • 4 个月前 •via X (Twitter)

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

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.

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

430,406 次观看 • 3 个月前

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

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

64,403 次观看 • 1 年前

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 🔥

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

81,446 次观看 • 1 年前

Launching SYNTHETIC-2: our next-gen open reasoning dataset and planetary-scale synthetic data generation run. Powered by our P2P inference stack and DeepSeek-R1-0528, it verifies traces for the hardest RL tasks. Contribute towards AGI via open, permissionless compute.

Launching SYNTHETIC-2: our next-gen open reasoning dataset and planetary-scale synthetic data generation run. Powered by our P2P inference stack and DeepSeek-R1-0528, it verifies traces for the hardest RL tasks. Contribute towards AGI via open, permissionless compute.

Prime Intellect

359,732 次观看 • 1 年前

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

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

141,486 次观看 • 2 年前

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%

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

532,841 次观看 • 1 个月前

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!

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

99,012 次观看 • 3 个月前

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!

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 次观看 • 3 个月前

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.

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

80,824 次观看 • 8 个月前

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

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

1,210,169 次观看 • 10 个月前

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.

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

578,690 次观看 • 10 个月前

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! 🧵👇

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 次观看 • 1 年前

🔗 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.

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

84,432 次观看 • 2 个月前

"We're teaching our young players to lose... We used to teach them to win!" 🏆 #mufc

"We're teaching our young players to lose... We used to teach them to win!" 🏆 #mufc

The United Stand

123,272 次观看 • 1 年前

Israel seeks to erase our presence in Gaza by cutting off basic necessities. To resist this, we provided 4 water trucks for hundreds of Gazan families, strengthening their resilience against Israel and Trump’s plans. we require your support to increase provision of water, food to our people in Gaza.

Israel seeks to erase our presence in Gaza by cutting off basic necessities. To resist this, we provided 4 water trucks for hundreds of Gazan families, strengthening their resilience against Israel and Trump’s plans. we require your support to increase provision of water, food to our people in Gaza.

‏Martyrs of Gaza

59,984 次观看 • 1 年前

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!

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

40,597 次观看 • 3 年前

Introducing hallucination correction. We have reduced hallucination by 70%. Giga's hallucination rate is at ~1%. Better than the best frontier models. Deploy AI your customers can trust.

Introducing hallucination correction. We have reduced hallucination by 70%. Giga's hallucination rate is at ~1%. Better than the best frontier models. Deploy AI your customers can trust.

Giga

1,219,889 次观看 • 1 个月前

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)

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

1,051,007 次观看 • 8 个月前

We finally got our visas. Now it’s time to open our foundry in the USA! We are looking for investors to walk by our side in this adventure!

We finally got our visas. Now it’s time to open our foundry in the USA! We are looking for investors to walk by our side in this adventure!

Atelier Missor

654,867 次观看 • 22 天前