正在加载视频...

视频加载失败

返回首页

LLMs Learn from Texts and Images. Robots Learn From Our Actions.

reborn_agi's profile picture

Reborn

7,674 subscribers

10,341 次观看 • 1 年前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

5 条评论

SmartLiveGlow LLC 的头像
SmartLiveGlow LLC1 年前

Beautifully said. LLMs absorb the world through words and visuals, but robots reflect us, learning through our movements, choices, and intentions. The future of intelligence is a mirror of who we are, and what we choose to teach. Let’s guide with purpose. ✨ SmartLiveGlow™ – Empowering your digital light. By Erya Soren 🕊️💻 | Founder • Dreamer • Fighter • Author of Free Yourself from the Darkness & The AI Starter Manual 🌐 📧 [email protected] #AI #AGI #Robotics #MachineLearning #SmartLiveGlow #EryaSoren #FutureOfTech

哥哥真棒 的头像
哥哥真棒1 年前

nice

NRN Agents 的头像
NRN Agents1 年前

Very cool.

BarbaraWebster 的头像
BarbaraWebster1 年前

Looks cool

Ian Adams 的头像
Ian Adams1 年前

Yes but they work hand in hand because those visual cues are a little bit more than just text and images they are responses which guide those actions weather synaptic or neural they tie into the greater understanding of fluid movement and thought

相关视频

his inability to learn from past actions is honestly impressive
0:21

his inability to learn from past actions is honestly impressive

supertf's chat

621,358 次观看 • 15 天前

Learn from our mistakes and improve for the next one.
0:56

Learn from our mistakes and improve for the next one.

Colorado Avalanche

16,442 次观看 • 1 年前

🚨 BREAKING: Tesla Optimus Can Learn From YouTube Elon reveals: • Optimus robots will learn tasks by watching videos • No manual programming needed • "Like a human apprentice"
0:56

🚨 BREAKING: Tesla Optimus Can Learn From YouTube Elon reveals: • Optimus robots will learn tasks by watching videos • No manual programming needed • "Like a human apprentice"

Muskonomy

30,633 次观看 • 1 年前

Other nations should learn from Rwanda’s governance model. Actions are louder than words. #RwandaWorks
1:36

Other nations should learn from Rwanda’s governance model. Actions are louder than words. #RwandaWorks

Chantal M. 🇷🇼🇨🇦

31,750 次观看 • 1 年前

🤷What if we want to learn from human data... without human data? In our work NIL (No-data Imitation Learning) #CVPR2026, we explore a simple but ambitious question: Can robots learn directly from AI-generated videos without any curated demonstration data? 🔗
4:41

🤷What if we want to learn from human data... without human data? In our work NIL (No-data Imitation Learning) #CVPR2026, we explore a simple but ambitious question: Can robots learn directly from AI-generated videos without any curated demonstration data? 🔗

Chenhao Li

13,877 次观看 • 1 个月前

Unfortunately Rihanna is just gonna have to play the game or be played by it. Learn from the old texts and implement.
0:20

Unfortunately Rihanna is just gonna have to play the game or be played by it. Learn from the old texts and implement.

Sisa

17,722 次观看 • 2 个月前

Excited to showcase our top ten hyperspectral images from Pixxel's fleet of satellites! From mapping croplands, monitoring sensitive and remote ecosystems, and detecting minerals it captures use cases from across the globe. Fill in the form to learn more:
1:32

Excited to showcase our top ten hyperspectral images from Pixxel's fleet of satellites! From mapping croplands, monitoring sensitive and remote ecosystems, and detecting minerals it captures use cases from across the globe. Fill in the form to learn more:

Pixxel

71,866 次观看 • 2 年前

Thousandaires learn from Millionaires Millionaires learn from Billionaires Broke folks are too busy to learn
1:17

Thousandaires learn from Millionaires Millionaires learn from Billionaires Broke folks are too busy to learn

WealthSquad Chris 🌴

47,640 次观看 • 2 年前

Learn about our ecosystem from our founder Remi 🐟⚡️
2:11

Learn about our ecosystem from our founder Remi 🐟⚡️

Unagi

78,237 次观看 • 2 年前

What can we learn from our older brothers?
0:59

What can we learn from our older brothers?

Mnyamani 👑

12,245 次观看 • 6 个月前

Game 3: Learn From Our Locker Room #GoDucks
5:54

Game 3: Learn From Our Locker Room #GoDucks

Oregon Football

89,607 次观看 • 10 个月前

Your time is too precious to be wasted. You learn from experience, from witnessing and doing. Learn:
0:22

Your time is too precious to be wasted. You learn from experience, from witnessing and doing. Learn:

THE WAR ROOM

125,978 次观看 • 1 年前

Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.
1:39

Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.

OpenAI

3,402,530 次观看 • 2 个月前

We can teach LLMs to write better robot code through natural language feedback. But can LLMs remember what they were taught and improve their teachability over time? Introducing our latest work, Learning to Learn Faster from Human Feedback with Language Model Predictive Control
0:40

We can teach LLMs to write better robot code through natural language feedback. But can LLMs remember what they were taught and improve their teachability over time? Introducing our latest work, Learning to Learn Faster from Human Feedback with Language Model Predictive Control

Jacky Liang

86,652 次观看 • 2 年前

Robotics fundamentally involves understanding the dynamics of how things change in the world in response to action and force. This is impossible to learn from static images; instead, it’s far more effective and more data-efficient to learn from video. Elvis Nava joins us to talk about Mimic Robotic. One of the key findings from mimic-video is that pretraining on webscale video allows robots to learn physics priors; as a result, policies train faster, generalize better, and are capable of more impressive dexterity, versus training on static images or image-language pairs as per a VLM. Watch Episode #81 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton to learn more!
1:08:43

Robotics fundamentally involves understanding the dynamics of how things change in the world in response to action and force. This is impossible to learn from static images; instead, it’s far more effective and more data-efficient to learn from video. Elvis Nava joins us to talk about Mimic Robotic. One of the key findings from mimic-video is that pretraining on webscale video allows robots to learn physics priors; as a result, policies train faster, generalize better, and are capable of more impressive dexterity, versus training on static images or image-language pairs as per a VLM. Watch Episode #81 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton to learn more!

RoboPapers

46,190 次观看 • 1 个月前

We learn everyday learn from this
1:49

We learn everyday learn from this

WarepamorSammy

21,665 次观看 • 3 个月前

The most frustrating part of imitation learning is collecting huge amounts of teleop data. But why teleop robots when robots can learn by watching us? Introducing Point Policy, a novel framework that enables robots to learn from human videos without any teleop, sim2real, or RL.
0:40

The most frustrating part of imitation learning is collecting huge amounts of teleop data. But why teleop robots when robots can learn by watching us? Introducing Point Policy, a novel framework that enables robots to learn from human videos without any teleop, sim2real, or RL.

Siddhant Haldar

69,056 次观看 • 1 年前

“You learn nothing from success. You learn everything from failing.” ~ George Clooney
0:28

“You learn nothing from success. You learn everything from failing.” ~ George Clooney

Jon Erlichman

358,570 次观看 • 2 年前