Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Language is the future for how we interact with robots. Today Wayve is sharing a first look at LINGO-1, a new vision-language-action AI model. To give you a glimpse of its capabilities, here is a video of me playing with LINGO-1 yesterday morning.

Alex Kendall

17,425 subscribers

154,741 Aufrufe • vor 2 Jahren •via X (Twitter)

Bildung Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Alex Kendall

Alex Kendallvor 2 Jahren

Learn more about LINGO-1 in our blog here:

Profilbild von Eoghan Flanagan

Eoghan Flanaganvor 2 Jahren

@wayve_ai I'm more impressed it has language support for Kiwi

Profilbild von Alex Kendall

Alex Kendallvor 2 Jahren

@wayve_ai 🤣🤣🤣 that's the hardest generalisation challenge

Profilbild von Robin Dechant

Robin Dechantvor 2 Jahren

@wayve_ai cc @tomazstolfa

Profilbild von Sahil Chandra

Sahil Chandravor 2 Jahren

@wayve_ai Had asked about this very feature to @elonmusk and @aelluswamy Congrats on implementing it

Profilbild von Seif

Seifvor 2 Jahren

@wayve_ai Really cool! Are you planning to open source the model?

Profilbild von Neil Katz

Neil Katzvor 2 Jahren

@EMostaque @wayve_ai Indeed but what language will they speak to each other

Profilbild von Ragnar

Ragnarvor 2 Jahren

@wayve_ai You'd like #cybermage a quick hitting sci-fi thriller Novella. About 3 hour read for most avid readers. Definitely relative to your work.

Profilbild von Catchmaker

Catchmakervor 2 Jahren

@wayve_ai Talk to your self-driving car. Want to help? 18 #JobOpenings in hardware, research, and beyond. "Our team is the first in the world to use autonomous vehicles on public roads using end-to-end deep learning."

Profilbild von diligentium

diligentiumvor 2 Jahren

@WholeMarsBlog @wayve_ai Looks helpful. AmazIng what it can see. Assuming it will support voice recognition some time too? Would be cool to be able to talk to it.

Ähnliche Videos

Autonomous driving with Chain of Thought - autopilot thinking out loud in text! LINGO-1 is the most interesting work I've read in autodriving for a while. Before: perception -> driving action After: perception -> textual reasoning -> action LINGO-1 trains a video-language model that comments on the ongoing scene. You can ask it to explain its decisions ("why are you stopped?") and planning ("what are you gonna do next?"). The explicit reasoning step comes with key benefits: - Explainability: driving models are no longer a mysterious blackbox that you pray for safety. - Counterfactuals: it's able to imagine scenarios that are not in the training data, and reason through how to handle them correctly. - Long-tail programming: there are soooo many edge cases in driving. It's impossible to have good data coverage on everything. Instead of collecting 1000s of examples to "neural program" a case, you can now have a human teacher write prompts to explain a handful of examples. LINGO-1 is closely related to a few works in game AI: - MineDojo (my team's work at NVIDIA, learns a reward model that aligns Minecraft gameplay videos with their transcripts. The model, called "MineCLIP", is able to ground commentary text in the video pixels. - Thought Cloning (Jeff Clune): pixel -> language -> action loop in gridworlds.

Autonomous driving with Chain of Thought - autopilot thinking out loud in text! LINGO-1 is the most interesting work I've read in autodriving for a while. Before: perception -> driving action After: perception -> textual reasoning -> action LINGO-1 trains a video-language model that comments on the ongoing scene. You can ask it to explain its decisions ("why are you stopped?") and planning ("what are you gonna do next?"). The explicit reasoning step comes with key benefits: - Explainability: driving models are no longer a mysterious blackbox that you pray for safety. - Counterfactuals: it's able to imagine scenarios that are not in the training data, and reason through how to handle them correctly. - Long-tail programming: there are soooo many edge cases in driving. It's impossible to have good data coverage on everything. Instead of collecting 1000s of examples to "neural program" a case, you can now have a human teacher write prompts to explain a handful of examples. LINGO-1 is closely related to a few works in game AI: - MineDojo (my team's work at NVIDIA, learns a reward model that aligns Minecraft gameplay videos with their transcripts. The model, called "MineCLIP", is able to ground commentary text in the video pixels. - Thought Cloning (Jeff Clune): pixel -> language -> action loop in gridworlds.

Jim Fan

552,760 Aufrufe • vor 2 Jahren

Lingo made quite the impact at Token 2049! 🚀 This time last year, we were just a vision, a concept with a mission to make Crypto accessible to everyone. This year we're at over 20 employees, with a following of over 20k community members! And do you know the best part? We're growing week on week. Lingo is here to change the game and we're here to revolutionize Web3 and target 1 billion crypto curious individuals. We can't wait to meet you in person, but until then - enjoy our sizzle reel 🎞️ #lingo #web3

Lingo made quite the impact at Token 2049! 🚀 This time last year, we were just a vision, a concept with a mission to make Crypto accessible to everyone. This year we're at over 20 employees, with a following of over 20k community members! And do you know the best part? We're growing week on week. Lingo is here to change the game and we're here to revolutionize Web3 and target 1 billion crypto curious individuals. We can't wait to meet you in person, but until then - enjoy our sizzle reel 🎞️ #lingo #web3

Lingo

23,056 Aufrufe • vor 2 Jahren

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Sergey Levine

30,388 Aufrufe • vor 2 Jahren

California startup announces breakthrough in general-purpose robotics with π0.5 AI — a vision-language-action model. Everything the robot sees, it sees for the first time. The robot has not been trained to recognize its surroundings. We are getting there! Only a few more years until we finally have household robots. A dream is coming true!

California startup announces breakthrough in general-purpose robotics with π0.5 AI — a vision-language-action model. Everything the robot sees, it sees for the first time. The robot has not been trained to recognize its surroundings. We are getting there! Only a few more years until we finally have household robots. A dream is coming true!

Chubby♨️

218,411 Aufrufe • vor 1 Jahr

AI Language learning just leveled up. TalkMe AI’s FIRST brand film isn’t just marketing—it’s a vision of the future. It’s award-winning, cinematic, and shows exactly how AI is rewriting the rules of learning. You’ll never look at language learning the same way again. 👇

Future Stacked

106,415 Aufrufe • vor 11 Monaten

Today, we announced 𝗥𝗧-𝟮: a first of its kind vision-language-action model to control robots. 🤖 It learns from both web and robotics data and translates this knowledge into generalised instructions. Find out more:

Today, we announced 𝗥𝗧-𝟮: a first of its kind vision-language-action model to control robots. 🤖 It learns from both web and robotics data and translates this knowledge into generalised instructions. Find out more:

Google DeepMind

537,808 Aufrufe • vor 3 Jahren

🚀 Excited to announce the first release of a novel open source programming language and platform for language model interaction! Combining prompts, constraints & scripting, LMQL elevates the capabilities of large language models. 🧵1/6 A quick tour.

🚀 Excited to announce the first release of a novel open source programming language and platform for language model interaction! Combining prompts, constraints & scripting, LMQL elevates the capabilities of large language models. 🧵1/6 A quick tour.

LMQL (Language Model Query Language)

198,966 Aufrufe • vor 3 Jahren

Okay guy’s recently i have partnered with a top notch company call Lingo It would be 2 year of partnership with them to support every way and bring more exposure. When there is any project came with long term vision we do expect them to deliver their mission to communities. Check them out they are building something extraordinary. Here is detailed introduction video which will help you to understand more about #LINGO $LINGO

Okay guy’s recently i have partnered with a top notch company call Lingo It would be 2 year of partnership with them to support every way and bring more exposure. When there is any project came with long term vision we do expect them to deliver their mission to communities. Check them out they are building something extraordinary. Here is detailed introduction video which will help you to understand more about #LINGO $LINGO

DMT🐐

47,240 Aufrufe • vor 2 Jahren

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

The Humanoid Hub

20,458 Aufrufe • vor 1 Jahr

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

Google DeepMind

819,379 Aufrufe • vor 1 Jahr

Launching the biggest SocialFi campaign…EVER The stats are in for the Lingo Lingo Islands Campaign 📈🚀 Let's take a closer look at phase 1 of the project 👇▶️ Shout out to the great team at $lingo 🤝 What's next? 👀⏰

Launching the biggest SocialFi campaign…EVER The stats are in for the Lingo Lingo Islands Campaign 📈🚀 Let's take a closer look at phase 1 of the project 👇▶️ Shout out to the great team at $lingo 🤝 What's next? 👀⏰

Avark

120,051 Aufrufe • vor 2 Jahren

Want to learn a new language with the help of AI? → Little Language Lessons is built with Gemini 2.0 Flash via the Gemini API. It leverages Gemini’s multilingual capabilities to make practicing foreign languages more contextual and personalized.

Want to learn a new language with the help of AI? → Little Language Lessons is built with Gemini 2.0 Flash via the Gemini API. It leverages Gemini’s multilingual capabilities to make practicing foreign languages more contextual and personalized.

Google for Developers

17,637 Aufrufe • vor 1 Jahr

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

Ted Xiao

152,445 Aufrufe • vor 1 Jahr

Today we introduce T-Free, a new paradigm in language processing. Tokenization is one of the core building blocks of large language models (LLMs), transforming natural language into numeric representations for further processing. (1/3) 🔗 #writtenbyalephalpha

Today we introduce T-Free, a new paradigm in language processing. Tokenization is one of the core building blocks of large language models (LLMs), transforming natural language into numeric representations for further processing. (1/3) 🔗 #writtenbyalephalpha

Aleph Alpha

18,121 Aufrufe • vor 1 Jahr

Kannada is a language with a rich history of 2500 years and a promising future. It is more than a language for Kannadigas and has nothing to do with Tamil. Actor Kamal Hasaan need to know that.

Kannada is a language with a rich history of 2500 years and a promising future. It is more than a language for Kannadigas and has nothing to do with Tamil. Actor Kamal Hasaan need to know that.

Harish Itagi

82,948 Aufrufe • vor 1 Jahr

AI is going to completely change the way we interact with our phones. Here's a first look at how we're using it to build a home screen without apps.

AI is going to completely change the way we interact with our phones. Here's a first look at how we're using it to build a home screen without apps.

Sam Hall

120,794 Aufrufe • vor 1 Jahr

UK-based startup 'Humanoid' announced KinetIQ, an AI framework with a Vision-Language-Action (VLA) model at its core. It uses a four-layer architecture: fleet orchestration, task decomposition, VLA, and RL for whole-body control. It works on both bipedal and wheeled robots.

UK-based startup 'Humanoid' announced KinetIQ, an AI framework with a Vision-Language-Action (VLA) model at its core. It uses a four-layer architecture: fleet orchestration, task decomposition, VLA, and RL for whole-body control. It works on both bipedal and wheeled robots.

The Humanoid Hub

21,954 Aufrufe • vor 5 Monaten