Loading video...

Video Failed to Load

Go Home

Language models predict the next token. Interactive video models predict the next video frame. We're in the 2022-era of these models, but video feeling sentient is imminent, along with an explosion of applications.

olivercameron's profile picture

Oliver Cameron

49,140 subscribers

16,730 views • 7 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Brisbane (Australia) is expected to be directly hit by a tropical cyclone #Alfred 🙏🧐 The storm will slow down significantly before making landfall, thus resulting in extremely heavy rainfall along the coast. ICON models predict over 500 mm of precipitation in some areas by the end of the week. Flooding is expected. The video shows the progress of the storm over the next 3 days:
0:13

Brisbane (Australia) is expected to be directly hit by a tropical cyclone #Alfred 🙏🧐 The storm will slow down significantly before making landfall, thus resulting in extremely heavy rainfall along the coast. ICON models predict over 500 mm of precipitation in some areas by the end of the week. Flooding is expected. The video shows the progress of the storm over the next 3 days:

Ventusky

258,224 views • 1 year ago

Predicting the next word "only" is sufficient for language models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.
0:14

Predicting the next word "only" is sufficient for language models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.

Nando de Freitas

130,179 views • 2 years ago

Video-as-Answer Predict and Generate Next Video Event with Joint-GRPO
0:13

Video-as-Answer Predict and Generate Next Video Event with Joint-GRPO

AK

13,696 views • 6 months ago

💡 The Age of Foundational AI! In AI, the base layer matters most. Solidus Ai Tech AI Marketplace offers a curated lineup of foundational models designed to support reasoning, coding, multilingual tasks, and enhanced privacy features. From DeepSeek-R1 to SecretAI, these models provide the infrastructure for the next generation of AI agents and applications. Explore the models here →
0:14

💡 The Age of Foundational AI! In AI, the base layer matters most. Solidus Ai Tech AI Marketplace offers a curated lineup of foundational models designed to support reasoning, coding, multilingual tasks, and enhanced privacy features. From DeepSeek-R1 to SecretAI, these models provide the infrastructure for the next generation of AI agents and applications. Explore the models here →

AITECH CLOUD NETWORK

39,060 views • 8 months ago

It’s incredible what’s possible to generate with just a prompt in a few minutes! The progress of video models is astonishing. Imagine the quality and accuracy in the next few years. Prompt ⬇️
0:10

It’s incredible what’s possible to generate with just a prompt in a few minutes! The progress of video models is astonishing. Imagine the quality and accuracy in the next few years. Prompt ⬇️

Umesh

131,367 views • 4 months ago

ECMWF models predict a massive low latitude Western Distrubance to affect india during first week of December. Almost 10 days to go so models may change however remain watchful for this remote possibility.. Video Courtesy Windy
0:10

ECMWF models predict a massive low latitude Western Distrubance to affect india during first week of December. Almost 10 days to go so models may change however remain watchful for this remote possibility.. Video Courtesy Windy

🔴All India Weather

21,581 views • 6 months ago

Most AI models just predict the next pixel to build a narrative or an image. Gemini Omni is different. Gemini Omni has an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics for more realistic movements that follow real-world logic.
0:10

Most AI models just predict the next pixel to build a narrative or an image. Gemini Omni is different. Gemini Omni has an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics for more realistic movements that follow real-world logic.

Google

65,350 views • 4 days ago

these might be the best video game character models ever made
0:16

these might be the best video game character models ever made

GermanStrands

3,949,826 views • 4 months ago

no these are not normal mapped 3D models, this is an AI generated video
0:15

no these are not normal mapped 3D models, this is an AI generated video

Is this a 3D model?

181,938 views • 26 days ago

📢Introducing Generated Reality📢 A world model for XR that turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4
0:15

📢Introducing Generated Reality📢 A world model for XR that turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4

Gordon Wetzstein

20,045 views • 3 months ago

Automating the Search for Artificial Life with Foundation Models Presents ASAL, the first use of vision-language models in Artificial Life, discovering diverse, novel simulations across substrates proj: abs:
0:16

Automating the Search for Artificial Life with Foundation Models Presents ASAL, the first use of vision-language models in Artificial Life, discovering diverse, novel simulations across substrates proj: abs:

Aran Komatsuzaki

39,177 views • 1 year ago

and the way you can NEVER predict what the next lingorm video to hit your timeline is going to be 😭😭😭😭
0:15

and the way you can NEVER predict what the next lingorm video to hit your timeline is going to be 😭😭😭😭

p 🐭🖤🦜

17,342 views • 1 month ago

Combining the explicit control of 3D software with the creativity of generative AI models is a promising yet underrated workflow. Build your 3D scenes procedurally by describing them in natural language, then take them all the way with your image & video models of choice. Tools like intangible are built around such a workflow so you don't need to duct-tape apps together. Pretty cool!
0:15

Combining the explicit control of 3D software with the creativity of generative AI models is a promising yet underrated workflow. Build your 3D scenes procedurally by describing them in natural language, then take them all the way with your image & video models of choice. Tools like intangible are built around such a workflow so you don't need to duct-tape apps together. Pretty cool!

Bilawal Sidhu

37,544 views • 10 months ago

Predicting how the environment changes over time is a key task in robotics, enabling all kinds of downstream tasks. Trace Anything is a very interesting look at how you can train models which predict the trajectory each point will take in the future -- you can use this for robot manipulation, video prediction, and more. Learn more ->
0:16

Predicting how the environment changes over time is a key task in robotics, enabling all kinds of downstream tasks. Trace Anything is a very interesting look at how you can train models which predict the trajectory each point will take in the future -- you can use this for robot manipulation, video prediction, and more. Learn more ->

Chris Paxton

56,845 views • 5 months ago

All the big language models under one roof for the very first time 🤯 Compare the output of OpenAI ChatGPT, Anthropic's Claude and Cohere's language model in a single playground!! Check out this amazing tool to get the best of large language models 👇
0:10

All the big language models under one roof for the very first time 🤯 Compare the output of OpenAI ChatGPT, Anthropic's Claude and Cohere's language model in a single playground!! Check out this amazing tool to get the best of large language models 👇

Shubham Saboo

299,255 views • 3 years ago

It feels totally different when video models actually become real-time interactive. Drag the mouse, and the cup instantly moves with it, and the water follows. You’re not just watching a video anymore, you’re playing with it.
0:18

It feels totally different when video models actually become real-time interactive. Drag the mouse, and the cup instantly moves with it, and the water follows. You’re not just watching a video anymore, you’re playing with it.

Xun Huang

23,029 views • 7 months ago

World models aren't the same as regular video models. The benchmarks are different. I'm really stoked to see what visionary creators do with this technology.
0:10

World models aren't the same as regular video models. The benchmarks are different. I'm really stoked to see what visionary creators do with this technology.

Purz.ai

47,433 views • 13 days ago

Working with multiple models in Chat? The model picker in VS Code is now organized by provider, making it easier to browse, search, and switch between models. You'll also see provider names next to your recent models for quicker recognition. 💡 Tip: Use /models for quick access.
0:14

Working with multiple models in Chat? The model picker in VS Code is now organized by provider, making it easier to browse, search, and switch between models. You'll also see provider names next to your recent models for quicker recognition. 💡 Tip: Use /models for quick access.

Visual Studio Code

32,599 views • 24 days ago

Seedance 2.0 is the AI video model everyone’s talking about — fluid motion, accurate text rendering, sharp detail. Now one of the models powering Envato’s AI video generator.
0:13

Seedance 2.0 is the AI video model everyone’s talking about — fluid motion, accurate text rendering, sharp detail. Now one of the models powering Envato’s AI video generator.

Envato

1,519,349 views • 1 month ago