Загрузка видео...

Не удалось загрузить видео

На главную

Introducing ✨Generative Interfaces where LLMs respond to users by proactively generating UIs that enable adaptive interaction 🎹 Piano practice tools, 🤖 neural net animations, and more🪄

Diyi_Yang's profile picture

Diyi Yang

21,889 subscribers

30,349 просмотров • 9 месяцев назад •via X (Twitter)

Здоровье и велнесНаука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing json-render × React Native Another step toward UGI (User-Generated Interfaces), powered by Generative UI. Dynamic, personalized UIs per user without sacrificing reliability. Predefined components and actions for safe, predictable output.
0:26

Introducing json-render × React Native Another step toward UGI (User-Generated Interfaces), powered by Generative UI. Dynamic, personalized UIs per user without sacrificing reliability. Predefined components and actions for safe, predictable output.

Chris Tate

207,239 просмотров • 4 месяцев назад

So I added piano🎹✨ to Kaelix and Shu's autotune🤖🎵 #ShuNanigans #KaeliXD YT link:
1:23

So I added piano🎹✨ to Kaelix and Shu's autotune🤖🎵 #ShuNanigans #KaeliXD YT link:

Kai is busy :(

103,184 просмотров • 1 год назад

Using monkey brain data to operate robotic arms! 🙉 Project Jenkins explores brain-computer interfaces by decoding neural activity into robotic movement and generating synthetic brain data from motion patterns. Using neural recordings from a macaque monkey named Jenkins, researchers developed models to decode brain signals into robotic arm movements and encode movement data into simulated neural activity. The project utilizes robotic arms and an interactive web console for real-time brain data generation from joystick inputs. The research paves the way for adaptive brain-computer interfaces by modeling brain activity more flexibly. Congrats to authors Dima Yanovsky, and Andrii Zahorodnii! 🦾
0:26

Using monkey brain data to operate robotic arms! 🙉 Project Jenkins explores brain-computer interfaces by decoding neural activity into robotic movement and generating synthetic brain data from motion patterns. Using neural recordings from a macaque monkey named Jenkins, researchers developed models to decode brain signals into robotic arm movements and encode movement data into simulated neural activity. The project utilizes robotic arms and an interactive web console for real-time brain data generation from joystick inputs. The research paves the way for adaptive brain-computer interfaces by modeling brain activity more flexibly. Congrats to authors Dima Yanovsky, and Andrii Zahorodnii! 🦾

Lukas Ziegler

21,504 просмотров • 1 год назад

Introducing Microsoft Security Copilot—detect hidden patterns and respond to threats faster with generative AI. Learn more: #MSSecure #InfoSec
1:25

Introducing Microsoft Security Copilot—detect hidden patterns and respond to threats faster with generative AI. Learn more: #MSSecure #InfoSec

Microsoft Security

2,776,509 просмотров • 3 лет назад

Websites should have personalized UIs for every single user, not the same UI for everyone (with Magnus Müller from Browser Use) - Legacy systems (like banks) are already being reimagined with better UIs that fill out the ugly backend forms automatically - First-time Photoshop users face overwhelming interfaces that could be simplified based on their experience level - AI can generate custom UIs on the fly based on user context, preferences, and needs - The future: Hundreds of different UIs for the same website instead of one UI for millions of users - "Generative UIs" could serve as an intermediary between websites and what users actually see
1:48

Websites should have personalized UIs for every single user, not the same UI for everyone (with Magnus Müller from Browser Use) - Legacy systems (like banks) are already being reimagined with better UIs that fill out the ugly backend forms automatically - First-time Photoshop users face overwhelming interfaces that could be simplified based on their experience level - AI can generate custom UIs on the fly based on user context, preferences, and needs - The future: Hundreds of different UIs for the same website instead of one UI for millions of users - "Generative UIs" could serve as an intermediary between websites and what users actually see

Shane Thomas

15,192 просмотров • 1 год назад

more sax and piano practice! i wrote the music he is good at sight reading!! 🎷 🎹
0:47

more sax and piano practice! i wrote the music he is good at sight reading!! 🎷 🎹

lily🌸

243,441 просмотров • 1 год назад

Introducing Igniter Chat by @notabotdaily - the AI chatbot for finding AI tools. 🔥🤖 Search across 1000+ AI tools shared on Ben’s Bites (by Ben Tossell), Not A Bot, and more. Visit to try it out!
0:29

Introducing Igniter Chat by @notabotdaily - the AI chatbot for finding AI tools. 🔥🤖 Search across 1000+ AI tools shared on Ben’s Bites (by Ben Tossell), Not A Bot, and more. Visit to try it out!

Haroon Choudery

24,442 просмотров • 3 лет назад

Gemini Diffusion will be one of the steps that will define how user interfaces will evolve within the next several years. This is a huge prerequisite for the next level of generative UIs. There won't be a need to build a frontend UIs soon. Insane 🤯
0:31

Gemini Diffusion will be one of the steps that will define how user interfaces will evolve within the next several years. This is a huge prerequisite for the next level of generative UIs. There won't be a need to build a frontend UIs soon. Insane 🤯

TestingCatalog News 🗞

18,924 просмотров • 1 год назад

✨ Introducing Keypoint Action Tokens. 🤖 We translate visual observations and robot actions into a "language" that off-the-shelf LLMs can ingest and output. This transforms LLMs into *in-context, low-level imitation learning machines*. 🚀 Let me explain. 👇🧵
0:25

✨ Introducing Keypoint Action Tokens. 🤖 We translate visual observations and robot actions into a "language" that off-the-shelf LLMs can ingest and output. This transforms LLMs into *in-context, low-level imitation learning machines*. 🚀 Let me explain. 👇🧵

Norman Di Palo

23,088 просмотров • 2 лет назад

Introducing Adaptive Computer. We put AI inside of an always-on personal computer that it uses to get work done. Schedule agents. Create software. Automate anything. As part of the launch, we’re giving one free month of Adaptive to users. Retweet, like, and comment ‘Adaptive’ to get it.
3:27

Introducing Adaptive Computer. We put AI inside of an always-on personal computer that it uses to get work done. Schedule agents. Create software. Automate anything. As part of the launch, we’re giving one free month of Adaptive to users. Retweet, like, and comment ‘Adaptive’ to get it.

Adaptive

1,225,295 просмотров • 3 месяцев назад

Check out this demo from Google Research of Gemini's reasoning capabilities to understand and reason about users' intent, use tools, and generate bespoke user experiences that go beyond chat interfaces ↓ #GeminiAI
3:32

Check out this demo from Google Research of Gemini's reasoning capabilities to understand and reason about users' intent, use tools, and generate bespoke user experiences that go beyond chat interfaces ↓ #GeminiAI

Google AI

476,067 просмотров • 2 лет назад

Introducing 🆕 revenue and finance automation tools. Recovery and retention automations Create custom workflows (by customer or invoice type) to recover failed payments, notify your team when invoices are overdue, and more. 🤖 Request access:
0:27

Introducing 🆕 revenue and finance automation tools. Recovery and retention automations Create custom workflows (by customer or invoice type) to recover failed payments, notify your team when invoices are overdue, and more. 🤖 Request access:

Stripe

61,803 просмотров • 3 лет назад

Calf - Adaptive UIs for Compose Multiplatform apps (
0:49

Calf - Adaptive UIs for Compose Multiplatform apps (

Android Dev Notes

23,406 просмотров • 2 лет назад

🤖Introducing TWIST: Teleoperated Whole-Body Imitation System. We develop a humanoid teleoperation system to enable coordinated, versatile, whole-body movements, using a single neural network. This is our first step toward general-purpose robots. 🌐
1:30

🤖Introducing TWIST: Teleoperated Whole-Body Imitation System. We develop a humanoid teleoperation system to enable coordinated, versatile, whole-body movements, using a single neural network. This is our first step toward general-purpose robots. 🌐

Yanjie Ze

79,931 просмотров • 1 год назад

🚨 #UIST2024 Paper: SHAPE-IT🪄 SHAPE-IT enables users to freely 'tell' the shape display to transform by only giving text instructions using LLMs. It offers an experience like that Sci-Fi Clay that can shape-shift whatever you say it to be✨🪄 AxLab - Actuated Experience Lab The University of Chicago →🧵
4:17

🚨 #UIST2024 Paper: SHAPE-IT🪄 SHAPE-IT enables users to freely 'tell' the shape display to transform by only giving text instructions using LLMs. It offers an experience like that Sci-Fi Clay that can shape-shift whatever you say it to be✨🪄 AxLab - Actuated Experience Lab The University of Chicago →🧵

Ken Nakagaki

15,547 просмотров • 1 год назад

Education is getting its biggest upgrade in decades. We’re launching Feynman-2 — our new system for learning that remembers your progress, solves with you, and gives you tools to put your learning into practice. Visual generative content, highly accurate responses powered by web search, memory-based practice, and much more. Live now on Opennote →
1:32

Education is getting its biggest upgrade in decades. We’re launching Feynman-2 — our new system for learning that remembers your progress, solves with you, and gives you tools to put your learning into practice. Visual generative content, highly accurate responses powered by web search, memory-based practice, and much more. Live now on Opennote →

Abhi

90,968 просмотров • 1 год назад

Cursor can now respond by creating interactive canvases to visually represent information. Ask it to generate dashboards and custom interfaces that are richer than plain text.
0:21

Cursor can now respond by creating interactive canvases to visually represent information. Ask it to generate dashboards and custom interfaces that are richer than plain text.

Cursor

221,403 просмотров • 2 месяцев назад

How can video games become more accessible for disabled players? Haunted Space🔺 , powered by Avalanche, built Polaris Accessibility using 4D audio & Microsoft's adaptive controller to enable gaming through sound & adaptive controls. For more 👇
1:38

How can video games become more accessible for disabled players? Haunted Space🔺 , powered by Avalanche, built Polaris Accessibility using 4D audio & Microsoft's adaptive controller to enable gaming through sound & adaptive controls. For more 👇

Avalanche🔺

19,059 просмотров • 1 год назад