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。

What if we could model human input/output channels with multi-modal #AI? Congratulations to our amazing intern Bruce Liu for the Honorable Mentions Award #CHI2024 with amazing collaboration w/ Jiahao “Nick” Li, David Kim, and Xiang 'Anthony' Chen ! ACM SIGCHI UCLA #a11y

Ruofei Du

2,317 subscribers

10,790 次观看 • 2 年前 •via X (Twitter)

科学技术 #AI #CHI2024 #a11y

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

What an amazing start to the week! A little trip to London to accept the Estrella Damm Top 50 Gastropubs award for our pub! So proud to be up there with some absolute legends! We could never do this without our amazing team, fantastic guests and the most supportive locals ever we are humbled and honoured and this is just the most amazing start to the year!

What an amazing start to the week! A little trip to London to accept the Estrella Damm Top 50 Gastropubs award for our pub! So proud to be up there with some absolute legends! We could never do this without our amazing team, fantastic guests and the most supportive locals ever we are humbled and honoured and this is just the most amazing start to the year!

The White Horse Pub

12,878 次观看 • 6 个月前

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Zhiyang (Frank) Dou

14,610 次观看 • 1 年前

Content creators, we’ve got your back! 🔥 Creating posts and banners takes time—but what if AI could do it for you? 🤯 With #Inferium, just: ✅ Picking the perfect model (you can use our Magic Search and compare models if you dont know what to use) ✅ Entering your input ✅ Getting output in seconds No stress, no struggle—just high-quality content & stunning visuals in seconds! 🚀 Run inference with our free serverless API today 👉

Content creators, we’ve got your back! 🔥 Creating posts and banners takes time—but what if AI could do it for you? 🤯 With #Inferium, just: ✅ Picking the perfect model (you can use our Magic Search and compare models if you dont know what to use) ✅ Entering your input ✅ Getting output in seconds No stress, no struggle—just high-quality content & stunning visuals in seconds! 🚀 Run inference with our free serverless API today 👉

Inferium

91,769 次观看 • 1 年前

Together with the Ego4D consortium, we recently released Ego-Exo4D: A diverse, large-scale multi-modal, multi-view, video dataset and benchmark. Learn more about the work ➡️ Access the dataset ➡️ This work could help to advance AI models' understanding of complex human skills & enable new applications for AR systems, robotics & more.

Together with the Ego4D consortium, we recently released Ego-Exo4D: A diverse, large-scale multi-modal, multi-view, video dataset and benchmark. Learn more about the work ➡️ Access the dataset ➡️ This work could help to advance AI models' understanding of complex human skills & enable new applications for AR systems, robotics & more.

AI at Meta

78,070 次观看 • 2 年前

I went on AM 560 radio with Black and Right Radio W/John Anthony to talk about all the amazing things that Elon Musk is doing with AI and what the future holds for us. We talked about: -Cybercabs coming to Illinois -Grok curing cancer -Tesla creating post-scarcity -Neuralink helping the disabled -Staying ahead of China in AI -Me meeting Elon in Wisconsin -And more... We also talked about all the amazing things that Elon is doing to make the world a better place. We are truly blessed to have Elon with us; the future will look amazing. ❤️ Maye Musk 𝙺𝚒𝚖𝚋𝚊𝚕 𝙼𝚞𝚜𝚔 🤠 Tosca Musk

I went on AM 560 radio with Black and Right Radio W/John Anthony to talk about all the amazing things that Elon Musk is doing with AI and what the future holds for us. We talked about: -Cybercabs coming to Illinois -Grok curing cancer -Tesla creating post-scarcity -Neuralink helping the disabled -Staying ahead of China in AI -Me meeting Elon in Wisconsin -And more... We also talked about all the amazing things that Elon is doing to make the world a better place. We are truly blessed to have Elon with us; the future will look amazing. ❤️ Maye Musk 𝙺𝚒𝚖𝚋𝚊𝚕 𝙼𝚞𝚜𝚔 🤠 Tosca Musk

Adam Lowisz X Meetup 🇺🇸🇵🇱🇪🇺🇬🇧🇺🇦

105,377 次观看 • 20 天前

It’s amazing seeing Dr David Unwin (Dr David Unwin) on such a large platform sharing his knowledge. Dr David Unwin is a founding member of the Public Health Collaboration and a trusted voice within the health industry. We are incredibly grateful for the work he has done with our charity over the years. If you’d like to watch the full video: To read our thoughts on the conversation:

It’s amazing seeing Dr David Unwin (Dr David Unwin) on such a large platform sharing his knowledge. Dr David Unwin is a founding member of the Public Health Collaboration and a trusted voice within the health industry. We are incredibly grateful for the work he has done with our charity over the years. If you’d like to watch the full video: To read our thoughts on the conversation:

Public Health Collaboration

14,095 次观看 • 2 个月前

Last week we had an amazing conversation with Forbes Web3, going down the rabbit hole of AI and web3. Where do these two industries intersect? Are they working synergistically? Watch the full conversation below for the entire panel's opinions and input on what the future may have in store for both AI and web3. And be on the lookout for our next guest space tomorrow, 4 PM UTC with MicroGPT!

Last week we had an amazing conversation with Forbes Web3, going down the rabbit hole of AI and web3. Where do these two industries intersect? Are they working synergistically? Watch the full conversation below for the entire panel's opinions and input on what the future may have in store for both AI and web3. And be on the lookout for our next guest space tomorrow, 4 PM UTC with MicroGPT!

GameGPT by PRISM

17,980 次观看 • 1 年前

“..what an amazing opportunity for Ireland, we could form a new state that’s inclusive for everybody and looks at the social issues that our generation are really suffering with.” - Doireann Ní Ghlacáin, How to Gael

“..what an amazing opportunity for Ireland, we could form a new state that’s inclusive for everybody and looks at the social issues that our generation are really suffering with.” - Doireann Ní Ghlacáin, How to Gael

Irish Unity 🇮🇪🇵🇸

71,107 次观看 • 4 个月前

A night of excellence and appreciation! Fatima Aliko-Dangote, Group Executive Director, Commercial, Dangote Cement PLC, highlights our commitment to a customer-centric culture at the 2026 Customer Celebration and Distributor Awards Night. For us, it’s more than just volume—it’s about the value and growth we create with our amazing partners every single day. Congratulations to all our award winners!

A night of excellence and appreciation! Fatima Aliko-Dangote, Group Executive Director, Commercial, Dangote Cement PLC, highlights our commitment to a customer-centric culture at the 2026 Customer Celebration and Distributor Awards Night. For us, it’s more than just volume—it’s about the value and growth we create with our amazing partners every single day. Congratulations to all our award winners!

Dangote Cement

263,601 次观看 • 6 个月前

This means A LOT to me‼️ especially in these Times where the active Erasure of Trans people is priority ONE with our Government! To have iHeartPodcasts and Patreon Have our AWARD nominated podcast "Outlaws" with TS Madison plastered right there in TIMES SQUARE says to the world WE ARE HERE…… WE ARE QUEER and WE HAVE THE RIGHT to be seen and heard like every other HUMAN!! Thank you to my Amazing team ❤️ Trent ❤️🕊️ Tyler Rabinowitz My producer @turtlerunentertainment for OUR AMAZING SHOW ❤️ My momma is so proud 🥹 I LOVE YOU NYC 💕

This means A LOT to me‼️ especially in these Times where the active Erasure of Trans people is priority ONE with our Government! To have iHeartPodcasts and Patreon Have our AWARD nominated podcast "Outlaws" with TS Madison plastered right there in TIMES SQUARE says to the world WE ARE HERE…… WE ARE QUEER and WE HAVE THE RIGHT to be seen and heard like every other HUMAN!! Thank you to my Amazing team ❤️ Trent ❤️🕊️ Tyler Rabinowitz My producer @turtlerunentertainment for OUR AMAZING SHOW ❤️ My momma is so proud 🥹 I LOVE YOU NYC 💕

Ts Madison

44,613 次观看 • 4 个月前

In June 2024, a group of creators began creating with Kling AI. Besides "this is amazing," we heard one phrase more than anything else: "If only." If only characters felt more alive. If only movement felt more real. If only she could speak. For two years, we heard this over and over again. And with every iteration of our product, we listened. From Kling 1.0 to 3.0, every breakthrough began with a creator saying: "If only it could be better." In June 2026, Kling AI has reached over 100 million users worldwide. As we celebrate our Anniversary II, we want to say thank you to every creator. Kling has grown with you, every step of the way.

In June 2024, a group of creators began creating with Kling AI. Besides "this is amazing," we heard one phrase more than anything else: "If only." If only characters felt more alive. If only movement felt more real. If only she could speak. For two years, we heard this over and over again. And with every iteration of our product, we listened. From Kling 1.0 to 3.0, every breakthrough began with a creator saying: "If only it could be better." In June 2026, Kling AI has reached over 100 million users worldwide. As we celebrate our Anniversary II, we want to say thank you to every creator. Kling has grown with you, every step of the way.

Kling AI

14,609 次观看 • 1 个月前

🚨 EXCLUSIVE: BRYAN JOHNSON ON AI, IMMORTALITY, AND THE END OF HUMAN LIMITS What if AI doesn’t just change the world—but everything about what it means to be human? Bryan Johnson: “Living for tomorrow and living forever are identical ideas. It breaks the human brain.” AI is about to shatter our understanding of life, death, and free will—and we are more primitive than we dare to admit. Full interview with Bryan Johnson by Mario Nawfal and Dr Danish drops soon—only on 𝕏.

🚨 EXCLUSIVE: BRYAN JOHNSON ON AI, IMMORTALITY, AND THE END OF HUMAN LIMITS What if AI doesn’t just change the world—but everything about what it means to be human? Bryan Johnson: “Living for tomorrow and living forever are identical ideas. It breaks the human brain.” AI is about to shatter our understanding of life, death, and free will—and we are more primitive than we dare to admit. Full interview with Bryan Johnson by Mario Nawfal and Dr Danish drops soon—only on 𝕏.

Mario Nawfal

608,095 次观看 • 1 年前

Here we go again 🚀! Excited to announce that we're building A1Zap (YC W25) with Pennie Li and that we're in the Y Combinator W25 batch in San Francisco! What is A1Base? A1Base gives AI Agents a real world identity for work. We do that by rebuilding Twilio and Okta from the ground up, putting AI Agents first. This means developers can make AI-first agentic applications 10x easier with our API's. ⁉️ Why are we doing this? Because there's a huge torrent of new valuable companies possible with AI agents, but to get their AI Agents to users, they have to chain custom apps, chat interfaces, awkward Slack integrations, browser bots, and wrestle with Twilio’s legacy API (which is built for marketing). We solve this by providing developers with an easy to use API to interface your AI agent with humans/coworkers/users where they are in this case in Whatsapp, Slack, Teams, SMS and more) - with AI Agent features built in. These digital workers are poised to transform how we work and we're the critical infrastructure to help them interact naturally in human workflows. We're not just building another AI tool. We're creating the infrastructure that will enable AI agents to become a natural part of the workforce - handling everything from customer support to sales development to creative work. We're backed by Y Combinator and working with founding teams who share our vision. We believe that in the near future, AI Agents with human coworkers will enable us to pursue more creative and impactful work. Our mission is to help developers build AI Agents that people can partner with and rely on as trusted allies—always with a human-first mindset. If you're thinking about the Agentic future of your company reach out! If you're looking to build your first AI Agentic company - reach out too - we have some amazing open source templates to get you started on the journey. Excited to share more of what we're up to soon 🔜.

Here we go again 🚀! Excited to announce that we're building A1Zap (YC W25) with Pennie Li and that we're in the Y Combinator W25 batch in San Francisco! What is A1Base? A1Base gives AI Agents a real world identity for work. We do that by rebuilding Twilio and Okta from the ground up, putting AI Agents first. This means developers can make AI-first agentic applications 10x easier with our API's. ⁉️ Why are we doing this? Because there's a huge torrent of new valuable companies possible with AI agents, but to get their AI Agents to users, they have to chain custom apps, chat interfaces, awkward Slack integrations, browser bots, and wrestle with Twilio’s legacy API (which is built for marketing). We solve this by providing developers with an easy to use API to interface your AI agent with humans/coworkers/users where they are in this case in Whatsapp, Slack, Teams, SMS and more) - with AI Agent features built in. These digital workers are poised to transform how we work and we're the critical infrastructure to help them interact naturally in human workflows. We're not just building another AI tool. We're creating the infrastructure that will enable AI agents to become a natural part of the workforce - handling everything from customer support to sales development to creative work. We're backed by Y Combinator and working with founding teams who share our vision. We believe that in the near future, AI Agents with human coworkers will enable us to pursue more creative and impactful work. Our mission is to help developers build AI Agents that people can partner with and rely on as trusted allies—always with a human-first mindset. If you're thinking about the Agentic future of your company reach out! If you're looking to build your first AI Agentic company - reach out too - we have some amazing open source templates to get you started on the journey. Excited to share more of what we're up to soon 🔜.

Pasha Rayan

53,950 次观看 • 1 年前

For now, BCIs like mine are output-only. They don’t generate input in the brain. They simply read neural signals and turn them into actions — like controlling a computer with your mind. In the future, I do think BCIs will be able to generate input into the brain. We are very far from that today, and anyone saying otherwise is getting ahead of reality. But if we ever get there, the most important question won’t be technical. It’ll be: what will it mean to be human?

For now, BCIs like mine are output-only. They don’t generate input in the brain. They simply read neural signals and turn them into actions — like controlling a computer with your mind. In the future, I do think BCIs will be able to generate input into the brain. We are very far from that today, and anyone saying otherwise is getting ahead of reality. But if we ever get there, the most important question won’t be technical. It’ll be: what will it mean to be human?

Noland Arbaugh

13,757 次观看 • 7 个月前

What if we could teach an AI to master the strategic game of 2048 through pure reinforcement learning? I did exactly that with "Agent 2048" - fine-tuning Qwen 7B model using GRPO to develop spatial reasoning and merge strategies with zero prior gameplay SFTdata! Thanks to Hugging Face and Unsloth AI for their easy to use implementation kalomaze and will brown you might like this :)

What if we could teach an AI to master the strategic game of 2048 through pure reinforcement learning? I did exactly that with "Agent 2048" - fine-tuning Qwen 7B model using GRPO to develop spatial reasoning and merge strategies with zero prior gameplay SFTdata! Thanks to Hugging Face and Unsloth AI for their easy to use implementation kalomaze and will brown you might like this :)

Hrishbh Dalal

31,863 次观看 • 1 年前

"I think that what this technology should enable, if used correctly, is give us more time back." Chemistry laureate Demis Hassabis on how we could and maybe should use AI to simplify our lives. He and fellow laureate Paul Nurse joined our event in London, UK to discuss the topic of AI further. Hassabis shared the 2024 chemistry prize for presenting an AI model called AlphaFold2. With its help, we have been able to predict the structure of virtually all known proteins. Watch the full event:

"I think that what this technology should enable, if used correctly, is give us more time back." Chemistry laureate Demis Hassabis on how we could and maybe should use AI to simplify our lives. He and fellow laureate Paul Nurse joined our event in London, UK to discuss the topic of AI further. Hassabis shared the 2024 chemistry prize for presenting an AI model called AlphaFold2. With its help, we have been able to predict the structure of virtually all known proteins. Watch the full event:

The Nobel Prize

16,568 次观看 • 1 个月前

Systems like OpenAI's new Sora video model, just shows us that anyone can create a pretty video or a beautiful picture using nothing but a text prompt. But if we are to use the technology to create interesting art, thought-provoking cinema, and great games.. we need control of the output down to a granular level if that's what our project calls for. We need better tools and better interfaces to interact with the generative matter. Here's another example of what that could look like. Imagine this combined with a system like Sora. With complete temporal coherence and an ability to lock down the look of elements once you decide they look as they should. #ThePowerofDreams #Sora

Systems like OpenAI's new Sora video model, just shows us that anyone can create a pretty video or a beautiful picture using nothing but a text prompt. But if we are to use the technology to create interesting art, thought-provoking cinema, and great games.. we need control of the output down to a granular level if that's what our project calls for. We need better tools and better interfaces to interact with the generative matter. Here's another example of what that could look like. Imagine this combined with a system like Sora. With complete temporal coherence and an ability to lock down the look of elements once you decide they look as they should. #ThePowerofDreams #Sora

Martin Nebelong

52,888 次观看 • 2 年前

📍 Arvin, California 🥔 Great to be in California’s Central Valley with Rep. David Valadao. From potatoes to dairy, this region is a powerhouse of American agriculture. California is America’s #1 producer of specialty crops and a top producer with truly amazing output, accounting for nearly two-thirds of the nation’s fruits, vegetables, and nuts. Dept. of Agriculture is working every day to ensure our producers have the tools, support, and certainty they need to keep doing what they do best.

📍 Arvin, California 🥔 Great to be in California’s Central Valley with Rep. David Valadao. From potatoes to dairy, this region is a powerhouse of American agriculture. California is America’s #1 producer of specialty crops and a top producer with truly amazing output, accounting for nearly two-thirds of the nation’s fruits, vegetables, and nuts. Dept. of Agriculture is working every day to ensure our producers have the tools, support, and certainty they need to keep doing what they do best.

Secretary Brooke Rollins

12,220 次观看 • 2 个月前

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,763 次观看 • 1 年前