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。

We are thrilled to present Virtual Volunteer™, a digital visual assistant powered by OpenAI’s GPT-4 language model. Virtual Volunteer will answer any question about an image and provide instantaneous visual assistance in real-time within the app. #Accessibility #Inclusion #CSUN

Be My Eyes

34,748 subscribers

2,341,111 次观看 • 3 年前 •via X (Twitter)

健康养生科学技术 #Accessibility #Inclusion #CSUN

Anya Rossi• Live Now

Private livecam show

10 条评论

Be My Eyes 的头像

Be My Eyes3 年前

#BeMyEyes’ Virtual Volunteer™ is already available for a pool of beta testers. Join our waitlist in the Be My Eyes app!

Shubham Verma 的头像

Shubham Verma3 年前

@OpenAI One of the most impactful implementations of #ChatGPT I've seen.

Be My Eyes 的头像

Be My Eyes3 年前

And to read more about Virtual Volunteer, visit our new blog post:

Logan Kilpatrick 的头像

Logan Kilpatrick3 年前

@OpenAI GPT-4 is so powerful, seeing this in action and knowing the impact it will have is so exciting! ♥️

Tom Bielecki 的头像

Tom Bielecki3 年前

@OpenAI Fantastic! For colorblindness I'd rather ask an AI than a person anyway!

Roulette.dk 的头像

Roulette.dk3 年前

@OpenAI She looks so happy ♥️♥️♥️

Kamira 的头像

Kamira3 年前

@OpenAI Amazing work

Bilal 的头像

Bilal3 年前

@OpenAI Awesome - this could make alt tags unnecessary and users who use screen readers don't have to rely on manual descriptions for images.

gb 的头像

gb3 年前

@OpenAI This is one of the most amazing applications of gpt-4 to address a real world problem

Markus Schad 的头像

Markus Schad3 年前

@OpenAI Awesome work!

相关视频

Say hello to Alpha: your investing co-pilot powered by OpenAI’s GPT-4. Get real-time and historical market data in a natural language interface. On demand. Go ahead. Start a conversation about any asset you care about.

Say hello to Alpha: your investing co-pilot powered by OpenAI’s GPT-4. Get real-time and historical market data in a natural language interface. On demand. Go ahead. Start a conversation about any asset you care about.

Public

366,575 次观看 • 3 年前

We are excited to announce that we have successfully integrated Be My AI within Microsoft Disability Answer Desk! Starting today, Microsoft’s DAD will officially be powered by Be My AI, the Artificial Intelligence Visual Assistant from Be My Eyes! 🚀

We are excited to announce that we have successfully integrated Be My AI within Microsoft Disability Answer Desk! Starting today, Microsoft’s DAD will officially be powered by Be My AI, the Artificial Intelligence Visual Assistant from Be My Eyes! 🚀

Be My Eyes

84,404 次观看 • 2 年前

Ever wondered how the Alibaba Wonder on Ice experience comes to life?❄️ By leveraging Qwen3 series of large language and vision models and Wan 2.2 image-to-video generation model, each visitor will embark on an adventure that engages all senses and transcends the virtual and the real. The Olympic Games Milano Cortina 2026

Ever wondered how the Alibaba Wonder on Ice experience comes to life?❄️ By leveraging Qwen3 series of large language and vision models and Wan 2.2 image-to-video generation model, each visitor will embark on an adventure that engages all senses and transcends the virtual and the real. The Olympic Games Milano Cortina 2026

Alibaba Group

505,284 次观看 • 6 个月前

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai

GPT Image 2 - Character Reference Sheet Prompt You can create a character reference sheet in any style you want for use in your Seedance 2.0 videos. All you need to do is either provide a reference image or describe your character. You can also input random values to generate completely random characters. This reference sheet provides a clear, structured, and highly readable visual breakdown of the character, helping the model maintain strong identity consistency across different outputs. The layout ensures the model focuses on essential visual information rather than stylistic noise, while the inclusion of expressions, head angles, and performance cues improves the model’s ability to generate believable acting and varied poses without losing character integrity. All clips in the demonstration video were generated using the reference sheet image and the same Seedance 2.0 prompt. You can find the prompts in the replies. 👇 GPT Image 2 and Seedance 2.0 are both available on mitte.ai

Kōda

162,620 次观看 • 3 个月前

Taking talking shop to a whole new level. We just shipped Glean’s real-time voice capability, powered by OpenAI’s newest speech model GPT-Realtime-2. Grounded in the context across your org, it feels like a real AI coworker and can keep up with how work gets finished. In internal evals, GPT-Realtime-2 delivered a 42.9% relative increase in helpfulness over its previous version. Give it a try. It speaks for itself. OpenAIDevs

Taking talking shop to a whole new level. We just shipped Glean’s real-time voice capability, powered by OpenAI’s newest speech model GPT-Realtime-2. Grounded in the context across your org, it feels like a real AI coworker and can keep up with how work gets finished. In internal evals, GPT-Realtime-2 delivered a 42.9% relative increase in helpfulness over its previous version. Give it a try. It speaks for itself. OpenAIDevs

Glean

16,588 次观看 • 3 个月前

In November 2024, the Supreme Court ruled that accessibility is a fundamental right, directing businesses to ensure their digital platforms are accessible to people with disabilities. The Court essentially said that in a digital-first world, denying digital access means denying basic rights. It's not just about compliance, it's about constitutional equality. Accessibility has been core to how we build at . The mandate didn't change our approach, it just gave us a deadline. And since we don't have to rebuild for accessibility from scratch, we are confident to be able to make the deadline. 🙂 Here's one of our users with severe visual impairment using Kite.

In November 2024, the Supreme Court ruled that accessibility is a fundamental right, directing businesses to ensure their digital platforms are accessible to people with disabilities. The Court essentially said that in a digital-first world, denying digital access means denying basic rights. It's not just about compliance, it's about constitutional equality. Accessibility has been core to how we build at . The mandate didn't change our approach, it just gave us a deadline. And since we don't have to rebuild for accessibility from scratch, we are confident to be able to make the deadline. 🙂 Here's one of our users with severe visual impairment using Kite.

Nithin Kamath

184,282 次观看 • 8 个月前

We are thrilled to announce that EVA Flower Mound is now the official HEADQUARTERS of REGIMENT! 🇺🇸 Esports Virtual Arenas (known as EVA) is a world class concept centered around the art of casual and competitive gaming in the realm of Virtual Reality. Entertaining players of any level within a free roam physical and digital environment of 5,600 square feet. Unmatched in the industry, allowing for friends, family, companies, and teams to challenge each other and level up their skills. If you're ever in the Dallas-Fort Worth, Texas area - stop by the REGIMENT HQ!

We are thrilled to announce that EVA Flower Mound is now the official HEADQUARTERS of REGIMENT! 🇺🇸 Esports Virtual Arenas (known as EVA) is a world class concept centered around the art of casual and competitive gaming in the realm of Virtual Reality. Entertaining players of any level within a free roam physical and digital environment of 5,600 square feet. Unmatched in the industry, allowing for friends, family, companies, and teams to challenge each other and level up their skills. If you're ever in the Dallas-Fort Worth, Texas area - stop by the REGIMENT HQ!

REGIMENT

98,117 次观看 • 2 年前

Zuckerberg reveals that the near-term unlock for AI is agentic AI. This is moving away from the one-question, one-answer prompt model. $META is pivoting its consumer hardware to facilitate an always-on AI assistant. Zuckerberg envisions users tuning their glasses from 30 minutes of live AI engagement to eventually all day. The AI will proactively watch, listen, and offer assistance without being explicitly prompted. The glasses are the mechanism for this level of AI context. Smartphones in pockets cannot provide the continuous visual and auditory data stream needed for ambient AI. I see the vision 😏

Zuckerberg reveals that the near-term unlock for AI is agentic AI. This is moving away from the one-question, one-answer prompt model. $META is pivoting its consumer hardware to facilitate an always-on AI assistant. Zuckerberg envisions users tuning their glasses from 30 minutes of live AI engagement to eventually all day. The AI will proactively watch, listen, and offer assistance without being explicitly prompted. The glasses are the mechanism for this level of AI context. Smartphones in pockets cannot provide the continuous visual and auditory data stream needed for ambient AI. I see the vision 😏

CapexAndChill

144,650 次观看 • 1 个月前

🚨 Huge Empower News! We are working with OpenAI to bring advanced AI-powered tools for CFOs and their teams. The new features will provide relevant insights on corporate spend and answer critical business questions all in real-time. Learn more:

🚨 Huge Empower News! We are working with OpenAI to bring advanced AI-powered tools for CFOs and their teams. The new features will provide relevant insights on corporate spend and answer critical business questions all in real-time. Learn more:

Brex

968,354 次观看 • 3 年前

We are thrilled to announce "Layered Diffusion Brushes": a real-time training-free image editor powered by diffusion models. 🎨✨ This is new work from my PhD student Peyman Gholami Peyman Gholami. Explore the interactive demo and check out more videos at:

We are thrilled to announce "Layered Diffusion Brushes": a real-time training-free image editor powered by diffusion models. 🎨✨ This is new work from my PhD student Peyman Gholami Peyman Gholami. Explore the interactive demo and check out more videos at:

Robert Xiao

14,334 次观看 • 2 年前

It's time to get out of stealth 👋 Today, we are launching Monogram and announcing our $40m seed round led by DST and Lux Capital. Monogram is the first AI app that was built around a visual interface, from the ground up. We created a technology that generates an entire user interface on the fly, in just a few seconds. Ask anything, and instead of staring at a wall of text, you get an interactive visual response.

It's time to get out of stealth 👋 Today, we are launching Monogram and announcing our $40m seed round led by DST and Lux Capital. Monogram is the first AI app that was built around a visual interface, from the ground up. We created a technology that generates an entire user interface on the fly, in just a few seconds. Ask anything, and instead of staring at a wall of text, you get an interactive visual response.

Eren Bali

1,325,553 次观看 • 1 个月前

We are delighted to announce that we have today concluded negotiations with Bara Tala, our national team sponsor of 2025. Our sponsorship partnership will now be extended to include the 2026 and 2027 seasons. Their invaluable support will help to fund the activities of our men's national team, including our second visit to take part in the Euro Cup in Poland in July 2026, and support the development of youth cricket here. Bara Tala is a popular Icelandic AI-powered, digital language-learning app and company designed to help newcomers learn Icelandic, with a specific focus on workplace, daily conversation, and pronunciation. It acts as a virtual teacher, using speech recognition to provide real-time feedback. See more: In the video, you will see clips from our preparations for last year's Euro Cup at Hamranesvöllur.

We are delighted to announce that we have today concluded negotiations with Bara Tala, our national team sponsor of 2025. Our sponsorship partnership will now be extended to include the 2026 and 2027 seasons. Their invaluable support will help to fund the activities of our men's national team, including our second visit to take part in the Euro Cup in Poland in July 2026, and support the development of youth cricket here. Bara Tala is a popular Icelandic AI-powered, digital language-learning app and company designed to help newcomers learn Icelandic, with a specific focus on workplace, daily conversation, and pronunciation. It acts as a virtual teacher, using speech recognition to provide real-time feedback. See more: In the video, you will see clips from our preparations for last year's Euro Cup at Hamranesvöllur.

Iceland Cricket

54,451 次观看 • 6 个月前

All of the announcements recently have confirmed we are officially in the Ai OS era. I'm excited about what will become possible as we all continue to push things forward. Just a few things I was thinking about this weekend on Ai Pin & Cosmos in terms of what they could unlock... Visual compute - and the applications for education, accessibility, and beyond.

All of the announcements recently have confirmed we are officially in the Ai OS era. I'm excited about what will become possible as we all continue to push things forward. Just a few things I was thinking about this weekend on Ai Pin & Cosmos in terms of what they could unlock... Visual compute - and the applications for education, accessibility, and beyond.

Bethany Bongiorno

52,927 次观看 • 2 年前

🚀 Get ready to be amazed! 🌐✨ Take a sneak peek into the future with MBD Financials' photorealistic metaverse! Our latest video showcases stunning buildings and real estate that will redefine the boundaries between the real world and the virtual world. Imagine owning a condo in the MBD Blvd. metaverse, a Real World Asset (RWA) that acts as a digital twin of real-world properties.These virtual spaces are available in AR and VR, providing immersive experiences like never before! Not only do they mirror their real-world counterparts, but they also open up a world of possibilities for side revenue. 💡 Use Cases: 1. Investment Opportunities: Own a digital condo and generate side revenue as businesses lease or purchase these spaces for their stores. 2. Virtual Events: Host conferences, meetings, and events in state-of-the-art virtual venues, reflecting the exact look and feel of their real-world locations. 3. Retail Spaces: Create virtual storefronts that are perfect replicas of real-world shops, attracting a global audience and expanding your market reach. 4. Educational Institutions: Build virtual campuses that mirror real-world universities where students can learn and interact in immersive environments. Dive into a world where digital real estate isn't just a concept but a revolution in commerce. Stay tuned as we bridge the gap between reality and the virtual realm, transforming the way we live, work, and invest. #MBDFinancials #Metaverse #DigitalRealEstate #RWA #DigitalTwins #AR #VR #InvestmentOpportunity #FutureOfCommerce #VirtualReality #DigitalTransformation #AI #Phygital #NFT #Marketplace #AmazonofWeb3 #web3 $mbd

🚀 Get ready to be amazed! 🌐✨ Take a sneak peek into the future with MBD Financials' photorealistic metaverse! Our latest video showcases stunning buildings and real estate that will redefine the boundaries between the real world and the virtual world. Imagine owning a condo in the MBD Blvd. metaverse, a Real World Asset (RWA) that acts as a digital twin of real-world properties.These virtual spaces are available in AR and VR, providing immersive experiences like never before! Not only do they mirror their real-world counterparts, but they also open up a world of possibilities for side revenue. 💡 Use Cases: 1. Investment Opportunities: Own a digital condo and generate side revenue as businesses lease or purchase these spaces for their stores. 2. Virtual Events: Host conferences, meetings, and events in state-of-the-art virtual venues, reflecting the exact look and feel of their real-world locations. 3. Retail Spaces: Create virtual storefronts that are perfect replicas of real-world shops, attracting a global audience and expanding your market reach. 4. Educational Institutions: Build virtual campuses that mirror real-world universities where students can learn and interact in immersive environments. Dive into a world where digital real estate isn't just a concept but a revolution in commerce. Stay tuned as we bridge the gap between reality and the virtual realm, transforming the way we live, work, and invest. #MBDFinancials #Metaverse #DigitalRealEstate #RWA #DigitalTwins #AR #VR #InvestmentOpportunity #FutureOfCommerce #VirtualReality #DigitalTransformation #AI #Phygital #NFT #Marketplace #AmazonofWeb3 #web3 $mbd

MBD Financials

11,093 次观看 • 2 年前

The wait is over! 🎉 Be My Eyes is now rolling out on Ray-Ban Meta glasses, bringing hands-free accessibility to our blind and low-vision community in the US, Canada, UK, Ireland, and Australia.🌟 Say, “Hey Meta, Call a Volunteer on Be My Eyes,” for hands-free, real-time assistance from 8.1M volunteers. Updates are rolling out over a few days, stay tuned! Learn more:

The wait is over! 🎉 Be My Eyes is now rolling out on Ray-Ban Meta glasses, bringing hands-free accessibility to our blind and low-vision community in the US, Canada, UK, Ireland, and Australia.🌟 Say, “Hey Meta, Call a Volunteer on Be My Eyes,” for hands-free, real-time assistance from 8.1M volunteers. Updates are rolling out over a few days, stay tuned! Learn more:

Be My Eyes

46,316 次观看 • 1 年前

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

Wenhu Chen

82,829 次观看 • 1 年前

Been playing with a character consistency workflow again. This came from Nexora that starts with a single GPT Image 2.0 character sheet and turns it into a multi-shot cinematic sequence in Seedance 2.0. One thing I added to the workflow: I first comped the character, environment, and visual style together in Midjourney before bringing everything into GPT Image 2.0 to build the character sheet. I also pushed it a bit further by generating multiple characters, destinations, and art directions at the same time, then turning those into production-style character sheets and shot sequences. It's interesting how much consistency you can get from a single well-defined character board when the visual language, wardrobe, and environment are established upfront. Check out three different character + scenes here 👇

Been playing with a character consistency workflow again. This came from Nexora that starts with a single GPT Image 2.0 character sheet and turns it into a multi-shot cinematic sequence in Seedance 2.0. One thing I added to the workflow: I first comped the character, environment, and visual style together in Midjourney before bringing everything into GPT Image 2.0 to build the character sheet. I also pushed it a bit further by generating multiple characters, destinations, and art directions at the same time, then turning those into production-style character sheets and shot sequences. It's interesting how much consistency you can get from a single well-defined character board when the visual language, wardrobe, and environment are established upfront. Check out three different character + scenes here 👇

Curious Refuge

12,209 次观看 • 2 个月前

NEW: Influencer Khaby Lame signs a $975M deal, authorizes use of his personal brand, Face ID, voice ID, and behavioral models, enabling the creation of an AI-powered digital twin. Lame started posting on TikTok back in 2020 after being fired from his job. He now has over 350,000,000 followers across platforms. He signed an all-stock deal with 'Rich Sparkle Holdings' worth just shy of $1B. "[Lame] has also authorized the development of an AI-powered digital twin. A digital twin is a virtual replica of something real, whether it be a place, an object, or a person," Complex reported. "To create it, Lame will enable Rich Sparkle to copy his facial features, voice patterns, and behavior. This will allow the company to create multilingual content, or even virtual livestreams with the streamer's digital doppelganger." Rich Sparkle predicts the deal could generate over $4B in annual sales. Insane.

Collin Rugg

8,241,964 次观看 • 6 个月前

🚨 Introducing Tempo Labs (YC S23) 🚨 A Visual Editor for React, Powered by AI. Feels like a design tool, works like an IDE. Design visually. Ship code instantly. What Makes Tempo Different: ⚡ Code-First: Works with any codebase just like an IDE. 🤝 Live Collaboration: Share links and build together in real-time. 🚀 AI-Powered: Generate full-stack apps using a text or image prompt 📢 We’re LIVE on Product Hunt! So please support us! Link below👇

🚨 Introducing Tempo Labs (YC S23) 🚨 A Visual Editor for React, Powered by AI. Feels like a design tool, works like an IDE. Design visually. Ship code instantly. What Makes Tempo Different: ⚡ Code-First: Works with any codebase just like an IDE. 🤝 Live Collaboration: Share links and build together in real-time. 🚀 AI-Powered: Generate full-stack apps using a text or image prompt 📢 We’re LIVE on Product Hunt! So please support us! Link below👇

Kevin Michael

108,475 次观看 • 1 年前

For the past few days, I've been receiving messages asking the same question: Is Junaid simply a volunteer, or is he a political actor in the making? It's a fair question. When someone repeatedly appears at high-profile protest sites, people are bound to wonder what motivates them. Rather than speculate, I decided to ask him directly. Junaid's answer was clear: "We aren't against any government. We are against the system." He insisted that his role at places like Jantar Mantar is purely humanitarian. According to him, he is there to provide food and water to students because, as he puts it, "No movement runs on an empty stomach." At the same time, his presence raises an interesting question. Even without belonging to a political party or speaking in carefully crafted political language, showing up at protest sites, supporting demonstrators, and engaging with the media inevitably carries political significance. So where do we draw the line between humanitarian support and political participation? Can an act of solidarity at a protest ever be completely apolitical, or does the context itself make it political? Watch the video to hear Junaid's answer in his own words.

Harsh Yadav

38,810 次观看 • 7 天前