Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Today we're introducing TRIBE v2 (Trimodal Brain Encoder), a foundation model trained to predict how the human brain responds to almost any sight or sound. Building on our Algonauts 2025 award-winning architecture, TRIBE v2 draws on 500+ hours of fMRI recordings from 700+ people to create a digital twin... show more

AI at Meta

847,509 subscribers

6,973,750 görüntüleme • 5 ay önce •via X (Twitter)

Eğitim Sağlık & İyilik Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Meta's new AI can predict your brain better than a brain scan. TRIBE v2 is a foundation model trained on 1,000+ hours of brain imaging data from 720 people. You feed it a video, sound clip, or text, and it predicts: > Which brain regions light up > How strongly > And in what order When tested on people it had never seen, the model's predictions were actually more accurate than most real brain scans (which get distorted by heartbeats, breathing, and movement). Researchers then replicated decades of classic neuroscience experiments entirely inside the software. No scanner, no human subjects. The model correctly identified the brain's face recognition center, language network, and emotional processing regions on its own. But look at what else Meta has been building: > Ray-Ban smart glasses that see and hear what you do > A wristband that reads nerve signals > And now a model that predicts how your brain responds to any piece of content There's no evidence these are all connected... but Meta now has a complete picture of attention, from the stimulus to the neural response.

Meta's new AI can predict your brain better than a brain scan. TRIBE v2 is a foundation model trained on 1,000+ hours of brain imaging data from 720 people. You feed it a video, sound clip, or text, and it predicts: > Which brain regions light up > How strongly > And in what order When tested on people it had never seen, the model's predictions were actually more accurate than most real brain scans (which get distorted by heartbeats, breathing, and movement). Researchers then replicated decades of classic neuroscience experiments entirely inside the software. No scanner, no human subjects. The model correctly identified the brain's face recognition center, language network, and emotional processing regions on its own. But look at what else Meta has been building: > Ray-Ban smart glasses that see and hear what you do > A wristband that reads nerve signals > And now a model that predicts how your brain responds to any piece of content There's no evidence these are all connected... but Meta now has a complete picture of attention, from the stimulus to the neural response.

Rowan Cheung

29,939 görüntüleme • 5 ay önce

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Soniox

663,421 görüntüleme • 29 gün önce

Gold on digital rails can open more than access. It can create new ways for people to enter, exit, learn, and participate in the world of finance. Most RWA tokens focus on providing exposure to an asset, but Ubuntu Tribe is building a community that empowers financial literacy and rewards participants. Together we rise!

Gold on digital rails can open more than access. It can create new ways for people to enter, exit, learn, and participate in the world of finance. Most RWA tokens focus on providing exposure to an asset, but Ubuntu Tribe is building a community that empowers financial literacy and rewards participants. Together we rise!

Ubuntu Tribe

10,335 görüntüleme • 4 ay önce

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,645 görüntüleme • 1 yıl önce

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

We are back. After one year of quiet building. Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability. For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans. Solving it means rethinking the whole stack from the ground up: - A robotics-native foundation model. - A 1:1 human-like robotic hand. - A noninvasive data collection glove for motion, force, and touch. - A simulator that turns weeks of experiments into minutes. GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm. Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on) We are approaching the endgame for robotics. And this is just a beginning.

Genesis AI

2,736,146 görüntüleme • 4 ay önce

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

AI at Meta

1,252,672 görüntüleme • 8 ay önce

🚨Science nerds are going to lose their minds. Kai Rowan just open sourced a framework that predicts how your brain responds to any text, audio, or video by simulating cortical fMRI activity with 30% more accuracy than Meta's own model. No fMRI scanner. No neuroscience PhD. No million-dollar lab. It's called NForge. Here's what this thing actually does: → Feed it any combination of text, audio, or video and it predicts cortical surface activity across ~20,484 brain vertices → Extracts deep features via LLaMA 3.2, V-JEPA2, and Wav2Vec-BERT simultaneously → Generates ROI attention maps showing exactly which brain regions fire hardest at which moments → Runs real-time streaming predictions from live feature streams -- no pre-loading the full clip → Breaks down exactly how much text vs audio vs video drove each prediction with per-vertex modality attribution scores → Adapts to entirely new subjects with just a few calibration scans -- no full retraining required Here's the wildest part: Built on Meta's TRIBE v2 foundation but adds 6 major capabilities Meta never shipped. Cross-subject generalization. Streaming inference. Modality attribution. torch.compile support. Full test coverage. Professional src/ package layout. You literally point this at a movie clip and it tells you which parts of the human cortex light up -- broken down by what your eyes, ears, and language centers each contributed. That sentence shouldn't be real in 2026. But here we are. 100% Open Source. pip install nforge. (Link in the comments)

🚨Science nerds are going to lose their minds. Kai Rowan just open sourced a framework that predicts how your brain responds to any text, audio, or video by simulating cortical fMRI activity with 30% more accuracy than Meta's own model. No fMRI scanner. No neuroscience PhD. No million-dollar lab. It's called NForge. Here's what this thing actually does: → Feed it any combination of text, audio, or video and it predicts cortical surface activity across ~20,484 brain vertices → Extracts deep features via LLaMA 3.2, V-JEPA2, and Wav2Vec-BERT simultaneously → Generates ROI attention maps showing exactly which brain regions fire hardest at which moments → Runs real-time streaming predictions from live feature streams -- no pre-loading the full clip → Breaks down exactly how much text vs audio vs video drove each prediction with per-vertex modality attribution scores → Adapts to entirely new subjects with just a few calibration scans -- no full retraining required Here's the wildest part: Built on Meta's TRIBE v2 foundation but adds 6 major capabilities Meta never shipped. Cross-subject generalization. Streaming inference. Modality attribution. torch.compile support. Full test coverage. Professional src/ package layout. You literally point this at a movie clip and it tells you which parts of the human cortex light up -- broken down by what your eyes, ears, and language centers each contributed. That sentence shouldn't be real in 2026. But here we are. 100% Open Source. pip install nforge. (Link in the comments)

Guri Singh

244,515 görüntüleme • 5 ay önce

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

AI at Meta

310,507 görüntüleme • 1 yıl önce

Today, we released our new brand, vision and products to set a new foundation for the future on-chain economy. Hear the story of Injective, how we got here and how we are building an entirely new future for finance.

Injective 🥷

60,946 görüntüleme • 1 yıl önce

Jim Fan says NVIDIA trained humanoid robots to walk and move like humans -- zero-shot transfer from simulation to the real world. 10 years of learning, compressed into 2 hours of simulation. Turns out you don’t need a giant model to master motion. “1.5 million parameters, not billion, to capture the subconscious processing of the human body.” Big embodiment, small brain.

Jim Fan says NVIDIA trained humanoid robots to walk and move like humans -- zero-shot transfer from simulation to the real world. 10 years of learning, compressed into 2 hours of simulation. Turns out you don’t need a giant model to master motion. “1.5 million parameters, not billion, to capture the subconscious processing of the human body.” Big embodiment, small brain.

vitrupo

714,883 görüntüleme • 1 yıl önce

I cloned myself. Meet v2 of Hal = my second brain and AI human (digital twin) He is 10x better than v1, which we posted a few weeks. Smarter. Faster. More me. For most of my career, I chased developers to help me build something. For Hal, I did it myself. I stayed up until 4 am several nights building the core brain, connecting all the tools. Having total control over the context and architecture was the most fun I’ve had in years. He is an actual presence in my meetings and remembers more than I ever could.

I cloned myself. Meet v2 of Hal = my second brain and AI human (digital twin) He is 10x better than v1, which we posted a few weeks. Smarter. Faster. More me. For most of my career, I chased developers to help me build something. For Hal, I did it myself. I stayed up until 4 am several nights building the core brain, connecting all the tools. Having total control over the context and architecture was the most fun I’ve had in years. He is an actual presence in my meetings and remembers more than I ever could.

Brian Halligan

35,826 görüntüleme • 1 ay önce

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

NVIDIA Robotics

23,082 görüntüleme • 2 ay önce

AI’s trust problem ends today. We're thrilled to launch two new services, EigenCompute and EigenAI on EigenCloud. A new foundation for building truly verifiable apps and agents. One of the biggest upgrades to AI since the launch of GPTs. More 🧵 ↓

AI’s trust problem ends today. We're thrilled to launch two new services, EigenCompute and EigenAI on EigenCloud. A new foundation for building truly verifiable apps and agents. One of the biggest upgrades to AI since the launch of GPTs. More 🧵 ↓

EigenCloud

1,230,011 görüntüleme • 11 ay önce

Introducing GEN-1.5, a one-shot learner. It can learn new tasks in a few seconds. Show it what to do, and it generalizes. This capability emerged from pretraining on physical data at scale, as a step towards our mission of building general intelligence for the physical world.

Introducing GEN-1.5, a one-shot learner. It can learn new tasks in a few seconds. Show it what to do, and it generalizes. This capability emerged from pretraining on physical data at scale, as a step towards our mission of building general intelligence for the physical world.

Generalist

3,389,229 görüntüleme • 21 gün önce

New release from Meta FAIR — Meta Motivo is a first-of-its-kind behavioral foundation model for controlling virtual physics-based humanoid agents for a wide range of complex whole-body tasks. The model is capable of expressing human-like behaviors and achieves performance competitive with task-specific methods and outperforms state-of-the-art unsupervised RL and model-based baselines. Try the demo ➡️ Get the model and code ➡️ We’re excited about how this research could pave the way for fully embodied agents, leading to more lifelike NPCs, democratization of character animation and new types of immersive experiences.

New release from Meta FAIR — Meta Motivo is a first-of-its-kind behavioral foundation model for controlling virtual physics-based humanoid agents for a wide range of complex whole-body tasks. The model is capable of expressing human-like behaviors and achieves performance competitive with task-specific methods and outperforms state-of-the-art unsupervised RL and model-based baselines. Try the demo ➡️ Get the model and code ➡️ We’re excited about how this research could pave the way for fully embodied agents, leading to more lifelike NPCs, democratization of character animation and new types of immersive experiences.

AI at Meta

129,253 görüntüleme • 1 yıl önce

Introducing Spiral v2: A totally redesigned tool to automate your repetitive creative work—in your voice and style. Here's what's new: - 200+ new Every 📧-created Spirals we've handcrafted to help you create viral X posts, LinkedIn posts, blog posts and more - Completely redesigned interface to help you filter, clone, and edit Spirals for your use case - Significantly more powerful outputs with our enhanced AI writing prompts and the new Claude Sonnet 3.5 Our dream is to make Spiral a powerful tool to help you create content that’s catchy, confident, and authentic—that feels like the best version of you—in seconds. Check out the new version of Spiral on ProductHunt: Or try out Spiral for yourself here:

Introducing Spiral v2: A totally redesigned tool to automate your repetitive creative work—in your voice and style. Here's what's new: - 200+ new Every 📧-created Spirals we've handcrafted to help you create viral X posts, LinkedIn posts, blog posts and more - Completely redesigned interface to help you filter, clone, and edit Spirals for your use case - Significantly more powerful outputs with our enhanced AI writing prompts and the new Claude Sonnet 3.5 Our dream is to make Spiral a powerful tool to help you create content that’s catchy, confident, and authentic—that feels like the best version of you—in seconds. Check out the new version of Spiral on ProductHunt: Or try out Spiral for yourself here:

Dan Shipper 📧

56,245 görüntüleme • 1 yıl önce

Today, we are announcing the launch of Circle Gateway on testnet for Avalanche🔺, Base, and Ethereum. Circle Gateway allows users to hold a unified USDC balance across multiple chains and use it instantly on any supported chain, without needing to bridge or rely on external liquidity. To start building, watch a quick demo by Blessing Adesiji, clone the quickstart linked below, and explore our developer docs to learn more.

Today, we are announcing the launch of Circle Gateway on testnet for Avalanche🔺, Base, and Ethereum. Circle Gateway allows users to hold a unified USDC balance across multiple chains and use it instantly on any supported chain, without needing to bridge or rely on external liquidity. To start building, watch a quick demo by Blessing Adesiji, clone the quickstart linked below, and explore our developer docs to learn more.

Circle Developer

44,497 görüntüleme • 1 yıl önce

We're delighted to launch our new digital platform for the #BlackPlaysArchive 🎉 The new website contains a catalogue of over 850 Black British, African, and Caribbean plays produced in the UK from 1909 to today. Find out more here 👉

We're delighted to launch our new digital platform for the #BlackPlaysArchive 🎉 The new website contains a catalogue of over 850 Black British, African, and Caribbean plays produced in the UK from 1909 to today. Find out more here 👉

National Theatre

76,916 görüntüleme • 2 yıl önce

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

Andrew Ng

224,608 görüntüleme • 2 yıl önce