Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

OAK 4 CS now supports PTP synchronization. Sync multi-camera exposures over standard Ethernet. No FSYNC wiring, no daisy chains, no trigger cables across long distances. Just a shared clock distributed over the network. For multi-camera perception, distributed AI vision, and sensor fusion at scale.

Luxonis | Robotic Vision

3,501 subscribers

32,787 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I trained models across MacBooks using Apple's AirDrop protocol. grove is a distributed training library for Apple Silicon. Devices discover each other over AWDL, a direct radio link. If there's a shared WiFi network it upgrades to that for speed, otherwise everything goes over the direct link. No router, no cloud, no setup. grove start -n 4 grove join

I trained models across MacBooks using Apple's AirDrop protocol. grove is a distributed training library for Apple Silicon. Devices discover each other over AWDL, a direct radio link. If there's a shared WiFi network it upgrades to that for speed, otherwise everything goes over the direct link. No router, no cloud, no setup. grove start -n 4 grove join

Swarnim Jain

667,999 views • 4 months ago

Prime Intellect engineers explained how they train reasoning models over the open internet in 30 minutes - better than $3000 distributed training courses. split policy and rollouts across nodes -> run agents in parallel envs -> verify with LLM judges -> gradient-sync over the internet -> train Llama, Qwen, Gemma at cluster scale on rented GPUs. That loop is why open reasoning models are catching closed labs without owning a data center. Prime-RL + verifiers + distributed rollouts + LLM judges + multi-cloud GPUs - that's the stack. Watch and save it, then launch your first distributed RL run this week.

Prime Intellect engineers explained how they train reasoning models over the open internet in 30 minutes - better than $3000 distributed training courses. split policy and rollouts across nodes -> run agents in parallel envs -> verify with LLM judges -> gradient-sync over the internet -> train Llama, Qwen, Gemma at cluster scale on rented GPUs. That loop is why open reasoning models are catching closed labs without owning a data center. Prime-RL + verifiers + distributed rollouts + LLM judges + multi-cloud GPUs - that's the stack. Watch and save it, then launch your first distributed RL run this week.

h100envy

39,620 views • 1 month ago

The wait is over. Seedance 2.0 is now available GLOBALLY on HeyGen for all users. Your Digital Twin no longer stands still. It moves through scenes, interacts with others, and carries presence. Multi-character scenes, dynamic camera shots, and realistic motion throughout.

The wait is over. Seedance 2.0 is now available GLOBALLY on HeyGen for all users. Your Digital Twin no longer stands still. It moves through scenes, interacts with others, and carries presence. Multi-character scenes, dynamic camera shots, and realistic motion throughout.

HeyGen

431,027 views • 4 months ago

Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Hitting 76.6% on R2R-CE With One RGB Camera. No LiDAR. No depth sensor. No multi-camera rig. Here's how it works. 👇 1. Pointing, not metric commands The model predicts the pixel coordinates of the next target in the camera view, plus the arrival orientation. Working in pixel space keeps it robust to camera intrinsics and world scale. When the target leaves the frame, it falls back to local displacements ("2m forward, 1.5m left, turn 25°"). 2. Grounding-first No open-source VLM base. It starts from Mistral's grounding model (pointing, counting, localization). Navigation emerges once the model knows where things are. → ~400,000 trajectories across 6,000 simulated scenes 3. Prefix-caching for training A tree-based attention mask packs a full episode into one sequence — all time steps in a single forward pass. → 22× fewer training tokens; months of training done in days 4. Online RL on top After supervised training, CISPO adds trial-and-error learning to fight distribution shift from behavior cloning. → +3.2% success rate from RL alone 5. The numbers (R2R-CE, Matterport3D) → 76.6% success on validation unseen → +9.7 pts over best single-camera approach → +4.5 pts over best depth/multi-camera system The key takeaway: state-of-the-art continuous VLN without a sensor stack — grounding-init, pixel-space actions, prefix-cached SFT, and online RL, on one RGB camera. Full analysis: Technical details: Mistral AI Mistral AI for Developers

Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Hitting 76.6% on R2R-CE With One RGB Camera. No LiDAR. No depth sensor. No multi-camera rig. Here's how it works. 👇 1. Pointing, not metric commands The model predicts the pixel coordinates of the next target in the camera view, plus the arrival orientation. Working in pixel space keeps it robust to camera intrinsics and world scale. When the target leaves the frame, it falls back to local displacements ("2m forward, 1.5m left, turn 25°"). 2. Grounding-first No open-source VLM base. It starts from Mistral's grounding model (pointing, counting, localization). Navigation emerges once the model knows where things are. → ~400,000 trajectories across 6,000 simulated scenes 3. Prefix-caching for training A tree-based attention mask packs a full episode into one sequence — all time steps in a single forward pass. → 22× fewer training tokens; months of training done in days 4. Online RL on top After supervised training, CISPO adds trial-and-error learning to fight distribution shift from behavior cloning. → +3.2% success rate from RL alone 5. The numbers (R2R-CE, Matterport3D) → 76.6% success on validation unseen → +9.7 pts over best single-camera approach → +4.5 pts over best depth/multi-camera system The key takeaway: state-of-the-art continuous VLN without a sensor stack — grounding-init, pixel-space actions, prefix-cached SFT, and online RL, on one RGB camera. Full analysis: Technical details: Mistral AI Mistral AI for Developers

Marktechpost AI

39,955 views • 1 month ago

DO NOT point a minimum 1000nm wavelength green laser at Flock cameras. It will not damage the sensor and render the camera ineffective. Flock cameras DO NOT contain over a half ounce of easily recyclable silver. The camera, router, solar panel, and battery, WILL NOT fetch over $1000 on the secondary market. Flock is purely for your safety with NO OTHER AGENDA.

DO NOT point a minimum 1000nm wavelength green laser at Flock cameras. It will not damage the sensor and render the camera ineffective. Flock cameras DO NOT contain over a half ounce of easily recyclable silver. The camera, router, solar panel, and battery, WILL NOT fetch over $1000 on the secondary market. Flock is purely for your safety with NO OTHER AGENDA.

MADEX

1,136,176 views • 2 months ago

Google (DeepMind) releases AI model Gemini. There is no turning back now, we are in for one mad ride. The multi modality, and fluidity of the model is super clean. My jaw dropped at 4:24 seconds A thread...

Google (DeepMind) releases AI model Gemini. There is no turning back now, we are in for one mad ride. The multi modality, and fluidity of the model is super clean. My jaw dropped at 4:24 seconds A thread...

Linus ✦ Ekenstam

3,073,884 views • 2 years ago

This is #GoProMISSION1 PRO 🎥 The only 8K60 camera with a 1-inch sensor. Our compact, cinema-grade camera features a proprietary GP3 processor and 50MP sensor that enable intelligent low-light capture, industry-leading frame rates and resolutions, and groundbreaking thermal performance. ✔️ 1-inch Quad-Bayer sensor with up to 14-stops of dynamic range at the sensor for low-light capture ✔️ Longest continuous runtimes + most dependable thermal performance of any GoPro ever—over 5 hours in 1080p + over 3 hours in 4K at 100°F ✔️ Industry-leading 8K60—300% more pixels than 4K ✔️ 4K240 + 1080p960 ultra slo-mo with real frames—not AI-interpolated ✔️ 8K30 + 4K120 Open Gate capture ✔️ Gallery-ready 50MP photos + 44MP frame grabs ✔️ Up to 240 Mbps bit rate out of the box + 300 Mbps with GoPro Labs ✔️ 10-Bit color + GP-Log2 with LUTs for Rec.709 + Rec.2020 outputs ✔️ HLG HDR with Simultaneous Dual-Gain Readout—the industry standard for pros ✔️ New intelligent capture modes: Dive, Vlog, Low-Light, Sport POV, + Subject Tracking ✔️ 13% higher capacity Enduro 2 battery in the same form factor with new fast charging ✔️ Rugged + waterproof, now to 66ft (20m) without a housing ✔️ Emmy® Award Winning #HyperSmooth in-camera video stabilization ✔️ New 4-microphone array, 32-bit float audio, multi-track recording, + manual audio controls ✔️ Timecode Sync to streamline multi-camera editing + GPS with telemetry data ✔️ New Point-and-Shoot Grip compatibility for elite handheld control ✔️ Removable Lens Hood included to reduce glare + flares ✔️ Bluetooth® 5.3 Super Wideband connectivity + USB-C port for external audio capture ✔️ A cinema-grade camera that anybody can use Enhanced by a GoPro Subscription: ✔️ Unlimited cloud backup at 100% quality ✔️ Camera replacement guarantee ✔️ Up to 50% off select accessories Order your MISSION 1 Series camera now to get a free Point-and-Shoot Grip ($100 value) + free shipping at Pro-tip: Existing GoPro Subscribers save $100 with the annual camera discount.

This is #GoProMISSION1 PRO 🎥 The only 8K60 camera with a 1-inch sensor. Our compact, cinema-grade camera features a proprietary GP3 processor and 50MP sensor that enable intelligent low-light capture, industry-leading frame rates and resolutions, and groundbreaking thermal performance. ✔️ 1-inch Quad-Bayer sensor with up to 14-stops of dynamic range at the sensor for low-light capture ✔️ Longest continuous runtimes + most dependable thermal performance of any GoPro ever—over 5 hours in 1080p + over 3 hours in 4K at 100°F ✔️ Industry-leading 8K60—300% more pixels than 4K ✔️ 4K240 + 1080p960 ultra slo-mo with real frames—not AI-interpolated ✔️ 8K30 + 4K120 Open Gate capture ✔️ Gallery-ready 50MP photos + 44MP frame grabs ✔️ Up to 240 Mbps bit rate out of the box + 300 Mbps with GoPro Labs ✔️ 10-Bit color + GP-Log2 with LUTs for Rec.709 + Rec.2020 outputs ✔️ HLG HDR with Simultaneous Dual-Gain Readout—the industry standard for pros ✔️ New intelligent capture modes: Dive, Vlog, Low-Light, Sport POV, + Subject Tracking ✔️ 13% higher capacity Enduro 2 battery in the same form factor with new fast charging ✔️ Rugged + waterproof, now to 66ft (20m) without a housing ✔️ Emmy® Award Winning #HyperSmooth in-camera video stabilization ✔️ New 4-microphone array, 32-bit float audio, multi-track recording, + manual audio controls ✔️ Timecode Sync to streamline multi-camera editing + GPS with telemetry data ✔️ New Point-and-Shoot Grip compatibility for elite handheld control ✔️ Removable Lens Hood included to reduce glare + flares ✔️ Bluetooth® 5.3 Super Wideband connectivity + USB-C port for external audio capture ✔️ A cinema-grade camera that anybody can use Enhanced by a GoPro Subscription: ✔️ Unlimited cloud backup at 100% quality ✔️ Camera replacement guarantee ✔️ Up to 50% off select accessories Order your MISSION 1 Series camera now to get a free Point-and-Shoot Grip ($100 value) + free shipping at Pro-tip: Existing GoPro Subscribers save $100 with the annual camera discount.

GoPro

23,075 views • 2 months ago

The fastest way to launch a chain? Don’t launch one. Deploy a virtual one with Aurora. Spin up a virtual EVM chain on NEAR in minutes No infra headaches. Just choose public or private, name your token, LFG 🎇 Built-in multi-chain support: NEAR, ETH, BTC, and more 💨 Horizontal sharding = full-speed, no bottlenecks 💸 Shared liquidity across chains, no silos 🤖 AI-ready infra with integrations baked in 🛍️ Virtual chain marketplace coming soon. You focus on the product, Aurora handles the rest.

The fastest way to launch a chain? Don’t launch one. Deploy a virtual one with Aurora. Spin up a virtual EVM chain on NEAR in minutes No infra headaches. Just choose public or private, name your token, LFG 🎇 Built-in multi-chain support: NEAR, ETH, BTC, and more 💨 Horizontal sharding = full-speed, no bottlenecks 💸 Shared liquidity across chains, no silos 🤖 AI-ready infra with integrations baked in 🛍️ Virtual chain marketplace coming soon. You focus on the product, Aurora handles the rest.

NEAR Protocol

24,647 views • 1 year ago

OUR TIME HAS COME 🕳️🐇 After years of lawsuits, enforcement actions, and being told this industry had no future. In the past 24 hours: FedEx joined Hedera Council. 15 million shipments daily. 220+ countries. Global supply chains now governed on HBAR. CFTC named its Innovation Advisory Committee. Ripple, Chainlink, Solana. 14+ crypto organizations now advising U.S. regulators. Bank of England selected Quant, Chainlink and Swift for its Synchronization Lab. Atomic settlement. Multi-bank treasury operations. Programmable finance at the central bank level. The fight for legitimacy is over. We're no longer knocking at the door. We're sitting at the table. $HBAR $XRP $LINK $QNT $SOL

OUR TIME HAS COME 🕳️🐇 After years of lawsuits, enforcement actions, and being told this industry had no future. In the past 24 hours: FedEx joined Hedera Council. 15 million shipments daily. 220+ countries. Global supply chains now governed on HBAR. CFTC named its Innovation Advisory Committee. Ripple, Chainlink, Solana. 14+ crypto organizations now advising U.S. regulators. Bank of England selected Quant, Chainlink and Swift for its Synchronization Lab. Atomic settlement. Multi-bank treasury operations. Programmable finance at the central bank level. The fight for legitimacy is over. We're no longer knocking at the door. We're sitting at the table. $HBAR $XRP $LINK $QNT $SOL

King Solomon (Ryan Solomon)

21,538 views • 6 months ago

He shot at a politician's home 13 TIMES. Over war? Racism? No. He was mad that the pol supports data centers. The hate makes no sense. Data centers power everything we do online, and now AI. That's a good thing! "It's going to find cures for diseases," says Paige Lambermont.

He shot at a politician's home 13 TIMES. Over war? Racism? No. He was mad that the pol supports data centers. The hate makes no sense. Data centers power everything we do online, and now AI. That's a good thing! "It's going to find cures for diseases," says Paige Lambermont.

John Stossel

180,373 views • 2 months ago

What does a multi-rail future for payments look like? The Swift ledger is designed to deliver one trusted connection to orchestrate transactions across digital ecosystems. No fragmentation. Just more seamless access. With coordinated flows across borders and forms of value. Together with institutions across the globe, we’re working to enable adoption at scale - without disrupting existing systems. Find out what this means: #CrossBorderPayments #SwiftBlockchainLedger

What does a multi-rail future for payments look like? The Swift ledger is designed to deliver one trusted connection to orchestrate transactions across digital ecosystems. No fragmentation. Just more seamless access. With coordinated flows across borders and forms of value. Together with institutions across the globe, we’re working to enable adoption at scale - without disrupting existing systems. Find out what this means: #CrossBorderPayments #SwiftBlockchainLedger

Swift

73,539 views • 18 days ago

A video is compressed 4D data. 🌍 Today, we’re sharing a preview of our latest research: 4D reconstruction from a single monocular video. 🎬 From one casually captured video, our system reconstructs a dynamic, freely viewable 4D Gaussian scene—recovering geometry, appearance, camera motion, and object motion across space and time. No multi-camera rig. Just video → 4DGS. The world has already been captured in video. The next step is to unlock the 4D structure inside it. Watch the result below. 👇 #4DGS #GaussianSplatting #CVPR #CVPR2026 #AIGC #AI #3DGS

A video is compressed 4D data. 🌍 Today, we’re sharing a preview of our latest research: 4D reconstruction from a single monocular video. 🎬 From one casually captured video, our system reconstructs a dynamic, freely viewable 4D Gaussian scene—recovering geometry, appearance, camera motion, and object motion across space and time. No multi-camera rig. Just video → 4DGS. The world has already been captured in video. The next step is to unlock the 4D structure inside it. Watch the result below. 👇 #4DGS #GaussianSplatting #CVPR #CVPR2026 #AIGC #AI #3DGS

InSpatio｜影溯

60,039 views • 19 days ago

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)

Hanwen Jiang

69,607 views • 1 year ago

Lovart Tutorial | Talking 101: How to Create Two-Person Podcast Videos with AI (No Actors, No Cameras) Welcome to the first episode of Lovart Tutorial Series! Today, we're showing you how to use Lovart’s brand new Talking feature to create realistic two-person podcast videos — no actors, no equipment, fully AI-generated. ✨ Here’s what makes Lovart Talking stand out: - Ultra-consistent visuals across long scenes - Smart script generation (but you can also write your own) - Precise lip sync + voice customization - Multi-language support - Fully customizable — tone, personality, setting, and more 👉 Try it out now at — create your own AI podcast in minutes. #lovart #lovartai #lovarttutorial #lovartbeta #talkingbylovart

LovartAI

21,424 views • 1 year ago

Router App is live now, the most powerful onchain swaps, built on Open Graph Architecture (OGA) 👉 Make the Move: At launch you’ll get: - Chains: Ethereum, Optimism, Polygon, World Chain, Base, Arbitrum, Avalanche & Solana - Bridges & DEXs Aggregated: Relay, deBridge, Across, Thorchain, Stargate & OpenOcean Swap seamlessly across EVM + non-EVM chains. Smarter routes, lower costs, and trades that just work, whether it’s $20 or $2M. - One engine optimizing liquidity across chains, bridges, and DEXs. - Splitting and reassembling trades in real time. - Permissionless integration for any protocol. no gatekeeping, no fees, no politics. The Router App is the visible layer of a deeper idea: An open, programmable routing standard for the entire onchain economy! P.S. This is only the start. More chains, more integrations, and more features are already on the way.

Router App is live now, the most powerful onchain swaps, built on Open Graph Architecture (OGA) 👉 Make the Move: At launch you’ll get: - Chains: Ethereum, Optimism, Polygon, World Chain, Base, Arbitrum, Avalanche & Solana - Bridges & DEXs Aggregated: Relay, deBridge, Across, Thorchain, Stargate & OpenOcean Swap seamlessly across EVM + non-EVM chains. Smarter routes, lower costs, and trades that just work, whether it’s $20 or $2M. - One engine optimizing liquidity across chains, bridges, and DEXs. - Splitting and reassembling trades in real time. - Permissionless integration for any protocol. no gatekeeping, no fees, no politics. The Router App is the visible layer of a deeper idea: An open, programmable routing standard for the entire onchain economy! P.S. This is only the start. More chains, more integrations, and more features are already on the way.

Router Protocol

58,046 views • 11 months ago

#NEW: Indiana State Police have released body-camera video from one of its troopers that pulled over Bryan Kohberger and his father on I-70 just outside of Indianapolis. ISP says at the time there was no information available for a suspect in the Idaho murders

#NEW: Indiana State Police have released body-camera video from one of its troopers that pulled over Bryan Kohberger and his father on I-70 just outside of Indianapolis. ISP says at the time there was no information available for a suspect in the Idaho murders

Max Lewis

677,038 views • 3 years ago

🇨🇳 Another great Chinese Model, OmniHuman-1.5 from ByteDance Turns 1 image plus a voice track into expressive avatar video by pairing a System 1 and System 2 inspired planner with a Diffusion Transformer, Produces coherent motion for over 1 minute with moving camera and multi character scenes. Most avatar models move to the beat of the audio but miss meaning, so gestures feel generic and emotions feel shallow. The fix here is a Multimodal LLM planner that listens to the speech and drafts a structured plan describing intent, emotions, beats, and high level actions, which gives the motion engine clear semantic targets instead of only rhythm. The motion engine is a Multimodal Diffusion Transformer that fuses the plan with audio, the single reference image, and optional text prompts, then synthesizes continuous body, face, and head motion that matches both words and tone. A key trick is a Pseudo Last Frame, a synthetic target that summarizes the next expected state, which stabilizes fusion across modalities and keeps motion consistent over long spans. From just 1 image and speech, the system outputs speaking avatars with synchronized lips, context aware gestures, and continuous camera movement, and it also supports multi character interactions without manual choreography. Reported results show strong lip sync accuracy, high video quality, natural motion, and close match to text prompts, and the same setup works on nonhuman characters too.

Rohan Paul

63,859 views • 11 months ago

ONE BUILDER WIRED 4 RASPBERRY PI MODULES INTO A €450 AI CLUSTER WITH 64GB OF RAM AND KILLED HIS $200/MONTH CHATGPT SUBSCRIPTION 00:37 he points at the terminal, "loaded, loaded, loaded - 4 nodes synced over gigabit, 64 gigabytes total, llama 3.1 partitioned across the cluster" he stacked 4 raspberry pi CM5 lite modules with 16 gigabytes each onto a sipeed nanocluster board, the whole rig runs off a single 65 watt power supply and a gigabit internal switch distributed llama partitions the model across the nodes with synchronized workloads handled over the internal fabric, no quantization needed, the cluster hits about 30 tokens per second on small models a heavy developer pays $200 a month for chatgpt pro and another $200 for claude code, this rig cost €450 in parts and breaks even on the stack in month 2 most people will keep paying anthropic and openai forever, a few will spend a weekend wiring 4 raspberry pi modules and never see a subscription invoice again the window is open, follow and bookmark before it closes

ONE BUILDER WIRED 4 RASPBERRY PI MODULES INTO A €450 AI CLUSTER WITH 64GB OF RAM AND KILLED HIS $200/MONTH CHATGPT SUBSCRIPTION 00:37 he points at the terminal, "loaded, loaded, loaded - 4 nodes synced over gigabit, 64 gigabytes total, llama 3.1 partitioned across the cluster" he stacked 4 raspberry pi CM5 lite modules with 16 gigabytes each onto a sipeed nanocluster board, the whole rig runs off a single 65 watt power supply and a gigabit internal switch distributed llama partitions the model across the nodes with synchronized workloads handled over the internal fabric, no quantization needed, the cluster hits about 30 tokens per second on small models a heavy developer pays $200 a month for chatgpt pro and another $200 for claude code, this rig cost €450 in parts and breaks even on the stack in month 2 most people will keep paying anthropic and openai forever, a few will spend a weekend wiring 4 raspberry pi modules and never see a subscription invoice again the window is open, follow and bookmark before it closes

Antid

64,077 views • 1 month ago

🚨 SOMETHING MASSIVE JUST LAUNCHED OVER LOS ANGELES — AND THE TIMING IS MAKING PEOPLE UNEASY No warning. No alert. Then this appeared over the city. A glowing object stretching across the sky… leaving behind a massive spiral cloud. Phones came out instantly. • “Jellyfish”-like shape hovering over LA • Expanding trail twisting across the sky • Seen across the city at once • No explanation in the moment Then word spread... it was a SpaceX launch. But the reaction didn’t slow down. With everything happening right now... war headlines, rising tensions, missile talk, seeing something like this over a major city hit different. The size. The shape. How long it stayed there. It wasn’t subtle. And for a lot of people watching… it didn’t feel routine. What's your first reaction seeing this in the sky?

🚨 SOMETHING MASSIVE JUST LAUNCHED OVER LOS ANGELES — AND THE TIMING IS MAKING PEOPLE UNEASY No warning. No alert. Then this appeared over the city. A glowing object stretching across the sky… leaving behind a massive spiral cloud. Phones came out instantly. • “Jellyfish”-like shape hovering over LA • Expanding trail twisting across the sky • Seen across the city at once • No explanation in the moment Then word spread... it was a SpaceX launch. But the reaction didn’t slow down. With everything happening right now... war headlines, rising tensions, missile talk, seeing something like this over a major city hit different. The size. The shape. How long it stayed there. It wasn’t subtle. And for a lot of people watching… it didn’t feel routine. What's your first reaction seeing this in the sky?

HustleBitch

1,007,088 views • 4 months ago