Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

DiffusionGemma-as-Jev (aka djev) running near-real-time vision detection from a mobile phone using its native vision tower. Please don't fall down the stairs!

Matt Mastracci

9,393 subscribers

104,402 Aufrufe • vor 17 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

15 Kommentare

Profilbild von Matt Mastracci

Matt Mastraccivor 17 Tagen

You can even try it yourself! This is the shipping docker container with a packaged server and examples:

Profilbild von Matt Mastracci

Matt Mastraccivor 17 Tagen

Each image is captured from the webcam, tokenized by the model, and the structured query gets answered by DiffusionGemma in about ~300-400ms. This is the stock DiffusionGemma model, no fine tuning, running practically stock vLLM with only a few patches.

Profilbild von Mike Petch

Mike Petchvor 17 Tagen

It didn't do very well identifying the owner of the house (the furry one). Pet????? I'm sure th cat has something to say about that ;-)

Profilbild von Inch

Inchvor 17 Tagen

it could be useful for blind

Profilbild von Richelle🧬

Richelle🧬vor 17 Tagen

We just shipped open weights jev:

Profilbild von Matt Mastracci

Matt Mastraccivor 17 Tagen

We should chat - would be great to share a single server implementation and make sure we align on multimodal Jev (mmJev?)! Feel free to reach out (DM or email)

Profilbild von Richelle🧬

Richelle🧬vor 17 Tagen

dm me!

Profilbild von JB

JBvor 17 Tagen

Was setting up a pipeline with YOLO26 + Jev but going to run this and compare.

Profilbild von Chalkers

Chalkersvor 17 Tagen

I’m going to put it in to my robot dog

Profilbild von johnny, INFINITE FUN ENTHUSIAST

johnny, INFINITE FUN ENTHUSIASTvor 17 Tagen

keep going, Matt!

Profilbild von unsever

unsevervor 17 Tagen

Please give it perception of depth and try this again I'll wait

Profilbild von Latent

Latentvor 17 Tagen

I have been following your posts since yesterday. Amazing

Profilbild von AD3 Digital Marketing

AD3 Digital Marketingvor 17 Tagen

Very cool but to big for my 12gb vram Ç_Ç

Profilbild von Simplicity

Simplicityvor 17 Tagen

Do you want T-800s? Because that's how you get T-800s.

Profilbild von ego

egovor 17 Tagen

I really need to know how much vram jev uses

Ähnliche Videos

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

David Villalón

43,078 Aufrufe • vor 16 Tagen

Successfully running Ultralytics YOLOv8 on a Jetson Nano with an IMX219 camera. Real-time vision on the edge.

Successfully running Ultralytics YOLOv8 on a Jetson Nano with an IMX219 camera. Real-time vision on the edge.

Yu Xiang

193,979 Aufrufe • vor 9 Monaten

Palmer Luckey’s new Eagle Eye helmet blends real time threat detection with enhanced vision tech, giving soldiers a sci fi level view of the battlefield.

Palmer Luckey’s new Eagle Eye helmet blends real time threat detection with enhanced vision tech, giving soldiers a sci fi level view of the battlefield.

Massimo

57,885 Aufrufe • vor 10 Monaten

The main event is coming to a phone near you as WWE 2K comes to mobile, exclusively on #NetflixGames later this Fall 2025 #NextOnNetflix

The main event is coming to a phone near you as WWE 2K comes to mobile, exclusively on #NetflixGames later this Fall 2025 #NextOnNetflix

Netflix Games

706,313 Aufrufe • vor 1 Jahr

reality is getting malleable. real girl dancing, the ai copies it perfectly. made this music video using a wan 2.2 animate workflow with native bf16 weights. the stack: • vision: ~200 base images via grok imagine • motion: wan 2.2 animate • pipeline: visual fision beat detection + pose control • music: suno + reaper

reality is getting malleable. real girl dancing, the ai copies it perfectly. made this music video using a wan 2.2 animate workflow with native bf16 weights. the stack: • vision: ~200 base images via grok imagine • motion: wan 2.2 animate • pipeline: visual fision beat detection + pose control • music: suno + reaper

tetsuo

22,240 Aufrufe • vor 9 Monaten

Starting today, the BMA is surveilling our borderline day and night using advanced drones flying as high as 7 000 meters at over 40km/h, equipped with night-vision, thermal detection and AI, while body cameras clamp down further on corruption. Digital transformation in action! 🇿🇦

Starting today, the BMA is surveilling our borderline day and night using advanced drones flying as high as 7 000 meters at over 40km/h, equipped with night-vision, thermal detection and AI, while body cameras clamp down further on corruption. Digital transformation in action! 🇿🇦

Leon Schreiber

263,899 Aufrufe • vor 1 Jahr

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

Max

10,537 Aufrufe • vor 8 Monaten

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

AA

72,731 Aufrufe • vor 7 Monaten

Check out this Circulus Pion robot at Computex 2026. It’s running on a Panther Lake processor, using P-cores for real-time control, E-cores to collect sensor data, the GPU for vision-language-action models, and the NPU for continuous perception.

Check out this Circulus Pion robot at Computex 2026. It’s running on a Panther Lake processor, using P-cores for real-time control, E-cores to collect sensor data, the GPU for vision-language-action models, and the NPU for continuous perception.

Intel Technology

10,752 Aufrufe • vor 4 Monaten

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.

UBTech Robotics has showcased its humanoid robot Walker S2 playing tennis with a human. Using real-time vision sensors, it tracks the ball, adjusts its position, and returns shots with good accuracy. The robot can also swap its own batteries, allowing it to operate continuously without human help.

Space and Technology

16,121 Aufrufe • vor 5 Monaten

Check out this guy wearing an Apple Vision using hand-tracking to control a robot in real time. Could this shift more jobs toward teleoperation in the future?

Check out this guy wearing an Apple Vision using hand-tracking to control a robot in real time. Could this shift more jobs toward teleoperation in the future?

Nathie

32,919 Aufrufe • vor 2 Jahren

Humanoid robots can play soccer using a new vision-driven controller, facilitating their victory at real world competitions such as the RoboCup 2025. Learn more in Science #Robotics:

Humanoid robots can play soccer using a new vision-driven controller, facilitating their victory at real world competitions such as the RoboCup 2025. Learn more in Science #Robotics:

Science Robotics

555,310 Aufrufe • vor 1 Monat

Step-3.7-Flash Q4_K_S on DGX Spark (GB10, 128GB): > ~27 tok/s generation > 198B sparse MoE, ~11B active > 256K context, native vision > Agentic / tool-calling / reasoning > Apache 2.0 I added a mobile chat screen on the right showing what 27 tok/s actually feels like streaming on a phone.

Step-3.7-Flash Q4_K_S on DGX Spark (GB10, 128GB): > ~27 tok/s generation > 198B sparse MoE, ~11B active > 256K context, native vision > Agentic / tool-calling / reasoning > Apache 2.0 I added a mobile chat screen on the right showing what 27 tok/s actually feels like streaming on a phone.

stevibe

19,658 Aufrufe • vor 4 Monaten

Vision Group shareholder Robert Gumede says their plans after rescuing Tongaat Hulett from liquidation are to diversify the business into an Agri-energy business. He says they don't want to keep it running only as a sugar business. Watch:

Vision Group shareholder Robert Gumede says their plans after rescuing Tongaat Hulett from liquidation are to diversify the business into an Agri-energy business. He says they don't want to keep it running only as a sugar business. Watch:

Newzroom Afrika

310,608 Aufrufe • vor 3 Monaten

Why not use the real-world as a game level? This is a real-time augmented reality prototype using a physics based character controller, all running on the web 👀

Why not use the real-world as a game level? This is a real-time augmented reality prototype using a physics based character controller, all running on the web 👀

Ian Curtis

533,419 Aufrufe • vor 3 Jahren

We don’t need a technocrat so much as we need a visionary. We need someone who appreciates that the vision of a country that belongs to its people rather than its corporations is the vision we should hold most dear and protect from all assault. We don’t need more political car mechanics; the problem is that we’re on the wrong road.

We don’t need a technocrat so much as we need a visionary. We need someone who appreciates that the vision of a country that belongs to its people rather than its corporations is the vision we should hold most dear and protect from all assault. We don’t need more political car mechanics; the problem is that we’re on the wrong road.

Marianne Williamson

14,453 Aufrufe • vor 2 Jahren