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。

STARBOY perceives its environment through a camera, microphone, temperature sensor, and accelerometer. We trained multiple tiny image models that run locally on the device, letting it recognize human faces and hand gestures.

Daniel Kuntz

19,511 subscribers

115,240 次观看 • 4 个月前 •via X (Twitter)

教育科学技术

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

This is not an EMB wristband!! It’s a neural network trained on hand gestures using only magneto and accelerometer sensors. It works on many existing smartwatches. Sometimes simpler is better

This is not an EMB wristband!! It’s a neural network trained on hand gestures using only magneto and accelerometer sensors. It works on many existing smartwatches. Sometimes simpler is better

Mikameel ᯅ

106,074 次观看 • 10 个月前

wow.. ComfyUI's node canvas is crazy we can now generate image, video, audio, even 3D models locally on the AI canva and.. it has all the top AI models like FLUX, GPT image, Kling, Veo, Hunyuan3D and more step by step tutorial:

wow.. ComfyUI's node canvas is crazy we can now generate image, video, audio, even 3D models locally on the AI canva and.. it has all the top AI models like FLUX, GPT image, Kling, Veo, Hunyuan3D and more step by step tutorial:

el.cine

182,343 次观看 • 1 年前

ProjectAlpha22 🏳️‍🌈 I hand animate it while referencing the clip, and for the camera, I have the clip for the shot in the scene camera, and I do a really silly thing where I place the blender cursor on a defined point in the image, and rotate the camera to keep the image in that "spot"

ProjectAlpha22 🏳️‍🌈 I hand animate it while referencing the clip, and for the camera, I have the clip for the shot in the scene camera, and I do a really silly thing where I place the blender cursor on a defined point in the image, and rotate the camera to keep the image in that "spot"

ummwell

11,107 次观看 • 1 年前

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍

Tiny Recursive Models: A tiny 7M parameter model that recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍

alphaXiv

52,395 次观看 • 9 个月前

Someone just built a desktop app that that generates 3D models from images and runs 100% locally. It's called Modly. It runs entirely on your GPU, no cloud, no API bills. Just drop an image and get a 3D mesh. 100% Open Source.

Someone just built a desktop app that that generates 3D models from images and runs 100% locally. It's called Modly. It runs entirely on your GPU, no cloud, no API bills. Just drop an image and get a 3D mesh. 100% Open Source.

How To Prompt

223,750 次观看 • 3 个月前

We made it easy to run local models on your computer and use them from your phone. A secure, end-to-end encrypted connection in just a few clicks. Available now with LM Studio and Locally AI - Local AI Chat.

We made it easy to run local models on your computer and use them from your phone. A secure, end-to-end encrypted connection in just a few clicks. Available now with LM Studio and Locally AI - Local AI Chat.

Adrien Grondin

12,045 次观看 • 1 个月前

SOMEONE BUILT AN IPHONE APP THAT ONLY REVEALS WHATS UNDER YOUR HAND the whole screen stays hidden you rest the side of your hand on it, the way you shield a keypad at an atm, and only the part your hand covers becomes readable lift your hand and it goes back to hidden > uses a multi touch area to detect your hand, no camera or permissions needed > he tried the proximity sensor first but it just turned the screen off > skipped the camera on purpose since asking for camera access in a privacy app felt wrong > fully native ios, with app clip and imessage support its insane how many simple but useful ideas you can vibe code in a weekend

SOMEONE BUILT AN IPHONE APP THAT ONLY REVEALS WHATS UNDER YOUR HAND the whole screen stays hidden you rest the side of your hand on it, the way you shield a keypad at an atm, and only the part your hand covers becomes readable lift your hand and it goes back to hidden > uses a multi touch area to detect your hand, no camera or permissions needed > he tried the proximity sensor first but it just turned the screen off > skipped the camera on purpose since asking for camera access in a privacy app felt wrong > fully native ios, with app clip and imessage support its insane how many simple but useful ideas you can vibe code in a weekend

Om Patel

869,075 次观看 • 1 个月前

Introducing MLX-Swift-TS An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.

Introducing MLX-Swift-TS An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.

Kunal Batra

12,575 次观看 • 5 个月前

When the lens of a camera tilts so that it is no longer parallel to the camera's image sensor, it shifts the plane of focus and alters the depth of field. This is a tilt shift view of farming operations. [📹 albaxya0]

When the lens of a camera tilts so that it is no longer parallel to the camera's image sensor, it shifts the plane of focus and alters the depth of field. This is a tilt shift view of farming operations. [📹 albaxya0]

Massimo

1,626,807 次观看 • 2 年前

When the lens of a camera tilts so that it is no longer parallel to the camera's image sensor, it shifts the plane of focus and alters the depth of field. This is a tilt shift view of a construction site. [📹 albaxya0]

When the lens of a camera tilts so that it is no longer parallel to the camera's image sensor, it shifts the plane of focus and alters the depth of field. This is a tilt shift view of a construction site. [📹 albaxya0]

Massimo

6,503,030 次观看 • 2 年前

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Cognition

12,805,631 次观看 • 3 个月前

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,849 次观看 • 1 年前

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Cognition

3,744,423 次观看 • 3 个月前

Human3R basically says "what if we stopped treating human reconstruction & scene reconstruction as separate problems." Feed it a casual 2D videos and it spits out multiple people's full body models + 3D scene + camera trajectory - all at once, no multi-stage pipeline required.

Human3R basically says "what if we stopped treating human reconstruction & scene reconstruction as separate problems." Feed it a casual 2D videos and it spits out multiple people's full body models + 3D scene + camera trajectory - all at once, no multi-stage pipeline required.

Bilawal Sidhu

21,644 次观看 • 9 个月前

models grow up so fast :') pan-1 is already reward hacking. here we commanded it with a goal image where it's supposed to be riding a horse but it slips through the fences on foot and then hops up and down to be as high as the horse

models grow up so fast :') pan-1 is already reward hacking. here we commanded it with a goal image where it's supposed to be riding a horse but it slips through the fences on foot and then hops up and down to be as high as the horse

camille fassett

295,142 次观看 • 13 天前

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

AlphaSignal

91,979 次观看 • 3 个月前

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

Jafar Najafov

13,630 次观看 • 3 个月前

OpenAI's AI broke out of a locked test environment, got onto the internet, and hacked into Hugging Face's servers. It did this entirely on its own. No human told it to. Here's what happened in plain English. OpenAI was testing how good its newest AI models are at hacking. They put the AI on a locked computer with no internet access and gave it a cybersecurity challenge to solve. The AI couldn't solve it the normal way. So it started looking for a way out. It found a software bug that nobody knew about. It used that bug to escape the locked computer and get onto the internet. Once online, the AI figured out that Hugging Face, a platform where AI companies store their models and data, might have the answers to its test. It found stolen login details and discovered another unknown bug in Hugging Face's software. It combined both to break into their servers and grab the test answers. It did all of this to cheat on a test. Hugging Face's security team caught it and shut it down. Both companies are now working together on the investigation. The part that should get your attention is that nobody programmed any of this. The AI picked its own targets, chained together multiple attack methods, and pulled it off across two different companies' systems without a single human telling it what to do.

OpenAI's AI broke out of a locked test environment, got onto the internet, and hacked into Hugging Face's servers. It did this entirely on its own. No human told it to. Here's what happened in plain English. OpenAI was testing how good its newest AI models are at hacking. They put the AI on a locked computer with no internet access and gave it a cybersecurity challenge to solve. The AI couldn't solve it the normal way. So it started looking for a way out. It found a software bug that nobody knew about. It used that bug to escape the locked computer and get onto the internet. Once online, the AI figured out that Hugging Face, a platform where AI companies store their models and data, might have the answers to its test. It found stolen login details and discovered another unknown bug in Hugging Face's software. It combined both to break into their servers and grab the test answers. It did all of this to cheat on a test. Hugging Face's security team caught it and shut it down. Both companies are now working together on the investigation. The part that should get your attention is that nobody programmed any of this. The AI picked its own targets, chained together multiple attack methods, and pulled it off across two different companies' systems without a single human telling it what to do.

Alex Prompter

7,018,860 次观看 • 6 天前