Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Google just released PaliGemma 2 Mix: new versatile instruction vision language models 🔥 > Three new models: 3B, 10B, 28B with res 224, 448 💙 > Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything 🤯

mervenoyann's profile picture

merve

88,374 subscribers

83,712 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von merve
mervevor 1 Jahr

All models and the demo are here 🤝 Read our blog to learn more 📚

Profilbild von merve
mervevor 1 Jahr

@onuralpszr this might interest you!

Profilbild von Quantify Funds
Quantify Fundsvor 1 Jahr

Watch this space for the reveal 👀 BIG NEWS: Our family of ETFs is expanding with 10 new single stock offerings. Read the pre-effective prospectus @ #STKd #QuantifyFunds #QuantifyChaos #Nasdaq #ETFs

Profilbild von ondevice
ondevicevor 1 Jahr

love how, usually when we come across something from google, we usually see demos rather than just academic benchmarks thanks team! love this @DynamicWebPaige @OfficialLoganK @AarushSelvan

Profilbild von lambda
lambdavor 1 Jahr

openAI should take notes. Even google is open sourcing

Profilbild von merve
mervevor 1 Jahr

google has been open sourcing since early times and for a long while actually

Profilbild von nonc3ai
nonc3aivor 1 Jahr

Great news, 3B should be small enough to run on a phone, right?

Profilbild von merve
mervevor 1 Jahr

if you quantize, yes ☺️

Profilbild von Arpit Sharma
Arpit Sharmavor 1 Jahr

AI that sees, understands, and segments. Impressive!

Profilbild von Matthew Rogers
Matthew Rogersvor 1 Jahr

I want to scan my mail, lets go!

Profilbild von Furkan Gözükara
Furkan Gözükaravor 1 Jahr

Why res is still to low?

Ähnliche Videos

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.
0:38

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

AI at Meta

121,530 Aufrufe • vor 1 Jahr

Google released its new Gemini Robotics AI platform. It can take natural language instructions and uses vision AI to complete tasks that require dexterity: ▫️Folding origami ▫️Toy organization ▫️Packing lunches
0:14

Google released its new Gemini Robotics AI platform. It can take natural language instructions and uses vision AI to complete tasks that require dexterity: ▫️Folding origami ▫️Toy organization ▫️Packing lunches

Bearly AI

16,616 Aufrufe • vor 1 Jahr

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]
0:25

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,447 Aufrufe • vor 1 Jahr

Introducing ♾OmniJARVIS, our latest venture to #AgentGPT, or vision-language-action (VLA) models for open-world instruction-following agents 🦾🕹️ tuning in 👉 by Team CraftJarvis, 🤿⏬
2:16

Introducing ♾OmniJARVIS, our latest venture to #AgentGPT, or vision-language-action (VLA) models for open-world instruction-following agents 🦾🕹️ tuning in 👉 by Team CraftJarvis, 🤿⏬

Xiaojian Ma

32,550 Aufrufe • vor 2 Jahren

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇
1:39

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Sergey Levine

30,388 Aufrufe • vor 2 Jahren

🔓Unlock the power of multimodal AI with PaliGemma and Keras! Keras software engineer Varun Singh gave an inside look at how PaliGemma works to solve language and computer vision tasks and how to leverage Keras for streamlined development. Watch →
0:53

🔓Unlock the power of multimodal AI with PaliGemma and Keras! Keras software engineer Varun Singh gave an inside look at how PaliGemma works to solve language and computer vision tasks and how to leverage Keras for streamlined development. Watch →

Google for Developers

33,742 Aufrufe • vor 1 Jahr

Google released MedGemma on I/O'25 👏 > 4B and 27B instruction fine-tuned vision LMs and a 4B pre-trained vision LM for medicine > available with transformers from the get-go 🤗 they also released a cool demo for scan reading ⤵️
0:25

Google released MedGemma on I/O'25 👏 > 4B and 27B instruction fine-tuned vision LMs and a 4B pre-trained vision LM for medicine > available with transformers from the get-go 🤗 they also released a cool demo for scan reading ⤵️

merve

81,353 Aufrufe • vor 1 Jahr

Andrej Karpathy calls large language models the new computing paradigm: CPU -> LLM bytes -> tokens RAM -> context window this is the large language model OS (LMOS)
0:55

Andrej Karpathy calls large language models the new computing paradigm: CPU -> LLM bytes -> tokens RAM -> context window this is the large language model OS (LMOS)

ℏεsam

343,327 Aufrufe • vor 1 Jahr

New tiny VLM: LFM2.5-VL-450M > Supports bounding box prediction, object detection, and function calling > Improved multilingual capabilities across 9 languages > Enhanced instruction following for vision and text tasks
1:14

New tiny VLM: LFM2.5-VL-450M > Supports bounding box prediction, object detection, and function calling > Improved multilingual capabilities across 9 languages > Enhanced instruction following for vision and text tasks

Maxime Labonne

32,092 Aufrufe • vor 3 Monaten

GPT-4o level intelligence running on your phone! MiniCPM-V 4.5 delivers enterprise-grade AI performance in just 8B parameters, outperforming models like GPT-4o, Gemini-2.0 Pro on vision and language tasks. - 30+ language support - Runs smoothly on iPhone/iPad 100% open-source!
0:28

GPT-4o level intelligence running on your phone! MiniCPM-V 4.5 delivers enterprise-grade AI performance in just 8B parameters, outperforming models like GPT-4o, Gemini-2.0 Pro on vision and language tasks. - 30+ language support - Runs smoothly on iPhone/iPad 100% open-source!

Akshay 🚀

84,288 Aufrufe • vor 10 Monaten

VLAExplain — Interpreting Vision-Language-Action (VLA) Models VLAExplain is an interpretability toolkit designed to help users visually understand the inner workings of Vision-Language-Action (VLA) models. Currently, attention analysis is supported for both the pi05 and unifolm-vla models. For details, please check pi05 and UnifoLM-VLA readme files respectively. Demo of pi05 in action:
0:28

VLAExplain — Interpreting Vision-Language-Action (VLA) Models VLAExplain is an interpretability toolkit designed to help users visually understand the inner workings of Vision-Language-Action (VLA) models. Currently, attention analysis is supported for both the pi05 and unifolm-vla models. For details, please check pi05 and UnifoLM-VLA readme files respectively. Demo of pi05 in action:

Ryohei Sasaki@engineer

12,774 Aufrufe • vor 2 Monaten

What happens when you combine voice, vision, and reasoning on-device? 🤔 Gemma 4 + a vision-language agent (VLA) running on NVIDIA Jetson Orin Nano shows how compact hardware can now handle real-world AI tasks using today’s open models—no cloud required. Get started:
1:50

What happens when you combine voice, vision, and reasoning on-device? 🤔 Gemma 4 + a vision-language agent (VLA) running on NVIDIA Jetson Orin Nano shows how compact hardware can now handle real-world AI tasks using today’s open models—no cloud required. Get started:

NVIDIA Robotics

25,655 Aufrufe • vor 2 Monaten

Yay, finally! Introducing Vision Banana🍌 from Google DeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: (1/5)
0:25

Yay, finally! Introducing Vision Banana🍌 from Google DeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: (1/5)

Songyou Peng

285,984 Aufrufe • vor 2 Monaten

Introducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks. Learn more about how PLM can help the open source community build more capable computer vision systems. Read the research paper, and download the code and dataset:
1:11

Introducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks. Learn more about how PLM can help the open source community build more capable computer vision systems. Read the research paper, and download the code and dataset:

AI at Meta

94,330 Aufrufe • vor 1 Jahr

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source
0:21

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source

Sumanth

43,704 Aufrufe • vor 10 Monaten

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.
0:45

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

The Humanoid Hub

20,458 Aufrufe • vor 1 Jahr

Introducing → CodecFlow @CodecOpenFlow offers agent first infra powered by vision language models, making robotics and desktop operators simple Agents spin up compute, run models, and build autonomously with payments via x402 on @Solana 🔗
0:40

Introducing → CodecFlow @CodecOpenFlow offers agent first infra powered by vision language models, making robotics and desktop operators simple Agents spin up compute, run models, and build autonomously with payments via x402 on @Solana 🔗

Superteam UAE

33,841 Aufrufe • vor 3 Monaten

Physical Intelligence's π₀, a general-purpose robot foundation model that combines Internet-scale vision-language pretraining with robot interaction data to execute tasks. They aim "to develop foundation models that can control any robot to perform any task" Autonomous demos:
3:36

Physical Intelligence's π₀, a general-purpose robot foundation model that combines Internet-scale vision-language pretraining with robot interaction data to execute tasks. They aim "to develop foundation models that can control any robot to perform any task" Autonomous demos:

The Humanoid Hub

196,055 Aufrufe • vor 1 Jahr

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from
1:43

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

AK

85,570 Aufrufe • vor 2 Jahren

i trained a computer vision model to count chinups roboflow rapid + SAM3 detected the chinup bar - hands - head through natural language prompts then I wrote a python script to count completed reps (head above bar) and annotate the video idea for a gamified fitness app? automated tracking of your workout, with rep counts per exercise added to your database. this gives progress stats over time, and a leaderboard with your friends these new vision models are neat because they can detect exercise equipment, allowing tracking of dumbbell workouts, bench press, squat, etc.
0:30

i trained a computer vision model to count chinups roboflow rapid + SAM3 detected the chinup bar - hands - head through natural language prompts then I wrote a python script to count completed reps (head above bar) and annotate the video idea for a gamified fitness app? automated tracking of your workout, with rep counts per exercise added to your database. this gives progress stats over time, and a leaderboard with your friends these new vision models are neat because they can detect exercise equipment, allowing tracking of dumbbell workouts, bench press, squat, etc.

AA

1,180,355 Aufrufe • vor 7 Monaten