Loading video...

Video Failed to Load

Go Home

Introducing ✨ Aya Vision ✨ - an open-weights model to connect our world through language and vision Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿

Cohere_Labs's profile picture

Cohere Labs

27,416 subscribers

207,019 views • 1 year ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing ✨Aya Expanse ✨ – an open-weights state-of-art family of models to help close the language gap with AI. Aya Expanse is both global and local. Driven by a multi-year commitment to multilingual research.
0:15

Introducing ✨Aya Expanse ✨ – an open-weights state-of-art family of models to help close the language gap with AI. Aya Expanse is both global and local. Driven by a multi-year commitment to multilingual research.

Cohere Labs

239,950 views • 1 year ago

✨ Introducing the StratoVM Growth Campaign ✨ StratoVM is a Bitcoin-Aligned Layer 2 Solution. Our vision is to make DeFi on Bitcoin possible and accessible to everyone. Join the campaign: #StratoVM #BitcoinL2
0:15

✨ Introducing the StratoVM Growth Campaign ✨ StratoVM is a Bitcoin-Aligned Layer 2 Solution. Our vision is to make DeFi on Bitcoin possible and accessible to everyone. Join the campaign: #StratoVM #BitcoinL2

StratoVM | BTC Layer2

63,923 views • 2 years ago

We just shipped React Native ExecuTorch v0.8.0 – our biggest release yet! 👏🏼 ➡️ Vision Camera integration that runs computer vision models directly on your camera feed, in realtime. Also new: multiple CV models (including RF-DETR (Roboflow) and Liquid AI's Vision Language), Bare React Native support, and more. Takes minutes to try – check out the repo! ⬇️
0:12

We just shipped React Native ExecuTorch v0.8.0 – our biggest release yet! 👏🏼 ➡️ Vision Camera integration that runs computer vision models directly on your camera feed, in realtime. Also new: multiple CV models (including RF-DETR (Roboflow) and Liquid AI's Vision Language), Bare React Native support, and more. Takes minutes to try – check out the repo! ⬇️

Software Mansion

37,180 views • 6 months ago

Want to bring open-source vision language models to the edge? 💻 Check out our Hugging Face article on deploying NVIDIA Cosmos Reasoning 2B across the NVIDIA Jetson family with vLLM and a Live VLM WebUI. 📖
0:17

Want to bring open-source vision language models to the edge? 💻 Check out our Hugging Face article on deploying NVIDIA Cosmos Reasoning 2B across the NVIDIA Jetson family with vLLM and a Live VLM WebUI. 📖

NVIDIA Robotics

54,057 views • 7 months ago

Working on a new topic and hardware for a while: Feet Language Action models. VLAs teach robots to act through vision and language FLAs teach legged robots to act through contact Given a task, terrain, body state, and instruction - decide where, when, and how to make contact
0:18

Working on a new topic and hardware for a while: Feet Language Action models. VLAs teach robots to act through vision and language FLAs teach legged robots to act through contact Given a task, terrain, body state, and instruction - decide where, when, and how to make contact

Irvin (in Japan 🇯🇵)

14,015 views • 3 months ago

The eyes of the chameleon provide 360 degree vision due to unique eye anatomy and an ability to transition between monocular and binocular vision.
0:14

The eyes of the chameleon provide 360 degree vision due to unique eye anatomy and an ability to transition between monocular and binocular vision.

Nature is Amazing ☘️

2,582,803 views • 2 years ago

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.
0:12

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.

AI at Meta

195,673 views • 1 year ago

What comes after vision-language-action models in robotics? 🤖 Join NVIDIA researchers live to explore World Action Models (WAMs), Vision-Language-Action models (VLAs), and hybrid robot foundation models, and see how NVIDIA Cosmos 3 natively represents action alongside video. 🕑 Thursday, Aug. 13 • 9:00–10:00 a.m. PT 📅Add calendar:
0:15

What comes after vision-language-action models in robotics? 🤖 Join NVIDIA researchers live to explore World Action Models (WAMs), Vision-Language-Action models (VLAs), and hybrid robot foundation models, and see how NVIDIA Cosmos 3 natively represents action alongside video. 🕑 Thursday, Aug. 13 • 9:00–10:00 a.m. PT 📅Add calendar:

NVIDIA Robotics

12,659 views • 2 months ago

>they’ve read him and genuinely want his vision of the world to become a reality And what a beautiful vision it is
0:18

>they’ve read him and genuinely want his vision of the world to become a reality And what a beautiful vision it is

Anti-kun🌹🇮🇶☀️

11,518 views • 29 days ago

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang
0:11

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

LeRobot

25,163 views • 4 months ago

Gemma 4 is here! Our most intelligent open models to date, are built on the same world-class research and tech as Gemini 3, and are sized to run and fine-tune efficiently on local hardware. Check out what Google Gemma 4 brings to devs: 💎 Advanced Reasoning: Deep logic tasks, complex multi-step planning, and beyond 💎 Longer context: Seamlessly analyze entire codebases with context windows of 128K tokens for our edge models and 256K tokens for our largest models 💎 Vision and audio: Rich, multimodal interactions out of the box 💎 140+ languages: Trained on 140+ languages 💎 Apache 2.0 license: industry-standard open-source license
0:19

Gemma 4 is here! Our most intelligent open models to date, are built on the same world-class research and tech as Gemini 3, and are sized to run and fine-tune efficiently on local hardware. Check out what Google Gemma 4 brings to devs: 💎 Advanced Reasoning: Deep logic tasks, complex multi-step planning, and beyond 💎 Longer context: Seamlessly analyze entire codebases with context windows of 128K tokens for our edge models and 256K tokens for our largest models 💎 Vision and audio: Rich, multimodal interactions out of the box 💎 140+ languages: Trained on 140+ languages 💎 Apache 2.0 license: industry-standard open-source license

Google for Developers

270,290 views • 6 months ago

DeepSeek was developed for under $6 million. ChatGPT spent $6 billion. The difference was an algorithmic breakthrough. TIG is home to DeepSeek-level breakthroughs across all of science. And today, we're unveiling our new vision for accelerating algorithmic innovation worldwide. The future of open science starts today ↓
0:16

DeepSeek was developed for under $6 million. ChatGPT spent $6 billion. The difference was an algorithmic breakthrough. TIG is home to DeepSeek-level breakthroughs across all of science. And today, we're unveiling our new vision for accelerating algorithmic innovation worldwide. The future of open science starts today ↓

The Innovation Game (𝔦, 𝔦)

12,924 views • 1 year ago

✨#PortfolioDay 2025✨ Hi, we’re Deco and Niina (Niina🌸 ) ! Together, we bring your vision to life with custom designs and animations for logos, streaming assets, and more 💕 Contact us through DM 📩or check out our VGen! #DecoplumComms
0:26

✨#PortfolioDay 2025✨ Hi, we’re Deco and Niina (Niina🌸 ) ! Together, we bring your vision to life with custom designs and animations for logos, streaming assets, and more 💕 Contact us through DM 📩or check out our VGen! #DecoplumComms

Decoplum 🎨 COMMS OPEN ✨

10,931 views • 1 year ago

Time to lift the veil. We’ve been building quietly so far: designing, iterating, and aligning every piece of the puzzle. Now, you get to see the full picture through our vision paper. Understand our purpose:
0:12

Time to lift the veil. We’ve been building quietly so far: designing, iterating, and aligning every piece of the puzzle. Now, you get to see the full picture through our vision paper. Understand our purpose:

OVERTAKE

119,351 views • 1 year ago

Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding. • Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure. • Available to all via API today. Working with cybersecurity partners privately. Open weights release end of October.
0:17

Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding. • Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure. • Available to all via API today. Working with cybersecurity partners privately. Open weights release end of October.

Mistral AI

5,502,112 views • 2 days ago

Day one at KBW was a big win for OVERTAKE. Huge thanks to Adeniyi.sui from Sui for presenting our story on stage. It was the perfect moment to share our vision and connect with the community.
0:17

Day one at KBW was a big win for OVERTAKE. Huge thanks to Adeniyi.sui from Sui for presenting our story on stage. It was the perfect moment to share our vision and connect with the community.

OVERTAKE

16,164 views • 1 year ago

▇▄▋▋▎ ONTOS is our most ambitious game to date, both in terms of its size and scale, and in the depth and layers of our story and gameplay. In order to deliver this vision, we have decided to push the release of ONTOS to 2027. We look forward to sharing more updates about ONTOS, our characters, and our world soon. ▔█▌▄ █▒ ▀ ▂▎ ▍▒▔░▕▂▔
0:14

▇▄▋▋▎ ONTOS is our most ambitious game to date, both in terms of its size and scale, and in the depth and layers of our story and gameplay. In order to deliver this vision, we have decided to push the release of ONTOS to 2027. We look forward to sharing more updates about ONTOS, our characters, and our world soon. ▔█▌▄ █▒ ▀ ▂▎ ▍▒▔░▕▂▔

ONTOS

66,925 views • 3 months ago