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。

Meet Reka Core, our best and most capable multimodal language model yet. 🔮 It’s been a busy few months training this model and we are glad to finally ship it! 💪 Core has a lot of capabilities, and one of them is understanding video --- let’s see what Core... show more

Reka

19,929 subscribers

757,957 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Reka 的头像

Reka2 年前

We evaluate Core on standard benchmarks for both text and multimodal, along with a blind third-party human evaluation.

Reka 的头像

Reka2 年前

Along with Core, we have published a technical report detailing the training, architecture, data, and evaluation for the Reka models.

Reka 的头像

Reka2 年前

See some examples of outputs from Core in or try it yourself on

Reka 的头像

Reka2 年前

Check out the blogpost for more details.

dmitriy 的头像

dmitriy2 年前

Please familiarize it with big chungus

Matt Henderson 的头像

Matt Henderson2 年前

Flash to Core in two months! 📈

sridhar 的头像

sridhar2 年前

Congratulations, @DaniYogatama and @RekaAILabs team!!

Ben (e/treats) 的头像

Ben (e/treats)2 年前

congrats!!! please add pricing to your pricing page 👀 it's just a form right now

Reka 的头像

Reka2 年前

It's a bug and we are fixing it. Currently, Core is 10 bucks per million input tokens and 25 bucks per million output tokens.

djcows 的头像

djcows2 年前

nice. however, one small issue, no submariner

相关视频

Today we’re taking a big step on the path toward AGI and releasing Gemini 3— our most intelligent model yet. With Gemini 3, you can bring any idea to life. It is state-of-the-art in reasoning, the best model in the world for multimodal understanding, and our best agentic and vibe coding model.

Today we’re taking a big step on the path toward AGI and releasing Gemini 3— our most intelligent model yet. With Gemini 3, you can bring any idea to life. It is state-of-the-art in reasoning, the best model in the world for multimodal understanding, and our best agentic and vibe coding model.

Google AI

492,917 次观看 • 8 个月前

Start building with Gemini 3 Pro, our most intelligent model with state-of-the-art reasoning and complex multimodal understanding, as well as powerful agentic and vibe coding capabilities. See more below:

Start building with Gemini 3 Pro, our most intelligent model with state-of-the-art reasoning and complex multimodal understanding, as well as powerful agentic and vibe coding capabilities. See more below:

Google AI Developers

104,898 次观看 • 8 个月前

This is Gemini 3: our most intelligent model that helps you learn, build and plan anything. It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵

This is Gemini 3: our most intelligent model that helps you learn, build and plan anything. It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵

Google DeepMind

1,693,548 次观看 • 8 个月前

Gemini 3 Pro is the best model in the world for multimodal understanding. One of its most exciting capabilities is document understanding and reasoning. This means you can convert information in any format and into the medium that works best for you. Gemini 3 also has leading multilingual capabilities, enabling it to process, reason and even capture cultural relevance across a variety of languages. For example, here Gemini 3 is translating handwritten recipes in Korean and English to build a digital family cookbook in different languages.

Gemini 3 Pro is the best model in the world for multimodal understanding. One of its most exciting capabilities is document understanding and reasoning. This means you can convert information in any format and into the medium that works best for you. Gemini 3 also has leading multilingual capabilities, enabling it to process, reason and even capture cultural relevance across a variety of languages. For example, here Gemini 3 is translating handwritten recipes in Korean and English to build a digital family cookbook in different languages.

Google AI

36,696 次观看 • 8 个月前

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

AK

23,958 次观看 • 1 年前

#WATCH | Mumbai | NCP Leader Zeeshan Siddique says, "Our core committee meeting under the leadership of Sunil Tatkare has just ended. We discussed a lot of things. NCP will contest on a lot of seats throughout Mumbai, and we are very capable of contesting alone. Our party workers are ready, and Mumbai's Mayor will be from the NCP..."

#WATCH | Mumbai | NCP Leader Zeeshan Siddique says, "Our core committee meeting under the leadership of Sunil Tatkare has just ended. We discussed a lot of things. NCP will contest on a lot of seats throughout Mumbai, and we are very capable of contesting alone. Our party workers are ready, and Mumbai's Mayor will be from the NCP..."

ANI

24,558 次观看 • 7 个月前

Sec. Rubio: “What the President has done is he has, number one, he defines what's in the core national interest to the United States. There's a lot of terrible things happening in the world. Not all of them are at our core national interest. Number two, he defines what the outcome he wants. And number three, he takes actions that are very specific and limited to getting the outcome that’s good for our country.”

Sec. Rubio: “What the President has done is he has, number one, he defines what's in the core national interest to the United States. There's a lot of terrible things happening in the world. Not all of them are at our core national interest. Number two, he defines what the outcome he wants. And number three, he takes actions that are very specific and limited to getting the outcome that’s good for our country.”

Breaking911

22,483 次观看 • 7 个月前

.Secretary of War Pete Hegseth “Today, we are undertaking a Department-wide transformation of requirements, acquisition and foreign military sales. Addressing a core function of what we do at the War Department. Identifying what our war fighters need, how we buy those capabilities, and how we share those capabilities with our allies and partners.”

.Secretary of War Pete Hegseth “Today, we are undertaking a Department-wide transformation of requirements, acquisition and foreign military sales. Addressing a core function of what we do at the War Department. Identifying what our war fighters need, how we buy those capabilities, and how we share those capabilities with our allies and partners.”

DOW Rapid Response

223,654 次观看 • 8 个月前

After a couple successful limited runs, the DGT Semi-Hollow is officially being added to the PRS Core lineup! This new model offers the unique character of a semi-hollow body while carrying over the features you know and love from the Core DGT.

After a couple successful limited runs, the DGT Semi-Hollow is officially being added to the PRS Core lineup! This new model offers the unique character of a semi-hollow body while carrying over the features you know and love from the Core DGT.

PRS Guitars

11,527 次观看 • 6 个月前

"I think we'll get a lot more...incisive feedback that cuts to the core of what we're doing, and we are totally ready for it." What are your first impressions of #2XKO_AlphaLab?

"I think we'll get a lot more...incisive feedback that cuts to the core of what we're doing, and we are totally ready for it." What are your first impressions of #2XKO_AlphaLab?

Evo

34,885 次观看 • 1 年前

.Secretary Marco Rubio: “What the President has done is he has, number one, he defines what's in the core national interest to the United States. There's a lot of terrible things happening in the world. Not all of them are at our core national interest. Number two, he defines what the outcome he wants. And number three, he takes actions that are very specific and limited to getting the outcome that’s good for our country.”

.Secretary Marco Rubio: “What the President has done is he has, number one, he defines what's in the core national interest to the United States. There's a lot of terrible things happening in the world. Not all of them are at our core national interest. Number two, he defines what the outcome he wants. And number three, he takes actions that are very specific and limited to getting the outcome that’s good for our country.”

Department of State

207,140 次观看 • 7 个月前

“ xAI team is currently working heavily on coding models. Right now, the main focus is training a specialized coding model that will be both fast and smart. I believe we’ll share it with you guys in a few weeks. That’s exciting. Second ,after coding, we all see that the main weakness of Grok 4 is its multimodal capabilities. In fact, it was so bad that Grok was effectively looking at the world while squinting through glass trying to see blurry features and make sense of them. The most immediate improvement we’re stepping on with the next generation pre trained model is huge gains in image understanding, video understanding, and audio. Right now, the model can hear and see the world just like any of you. And with all the tools and other agents it can talk to, we’re going to see a huge unlock for many different application layers once multimodal agents arrive.” — xAI Team

“ xAI team is currently working heavily on coding models. Right now, the main focus is training a specialized coding model that will be both fast and smart. I believe we’ll share it with you guys in a few weeks. That’s exciting. Second ,after coding, we all see that the main weakness of Grok 4 is its multimodal capabilities. In fact, it was so bad that Grok was effectively looking at the world while squinting through glass trying to see blurry features and make sense of them. The most immediate improvement we’re stepping on with the next generation pre trained model is huge gains in image understanding, video understanding, and audio. Right now, the model can hear and see the world just like any of you. And with all the tools and other agents it can talk to, we’re going to see a huge unlock for many different application layers once multimodal agents arrive.” — xAI Team

Apurv Kochara

88,142 次观看 • 5 个月前

the way this video is so specific in one of my core memories of them…. i rememberSO VIVIDLY when this dropped and how insane it was that we got a larry interaction like this….

the way this video is so specific in one of my core memories of them…. i rememberSO VIVIDLY when this dropped and how insane it was that we got a larry interaction like this….

leeee ✴︎☽

33,427 次观看 • 1 个月前

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

Akshay 🚀

66,088 次观看 • 6 个月前

It’s been 3 months of cute chaos 🏕️ So, allow us to reintroduce ourselves. Fugz isn’t just another PFP project. It is the core and chaotic soul of a global IP that we are building in partnership with an elite animation Studio, Tokoto Studio. So let's dive in 👇

It’s been 3 months of cute chaos 🏕️ So, allow us to reintroduce ourselves. Fugz isn’t just another PFP project. It is the core and chaotic soul of a global IP that we are building in partnership with an elite animation Studio, Tokoto Studio. So let's dive in 👇

Fugz

14,754 次观看 • 11 个月前

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

Robby Stein

94,877 次观看 • 8 个月前

The infrastructure most people never see… but it matters. Licensing, compliance, and regulatory alignment sit at the core of everything we build. Watch the full video 👇

The infrastructure most people never see… but it matters. Licensing, compliance, and regulatory alignment sit at the core of everything we build. Watch the full video 👇

xMoney.com

2,398,761 次观看 • 2 个月前