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。

Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment:

OpenAI

5,038,359 subscribers

12,467,261 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

OpenAI 的头像

OpenAI3 年前

Join us at 1 pm PT today for a developer demo livestream showing GPT-4 and its capabilities/limitations: (comments in Discord:

Delysium - $AGI 🟨 的头像

Delysium - $AGI 🟨3 年前

Speaking of breakthroughs - here's the biggest one in #Web3

Lex Fridman 的头像

Lex Fridman3 年前

This is awesome! 🤯

Nick Massian 的头像

Nick Massian3 年前

This all sounds great, but why don’t you make it unbiased? It’s very left leaning.

Ali 的头像

Ali3 年前

I was hype for it until i saw "GPT-4 is 82% less likely to respond to requests for disallowed content"

Harrison Kinsley 的头像

Harrison Kinsley3 年前

Multi-modal is very interesting. The training data used for models like this becomes more and more general. Getting closer to "one model to rule them all."

Jason Wei 的头像

Jason Wei3 年前

This example of a pirate explaining taxes in the style of shakespeare indicates so many levels of compositionality. The qualitative experience of GPT-4 is remarkable and will unlock a world of new use cases!

Steev 的头像

Steev3 年前

“82% less likely to respond to requests for disallowed content” - huge red flag. Who gets to decide what’s disallowed? Hopefully this costs you the leadership position as someone else releases a model that’s not nerfed in an arbitrary way.

Neville's Toad 的头像

Neville's Toad3 年前

Does safer mean bias

Yiğit Konur 的头像

Yiğit Konur3 年前

In case you are looking for a summary, I've already created a 'human-curated' thread here 👇🏽

相关视频

🚀Introducing LLaVA Lightning: Train a lite, multimodal GPT-4 with just $40 in 3 hours! With our newly introduced datasets and the efficient design of LLaVA, you can now turbocharge your language model with image reasoning capabilities, in an incredibly affordable way.🧵

🚀Introducing LLaVA Lightning: Train a lite, multimodal GPT-4 with just $40 in 3 hours! With our newly introduced datasets and the efficient design of LLaVA, you can now turbocharge your language model with image reasoning capabilities, in an incredibly affordable way.🧵

Haotian Liu

302,319 次观看 • 3 年前

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,650,229 次观看 • 2 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

According to Microsoft, GPT-4 is set to launch this coming week. Here's why its rumored multimodal capabilities are a game-changer:

According to Microsoft, GPT-4 is set to launch this coming week. Here's why its rumored multimodal capabilities are a game-changer:

Eluna AI

10,588 次观看 • 3 年前

Let's go hands-on with #GeminiAI. Our newest AI model can reason across different types of inputs and outputs — like images and text. See Gemini's multimodal reasoning capabilities in action ↓

Let's go hands-on with #GeminiAI. Our newest AI model can reason across different types of inputs and outputs — like images and text. See Gemini's multimodal reasoning capabilities in action ↓

Google

1,005,910 次观看 • 2 年前

Introducing GPT-Rosalind, our frontier reasoning model built to support research across biology, drug discovery, and translational medicine.

Introducing GPT-Rosalind, our frontier reasoning model built to support research across biology, drug discovery, and translational medicine.

OpenAI

2,342,547 次观看 • 3 个月前

Live audience request for GPT-4o vision capabilities

Live audience request for GPT-4o vision capabilities

OpenAI

628,932 次观看 • 2 年前

Today we’re releasing a research preview of GPT-4.5—our largest and best model for chat yet. Rolling out now to all ChatGPT Pro users, followed by Plus and Team users next week, then Enterprise and Edu users the following week.

Today we’re releasing a research preview of GPT-4.5—our largest and best model for chat yet. Rolling out now to all ChatGPT Pro users, followed by Plus and Team users next week, then Enterprise and Edu users the following week.

OpenAI

2,750,389 次观看 • 1 年前

Stream-Omni Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model

Stream-Omni Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model

AK

12,374 次观看 • 1 年前

GPT-5.4 is our most factual and efficient model: fewer tokens, faster speed. In ChatGPT, GPT-5.4 Thinking has improved deep web research, better context retention when it thinks for longer—and oh—you can now interrupt the model and add instructions or adjust its direction mid-response. Steering is available this week on Android and web. iOS coming soon.

GPT-5.4 is our most factual and efficient model: fewer tokens, faster speed. In ChatGPT, GPT-5.4 Thinking has improved deep web research, better context retention when it thinks for longer—and oh—you can now interrupt the model and add instructions or adjust its direction mid-response. Steering is available this week on Android and web. iOS coming soon.

OpenAI

480,473 次观看 • 4 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

Say hello to GPT-4o, our new flagship model which can reason across audio, vision, and text in real time: Text and image input rolling out today in API and ChatGPT with voice and video in the coming weeks.

Say hello to GPT-4o, our new flagship model which can reason across audio, vision, and text in real time: Text and image input rolling out today in API and ChatGPT with voice and video in the coming weeks.

OpenAI

22,809,972 次观看 • 2 年前

LLava just hit 3800 stars on Github. It's a multimodal Large Language-and-Vision Assistant that can understand images and text. LLava can even handle memes (the same ones GPT-4 demo'ed at launch) and set a new SOTA on Science QA. It also supports LLaMA-2, LoRA training with academia GPUs, higher resolution (336x336), 4-/8- inference.

LLava just hit 3800 stars on Github. It's a multimodal Large Language-and-Vision Assistant that can understand images and text. LLava can even handle memes (the same ones GPT-4 demo'ed at launch) and set a new SOTA on Science QA. It also supports LLaMA-2, LoRA training with academia GPUs, higher resolution (336x336), 4-/8- inference.

Lior Alexander

143,530 次观看 • 3 年前

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face

New open Omni model released! 👀OpenBMB MiniCPM-o 2.6 is a new 8B parameters, any-to-any multimodal model that can understand vision, speech, and language and runs on edge devices like phones and tablets. TL;DR: 🧠 8B total parameters (SigLip-400M + Whisper-300M + ChatTTS-200M + Qwen2.5-7B) 🔥 Outperforms GPT-4V on visual tasks with 70.2 average score on OpenCompass 🎙️ Best-in-class bilingual speech capabilities with real-time conversation and voice cloning 🎬 Supports multimodal streaming with support for continuous video/audio processing 📱 Runs on iPads and phones and supports 30+ languages 🖼️ Processes images up to 1.8M pixels (1344x1344) with OCR capabilities 🛠️ Easy integration with popular frameworks (llama.cpp, vLLM, Gradio) 🤗 commercial friendly (< 1 mio DAU) and available on Hugging Face

Philipp Schmid

19,409 次观看 • 1 年前

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

492,853 次观看 • 8 个月前

Multimodal AI is here 🤯 GPT-4 can now turn your images into a text file in a snap with the new code interpreter model. Witness the OCR magic in action 🔥

Multimodal AI is here 🤯 GPT-4 can now turn your images into a text file in a snap with the new code interpreter model. Witness the OCR magic in action 🔥

Shubham Saboo

727,673 次观看 • 3 年前

We've just unveiled ERNIE 4.5 & X1! 🚀 As a deep-thinking reasoning model with multimodal capabilities, ERNIE X1 delivers performance on par with DeepSeek R1 at only half the price. Meanwhile, ERNIE 4.5 is our latest foundation model and new-generation native multimodal model. Plus, our AI chatbot ERNIE Bot has now been made free to individual users ahead of schedule. Both models are now freely accessible to all ERNIE Bot users via its official website:

We've just unveiled ERNIE 4.5 & X1! 🚀 As a deep-thinking reasoning model with multimodal capabilities, ERNIE X1 delivers performance on par with DeepSeek R1 at only half the price. Meanwhile, ERNIE 4.5 is our latest foundation model and new-generation native multimodal model. Plus, our AI chatbot ERNIE Bot has now been made free to individual users ahead of schedule. Both models are now freely accessible to all ERNIE Bot users via its official website:

Baidu Inc.

1,711,890 次观看 • 1 年前

Lullabies and whispers with GPT-4o

Lullabies and whispers with GPT-4o

OpenAI

529,238 次观看 • 2 年前

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

1,693,329 次观看 • 8 个月前

Point and learn Spanish with GPT-4o

Point and learn Spanish with GPT-4o

OpenAI

476,332 次观看 • 2 年前