Загрузка видео...

Не удалось загрузить видео

На главную

Gemini 1.5 Pro can understand tasks and questions across different modalities because of its long context understanding. When given a 44-minute Buster Keaton film, it's able to find small details in the film and understand plot points. #GeminiAI

229,104 просмотров • 2 лет назад •via X (Twitter)

Комментарии: 10

Фото профиля Samsung Mobile
Samsung Mobile2 лет назад

Another epic way to welcome the era of AI 🙌

Фото профиля Abhin
Abhin2 лет назад

Hey Google, please add Google Finance as a Gemini (Bard) extension.

Фото профиля Tatarin
Tatarin2 лет назад

Let me test it, it's just words for now😎

Фото профиля Webyscorp
Webyscorp2 лет назад

Gemini 1.5 pro ready for that #GrandeFratello #Drake

Фото профиля Michał Gonciarz
Michał Gonciarz2 лет назад

😮👏👍

Фото профиля Diegol
Diegol2 лет назад

@fofont

Фото профиля Bharat Buzz
Bharat Buzz2 лет назад

It's just insane that the Ultra was launched a month ago and now again an update to the newly released model Kudos Google 🔥

Фото профиля Google
Google2 лет назад

@digitaldetox_9 This is just the start ✨

Фото профиля Shipra Sen ོ
Shipra Sen ོ2 лет назад

The future is here! 🔮 #GeminiAI

Фото профиля Google
Google2 лет назад

Welcome to the Gemini era ✨

Похожие видео

Gemini-1.5 Pro has its spotlight stolen today, and people are poking fun at Sora vs Google memes. Well, I think it's the biggest boost in LLM capability so far in 2024. v1.5's 10M token context (1) excels at retrieval; (2) generalizes zero-shot to extremely long instructions like full tutorials and codebases; and (3) works across modalities such as text, audio, and video. Here's a stunning example: v1.5 learns to translate from English to Kalamang purely in context, following a full linguistic manual at inference time. Kalamang is a language spoken by fewer than 200 speakers in western New Guinea. Gemini has never seen this language during training and is only provided with 500 pages of linguistic documentation, a dictionary, and ~400 parallel sentences in context. It basically acquires a sophisticated new skill in the neural activations, instead of gradient finetuning. I talked about the Myth of Context Length many times before: don't get too excited by claims of 1M or even 1B context tokens. LSTMs already achieved literally infinite context length 25 yrs ago! What truly matters is how well the model actually uses the context to solve real-world problems, and Gemini-1.5 has surpassed the SOTA with flying colors. The paper is also well-written with lots of solid quantitative analysis on in-context memorization and generalization. Paper: “Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context” Congrats to Jeff Dean Oriol Vinyals Sundar Pichai and team!

Jim Fan

278,517 просмотров • 2 лет назад