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。

branching interface for writing a tighter creative feedback loop guided by a language model to weave through the possibility space of text

Azlen

10,728 subscribers

51,705 次观看 • 1 年前 •via X (Twitter)

艺术科学技术

Anya Rossi• Live Now

Private livecam show

11 条评论

Cube Flipper 的头像

Cube Flipper1 年前

oh this is awesome, though the circular arrangement is so much harder to scan than it would be if it was a vertical list

Azlen 的头像

Azlen1 年前

yeah i thought the same, but circular seemed more fun! I wanted to try it out inspired both by Dasher and this color-picker I made a while back

Kal 的头像

Kal1 年前

This could be useful for writing via eye tracking for AR glasses.

Andy Ayrey 的头像

Andy Ayrey1 年前

this is sick as hell

Ryan Wold 的头像

Ryan Wold1 年前

nice keeping the text horizontal (but keep the branching) might aid legibility/usability

Oliver Beavers 的头像

Oliver Beavers1 年前

I've been thinking about this concept for so, so long and have been considering slightly higher levels of abstraction for creating storylines/outlines/etc in a node-based UI.

Azlen 的头像

Azlen1 年前

definitely feels like there is interesting possibility in interfaces that let you shape or sculpt a story at a high level!

Casey 的头像

Casey1 年前

nested and recursive trinities.... (screenshot from ctrlcreep)

Noorie 的头像

Noorie1 年前

@thesephist cool idea. implementation is the hard part

Philippe Voinov 的头像

Philippe Voinov1 年前

Is there a natural way to undo? I did this a while ago with dasher's UI where you can undo by pointing backwards. Also have you tried anything to make the model generate diverse branches? That seemed important when I played with mine

Azlen 的头像

Azlen1 年前

it could leave a trail behind you! which is fun because each thing you write could have a sort of shape to it

相关视频

Introducing ClickDiffusion! We developed a system for precise image manipulation and generation that combines natural language instructions with visual feedback provided by the user through a direct manipulation interface.

Introducing ClickDiffusion! We developed a system for precise image manipulation and generation that combines natural language instructions with visual feedback provided by the user through a direct manipulation interface.

Alec Helbling

36,293 次观看 • 2 年前

exploring 2,500 named colour terms, organised by similarity in CLIP's 512-dimensional text embedding space. the structure that emerges from just text inputs forms a kind of continuous colour space, hinting at a low-dimensional manifold for colour language.

exploring 2,500 named colour terms, organised by similarity in CLIP's 512-dimensional text embedding space. the structure that emerges from just text inputs forms a kind of continuous colour space, hinting at a low-dimensional manifold for colour language.

Matt DesLauriers

13,799 次观看 • 1 个月前

Nearly real-time diffusion model, running locally and offline from my browser and with decent output quality. Pretty astonishing to use; but with such a tight feedback loop, the textual interface starts to feel really inadequate.

Nearly real-time diffusion model, running locally and offline from my browser and with decent output quality. Pretty astonishing to use; but with such a tight feedback loop, the textual interface starts to feel really inadequate.

Matt DesLauriers

122,502 次观看 • 2 年前

To achieve it, I used a single Niagara actor to read the screen-space velocity directly from the GBuffer and apply that to a render target by using a Grid2D interface to loop through each screen pixel. The rest is mapping, manipulating and masking that in the material :) #Shaders

To achieve it, I used a single Niagara actor to read the screen-space velocity directly from the GBuffer and apply that to a render target by using a Grid2D interface to loop through each screen pixel. The rest is mapping, manipulating and masking that in the material :) #Shaders

Pedro Borges

15,206 次观看 • 1 年前

This is Text-to-CAD. A new open-source prompt interface for generating CAD files through text prompts. It looks insane 🤯

This is Text-to-CAD. A new open-source prompt interface for generating CAD files through text prompts. It looks insane 🤯

Alvaro Cintas

111,304 次观看 • 1 年前

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:

DeepLearning.AI

46,065 次观看 • 3 个月前

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

Andrew Ng

128,085 次观看 • 1 年前

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

AK

254,242 次观看 • 1 年前

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→

Google AI

80,357 次观看 • 2 年前

We're thrilled to announce SignGemma, our most capable model for translating sign language into spoken text. 🧏 This open model is coming to the Gemma model family later this year, opening up new possibilities for inclusive tech. Share your feedback and interest in early testing →

We're thrilled to announce SignGemma, our most capable model for translating sign language into spoken text. 🧏 This open model is coming to the Gemma model family later this year, opening up new possibilities for inclusive tech. Share your feedback and interest in early testing →

Google DeepMind

524,612 次观看 • 1 年前

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 次观看 • 3 年前

What's it like to float through the International Space Station? Come take a guided tour with us:

What's it like to float through the International Space Station? Come take a guided tour with us:

NASA

4,180,661 次观看 • 5 个月前

2️⃣SignGemma is a sign language understanding model that’s coming later this year 🤟🏼It’s a massively multilingual model that’s best at translating ASL into English text, enabling further development of tech access for Deaf and Hard of Hearing users. 🧏 Share your feedback and interest in early testing here:

2️⃣SignGemma is a sign language understanding model that’s coming later this year 🤟🏼It’s a massively multilingual model that’s best at translating ASL into English text, enabling further development of tech access for Deaf and Hard of Hearing users. 🧏 Share your feedback and interest in early testing here:

Google AI Developers

78,800 次观看 • 1 年前

#genuary9 Crazy automaton. Cellular automata with a small language model as rule. The model is trying to recover the corrupted text. #genuary2026 #genuary

#genuary9 Crazy automaton. Cellular automata with a small language model as rule. The model is trying to recover the corrupted text. #genuary2026 #genuary

Hans Chiu

42,670 次观看 • 5 个月前

They are programming computer code. Each weave through a magnetic core is a “1”. These computer programs got us to space.

They are programming computer code. Each weave through a magnetic core is a “1”. These computer programs got us to space.

Brian Roemmele

35,844 次观看 • 6 个月前

For the first time we are fundamentally changing how humans can collaborate with ChatGPT since it launched two years ago. We’re introducing canvas, a new interface for working with ChatGPT on writing and coding projects that go beyond simple chat. Product and model features: 1/ Ask for in-line feedback. With canvas, ChatGPT can better understand the context of what you’re trying to accomplish. You can highlight specific sections to indicate exactly what you want ChatGPT to focus on. Like a copy editor or code reviewer, it can give in-line feedback and suggestions with the entire project in mind. 2/ Directly edit the model's output and select a specific area for targeted editing. You control your creative work on canvas. You can directly edit text or code. 3/ Menu of shortcuts. There’s a menu of shortcuts for you to ask ChatGPT to adjust writing length, debug your code, and quickly perform other useful actions. You can also restore previous versions of your work by using the back button in canvas. 4/ Use search with canvas for research writing! As we are moving towards the new paradigm of reasoning we are fundamentally evolving the chat interface into a more collaborative human-AI interaction. Today you can say “browse / use browsing to find XYZ on the internet and write a report in canvas”

For the first time we are fundamentally changing how humans can collaborate with ChatGPT since it launched two years ago. We’re introducing canvas, a new interface for working with ChatGPT on writing and coding projects that go beyond simple chat. Product and model features: 1/ Ask for in-line feedback. With canvas, ChatGPT can better understand the context of what you’re trying to accomplish. You can highlight specific sections to indicate exactly what you want ChatGPT to focus on. Like a copy editor or code reviewer, it can give in-line feedback and suggestions with the entire project in mind. 2/ Directly edit the model's output and select a specific area for targeted editing. You control your creative work on canvas. You can directly edit text or code. 3/ Menu of shortcuts. There’s a menu of shortcuts for you to ask ChatGPT to adjust writing length, debug your code, and quickly perform other useful actions. You can also restore previous versions of your work by using the back button in canvas. 4/ Use search with canvas for research writing! As we are moving towards the new paradigm of reasoning we are fundamentally evolving the chat interface into a more collaborative human-AI interaction. Today you can say “browse / use browsing to find XYZ on the internet and write a report in canvas”

Karina

845,496 次观看 • 1 年前

Introducing FlexOlmo, a new paradigm for language model training that enables the co-development of AI through data collaboration. 🧵

Introducing FlexOlmo, a new paradigm for language model training that enables the co-development of AI through data collaboration. 🧵

Ai2

369,259 次观看 • 11 个月前

Ready, Set, Pose! 📸 A loop of #CloneX PFPs brought to life by the insanely talented Ali (Aalasady) Join the Creative Revolution 💫

Ready, Set, Pose! 📸 A loop of #CloneX PFPs brought to life by the insanely talented Ali (Aalasady) Join the Creative Revolution 💫

RTFKT Creators

99,491 次观看 • 3 年前

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 次观看 • 2 年前