Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Photoshop for text. In our #CHI2025 paper “Textoshop”, we explore how interactions inspired by drawing software can help edit text. We consider words as pixels, sentences as regions, and tones as colours. #HCI #NLProc #LLMs #AI Thread 🧵 (1/10)

Damien Masson

1,285 subscribers

88,261 views • 1 year ago •via X (Twitter)

Science & Technology #CHI2025 #HCI #NLProc #LLMs #AI

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Excited to share our #CHI2026 paper “Texterial: A Text-as-Material Interaction Paradigm for LLM-Mediated Writing” (done during internship at Microsoft Research) We imagine interacting with LLMs by treating text as a material like plants/clay. 📃 🧵[1/n]

Excited to share our #CHI2026 paper “Texterial: A Text-as-Material Interaction Paradigm for LLM-Mediated Writing” (done during internship at Microsoft Research) We imagine interacting with LLMs by treating text as a material like plants/clay. 📃 🧵[1/n]

Jocelyn Shen

19,636 views • 4 months ago

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵

kyutai

53,003 views • 2 months ago

New work with Edward Grefenstette at Google DeepMind: 🚨Interaction Dynamics as a Reward Signal for LLMs🚨 When it comes to interactions, the "how" is just as important as the "what" There is a signal in how we interact with a model that text analysis misses: hesitation, drift, friction

New work with Edward Grefenstette at Google DeepMind: 🚨Interaction Dynamics as a Reward Signal for LLMs🚨 When it comes to interactions, the "how" is just as important as the "what" There is a signal in how we interact with a model that text analysis misses: hesitation, drift, friction

Sian Gooding

36,663 views • 8 months ago

(1/7) As an AI filmmaking tool built with and for creatives, we wanted to put our features to the test. So, we created our own short film! Follow this thread for a behind-the-scenes look at the creative process, and see how Flow can help you build stories with consistent characters, scenes, and objects.

(1/7) As an AI filmmaking tool built with and for creatives, we wanted to put our features to the test. So, we created our own short film! Follow this thread for a behind-the-scenes look at the creative process, and see how Flow can help you build stories with consistent characters, scenes, and objects.

Google Flow

75,398 views • 10 months ago

How can LLMs help improve local government services? This is the end of “Please listen closely as our menu options may have changed”: Lizzie Siegle’s team built a superset of San Francisco’s 311 service - which routes all residents through a massive, confusing and slow phone tree - all replaced by a simple natural language phone call with an AI agent as first line of response. voice to text, text to voice, all in a one day hackathon. Para Español, no necesita oprima numero dos.

How can LLMs help improve local government services? This is the end of “Please listen closely as our menu options may have changed”: Lizzie Siegle’s team built a superset of San Francisco’s 311 service - which routes all residents through a massive, confusing and slow phone tree - all replaced by a simple natural language phone call with an AI agent as first line of response. voice to text, text to voice, all in a one day hackathon. Para Español, no necesita oprima numero dos.

swyx

133,550 views • 2 years ago

DESIGN.md is how we work with agents now, but a text file is a terrible way for a human to make a visual decision. So we built our preview to give some of that control back: edit the file as text or pick colors visually, and the two stay in sync. And swatches sit on the actual light and dark backgrounds because color only means something in the context you'll see it in.

DESIGN.md is how we work with agents now, but a text file is a terrible way for a human to make a visual decision. So we built our preview to give some of that control back: edit the file as text or pick colors visually, and the two stay in sync. And swatches sit on the actual light and dark backgrounds because color only means something in the context you'll see it in.

Chloe Park

86,285 views • 1 month ago

In VR, users can experience “magical” interactions, such as moving distant virtual objects with the Go-Go technique. How might we similarly extend people’s abilities in the physical world? 🪄 Excited to share Reality Promises, our #UIST2025 paper, led by the amazing Mohamed Kari ✨

In VR, users can experience “magical” interactions, such as moving distant virtual objects with the Go-Go technique. How might we similarly extend people’s abilities in the physical world? 🪄 Excited to share Reality Promises, our #UIST2025 paper, led by the amazing Mohamed Kari ✨

Parastoo Abtahi

12,997 views • 11 months ago

New paper: You can make ChatGPT 2x as creative with one sentence. Ever notice how LLMs all sound the same? They know 100+ jokes but only ever tell one. Every blog intro: "In today's digital landscape..." We figured out why – and how to unlock the rest 🔓 Copy-paste prompt: 🧵

New paper: You can make ChatGPT 2x as creative with one sentence. Ever notice how LLMs all sound the same? They know 100+ jokes but only ever tell one. Every blog intro: "In today's digital landscape..." We figured out why – and how to unlock the rest 🔓 Copy-paste prompt: 🧵

Weiyan Shi

329,823 views • 9 months ago

I just tried Sarvam, and it’s truly impressive. You can convert any text into audio in Indian languages and save it as an MP3 on your system. You can also convert audio into text and save it as a TXT file or even a video file. It offers many more features that I’m excited to explore. Congratulations to Team Sarvam for building India’s first truly Make in India AI platform. A proud moment for India 🇮🇳 Special thanks to our respected PM Narendra Modi ji and IT Minister Ashwini Vaishnaw ji for their leadership in driving India’s AI revolution.

I just tried Sarvam, and it’s truly impressive. You can convert any text into audio in Indian languages and save it as an MP3 on your system. You can also convert audio into text and save it as a TXT file or even a video file. It offers many more features that I’m excited to explore. Congratulations to Team Sarvam for building India’s first truly Make in India AI platform. A proud moment for India 🇮🇳 Special thanks to our respected PM Narendra Modi ji and IT Minister Ashwini Vaishnaw ji for their leadership in driving India’s AI revolution.

STAR Boy TARUN

70,548 views • 5 months ago

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 views • 11 months ago

Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ The 7B & 34B safety tuned models we’ve released can take any combination of text and images as input and produce text outputs using a new early fusion approach. While some LLMs have separate image and text encoders or decoders, Chameleon is one of the first publicly released approaches using a single unified architecture. We’re releasing Chameleon models under a research license to help democratize access to foundational mixed-modal models & further research on early fusion. Approach & training details in the paper ➡️

Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ The 7B & 34B safety tuned models we’ve released can take any combination of text and images as input and produce text outputs using a new early fusion approach. While some LLMs have separate image and text encoders or decoders, Chameleon is one of the first publicly released approaches using a single unified architecture. We’re releasing Chameleon models under a research license to help democratize access to foundational mixed-modal models & further research on early fusion. Approach & training details in the paper ➡️

AI at Meta

54,428 views • 2 years ago

We introduced Text-to-CAD into our Modeling App to allow hardware designers to use prompts in addition to the traditional point and click style they are used to. We also have a third method, CAD represented as code, for users who want it. I expand on the code approach here. 🧵

We introduced Text-to-CAD into our Modeling App to allow hardware designers to use prompts in addition to the traditional point and click style they are used to. We also have a third method, CAD represented as code, for users who want it. I expand on the code approach here. 🧵

Jordan Noone 🇺🇸

47,900 views • 1 year ago

DEBUNKED: Vice President Vance just spoke about how the media has been ENDLESSLY speculating about why the text of the MOU between America and Iran wasn't "immediately released." "I don‘t think OUR public messaging has been chaotic." Vance says he told the leaders involved in the MOU: "We understand your desire not to have the text out until Friday, but, you know, we, we live in a democratic system. The American people wanna see the text of this deal. We would certainly like to get it out as soon as possible." "But the reason why it went back and forth a little bit about when exactly the text would be released is just we were trying to show good faith to the Iranians, who for reasons I have no idea, cared a lot about how the text itself was rolled out."

DEBUNKED: Vice President Vance just spoke about how the media has been ENDLESSLY speculating about why the text of the MOU between America and Iran wasn't "immediately released." "I don‘t think OUR public messaging has been chaotic." Vance says he told the leaders involved in the MOU: "We understand your desire not to have the text out until Friday, but, you know, we, we live in a democratic system. The American people wanna see the text of this deal. We would certainly like to get it out as soon as possible." "But the reason why it went back and forth a little bit about when exactly the text would be released is just we were trying to show good faith to the Iranians, who for reasons I have no idea, cared a lot about how the text itself was rolled out."

Andrew Kolvet

57,151 views • 1 month ago

Newly released documents in the Smartmatic defamation case against Fox News reveal how much anchors like Jeanine Pirro and Jesse Watters wanted to help Donald Trump. Some dissented: "Fox executive Jay Wallace was made aware by Bret Baier via text that Maria Bartiromo tweeted false claims about vote dumps in favor of Joe Biden... 'none of that is true as far as we can tell. We need to fact-check this crap.'"

Newly released documents in the Smartmatic defamation case against Fox News reveal how much anchors like Jeanine Pirro and Jesse Watters wanted to help Donald Trump. Some dissented: "Fox executive Jay Wallace was made aware by Bret Baier via text that Maria Bartiromo tweeted false claims about vote dumps in favor of Joe Biden... 'none of that is true as far as we can tell. We need to fact-check this crap.'"

Blue Georgia

304,239 views • 11 months ago

In the studio today recording the audio version of my book, “Go and Do Likewise.” In my words, I’m sharing how we can reclaim faith as a force for good to help the American people and the country we love. It’s out September 22 – but you can pre-order now.

In the studio today recording the audio version of my book, “Go and Do Likewise.” In my words, I’m sharing how we can reclaim faith as a force for good to help the American people and the country we love. It’s out September 22 – but you can pre-order now.

Andy Beshear

14,377 views • 12 days ago

I wrote a AI "text adventure game" (MUD) in the past two weeks. We had a "hackweek" for prototyping AI game play. Story is AI generated text. Text generator is fed the theme and previous rooms and rules for exit generation. It returns a JSON string of exits and their descriptions. Which the game then parses and sends to AI image generator and room graph system. There's also a AI written battle story generator, which gets your inventory as input. AI figures how to use your weapons and consumables. And returns JSON for managing inventory state (broken weapons, consumables, etc).

I wrote a AI "text adventure game" (MUD) in the past two weeks. We had a "hackweek" for prototyping AI game play. Story is AI generated text. Text generator is fed the theme and previous rooms and rules for exit generation. It returns a JSON string of exits and their descriptions. Which the game then parses and sends to AI image generator and room graph system. There's also a AI written battle story generator, which gets your inventory as input. AI figures how to use your weapons and consumables. And returns JSON for managing inventory state (broken weapons, consumables, etc).

Sebastian Aaltonen @ SIGGRAPH

72,311 views • 6 months ago

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,532 views • 2 years ago