Rima Cao

(Incoming) Research Scientist @AdobeResearch | Research Fellow @MSFTResearch | Building generative, malleable softwares.
Alum. @UCSanDiego @UMich @Tsinghua_Uni

[Rima Cao @rrrima_]

Aware is (basically) a browser we're building to explore personal computing and generative, malleable software. it keeps a footprint of the materials (pages, files) as a graph in a relational database stored locally.

Been writing my paper in my own latex editor inside Aware. It's very satisfying when software fixes itself and fetches its own context and attach them to the right parts.

The editor is an experiment of "interface as a skill": the editor's code and its skill live in the paper's repo, so the same agent that knows my code and data also lives in the editor. So i get:
1. an interface i can reprogram any part anytime (aesthetics i like, and the scratch pad i always wanted)
2. an agent living in the editor, with the whole project as context (a figure links to the dashboard, built from the real analysis code that made it)

(though i have to admit, some of my focused writing time now goes to wanting to tweak the editor instead)

[Haijun Xia @HaijunXia]

We live in a vast digital universe with billions of websites, services, and applications. Yet, we’ve always been visitors, subscribers, and users,
and never the * owners *.

What if we can create our own information universe, one that holds our own data, understands us, and evolves with us?

We have been building Aware, a united place for the internet, your materials, and your agents. This clip shows how you can turn a tab into your *own* tab.

[Bruce Liu @liu_xingyu]

I built a way to make videos with NO timeline.

You write it like a story all in one doc, from first idea to final cut. Doki ensures that the whole video stays consistent and continuous.

You can try it today 👇

[Rima Cao @rrrima_]

@orvonu @adarshxd working on it :)

[Rima Cao @rrrima_]

Reprogrammed my cursor to do two things that have been helpful:
- carry a screenshot (double-click to drop, shake to toss)
- jot a note in any margin (keeps the time and source)

The cursor is the one thing that's in every app, so it's extremely suitable for cross-app pains.

[Rima Cao @rrrima_]

@coldwoodlh Thanks! In fact, we had a paper on this matter: https://t.co/ZW6eqdC4UT

[Rima Cao @rrrima_]

@dinizz thanks! thinking about how to share it.. will post here when it's out :)

[Rima Cao @rrrima_]

@olzhas on my list! will post here if it's out :)

[Rima Cao @rrrima_]

@chenzhangreal haha fair.. the default behavior is actually auto-saved in a local folder. I never revisit my screenshots so i set it just to be deleted

[Rima Cao @rrrima_]

@dmytrovirych all notes are saved in one local folder. each one keeps a deep link back to where you started it

[Rima Cao @rrrima_]

@adarshxd thanks :) it's a native swift menu-bar app, actually built on top of Aware's event handling pipeline with its own UI.. mostly the accessibility API and applescript under the hood

[Rima Cao @rrrima_]

@sidhg_ rarely! it looks for repeated direction reversals, and i tuned the thresholds and cooldown.. haven't lost one by accident so far

[Rima Cao @rrrima_]

both follow a simple concept: if the OS is more like an agent than an office, things don't need to be filed away in a specific place first - they just stay at hand.

[Rima Cao @rrrima_]

@gezhang001 @UChicago @Stanford @Harvard @UCSanDiego congratssss!

[Haijun Xia @HaijunXia]

Why does getting a little AI help require a whole chat session? It takes us out of context and breaks our flow. This is something we're trying to get right in Aware.

One core principle we have for Aware is simple: AI assistance should be accessible anywhere.

In Aware, you can type @​aware in any text box to get help. Or select any text or any part of your screen and ask AI about it, without interrupting what you're doing.

The first example in the video addresses a pain point that I have: I get a lot of links from all over the place- Slack, email, websites. Aware remembers all these links, and I can ask Aware to get them for me with the context I remember.

[Rima Cao @rrrima_]

@building_pri @dingzeyuli @liu_xingyu @bryanhaoenwang please apply!

[Rima Cao @rrrima_]

We are hiring summer 2027 interns. Come join us!
Our team @dingzeyuli , @liu_xingyu , @bryanhaoenwang will all be at #UIST2026! Say hi to us :)

[Bruce Liu @liu_xingyu]

We're hiring! Adobe Research is seeking summer 2027 Research Scientist/Engineer interns (SF/Seattle) to work at the intersection of novel experiences and AI models for video creativity, from new interactions and agents to the models behind them.

Apply: https://t.co/KHkpmGVJLl

[Haijun Xia @HaijunXia]

The Aware that I posted earlier can't, but now it can, because it's a malleable environment that you can shape. A simple prompt in Aware and a couple of minutes of agent work, and there you have it.

My prompt to Aware: give me a pop-up to write down my notes when I bookmark on X, and also allow me to search the note in the Bookmarks.

[Rima Cao @rrrima_]

well-designed dynamic documents are just a really flexible substrate for any medium.. reminds me of Embark from Ink & Switch (@geoffreylitt and co) on travel planning too: https://t.co/RvM8MpoWHV

[Rima Cao @rrrima_]

Can someone fix call centers before AGI?
Or is there a personal agent that can navigate a call center and actually get through to a human? Can we make that the next launch demo... (besides planning trips)

..anyway, it's been fun making this little video with Doki!
tho it's rlly NOT fun dealing with this situation 🫠 it's literally been draining me for the past week.
I guess pain is my source of creativity ᐛ

[Bruce Liu @liu_xingyu]

Introducing Doki, our latest paper and research prototype @AdobeResearch, a complete reimagination of generative video authoring.
Instead of juggling scripts, prompts, timelines, and editors, you write a story in a single document… and it becomes the video. 🧵👇

[Rima Cao @rrrima_]

@KyuMehul thanks for sharing! we thought about obsidian too.. the main challenge is that we need our own backend process to handle continuous context collecting and keep apps live (as opposed to a clipped snapshot).. that's why we went with a rust + cef host and a native macOS shell

[Rima Cao @rrrima_]

Aware is (basically) a browser we're building to explore personal computing and generative, malleable software. it keeps a footprint of the materials (pages, files) as a graph in a relational database stored locally.

Been writing my paper in my own latex editor inside Aware. It's very satisfying when software fixes itself and fetches its own context and attach them to the right parts.

The editor is an experiment of "interface as a skill": the editor's code and its skill live in the paper's repo, so the same agent that knows my code and data also lives in the editor. So i get:
1. an interface i can reprogram any part anytime (aesthetics i like, and the scratch pad i always wanted)
2. an agent living in the editor, with the whole project as context (a figure links to the dashboard, built from the real analysis code that made it)

(though i have to admit, some of my focused writing time now goes to wanting to tweak the editor instead)

[Haijun Xia @HaijunXia]

We live in a vast digital universe with billions of websites, services, and applications. Yet, we’ve always been visitors, subscribers, and users,
and never the * owners *.

What if we can create our own information universe, one that holds our own data, understands us, and evolves with us?

We have been building Aware, a united place for the internet, your materials, and your agents. This clip shows how you can turn a tab into your *own* tab.

[Rima Cao @rrrima_]

@richardparayno Haha, it might not be a paper, but will share more insights soon