We’re a research group at @MIT_CSAIL using data visualization as a petri dish to study intelligence augmentation.
Joined July 2018
- Tweets 270
- Following 20
- Followers 3,211
- Likes 250
46 Photos and videos
Pinned Tweet
HUGE CONGRATS to Dr. @angie_boggust for a masterful defense of her thesis on “Reconciling AI Representations and User Mental Models” 🎉🍾🥂
We are going to miss you dearly at @mitvis 🥲
ALT Angie delivering her thesis defense
ALT Angie thanking the @mitvis research group
ALT Angie popping a bottle of champagne and pouring herself a glass!
1
9
628
MIT Visualization Group retweeted
My PhD has been some of the most fun I've ever had, and that's almost entirely thanks to my incredible colleagues @mitvis, collaborators @MIT_CSAIL, and committee — @arvindsatya1, @wattenberg, and @mitchellgordon!
1
3
18
775
MIT Visualization Group retweeted
I defended! 🎉
For the past six years, I have studied whether AI models see the world the same way as their users. My dissertation, "Reconciling AI Representations and User Mental Models," gives people the agency to define, measure, and adjust human-AI alignment in their domain.
4
5
73
4,852
MIT Visualization Group retweeted
Apr 22
Check out our autointerp paper ✨Semantic Regexes ✨at ICLR on Friday April 24!
@MIT_CSAIL and @Apple with @donghaoren, @tafsiri, @domoritz, @arvindsatya1 & @fredhohman
📅 iclr.cc/virtual/2026/poster/…
📄 arxiv.org/abs/2510.06378
🖥️ github.com/apple/ml-semantic…
🔗 machinelearning.apple.com/re…
3
11
39
3,553
MIT Visualization Group retweeted
Mar 17
color scales landing in gofish this week!
1
2
8
403
MIT Visualization Group retweeted
Jan 2
Hello! New blog post about connections between external representations: joshmpollock.com/blog/extern…
3
13
1,388
MIT Visualization Group retweeted
5 Nov 2025
Come learn from Josh about how graphical operators enable some incredibly expressive vis design! This work has been incredibly influential in shaping how we’ve been thinking of the future of visualization grammars at @mitvis. 3:45 pm in Hall M2 #ieeevis #VIS26
30 Oct 2025
2
9
791
MIT Visualization Group retweeted
30 Oct 2025
The most high quality poster Ive ever seen
30 Oct 2025
3
8
2,222
MIT Visualization Group retweeted
30 Oct 2025
1
4
21
4,092
MIT Visualization Group retweeted
30 Sep 2025
bet
1
2
6
1,084
MIT Visualization Group retweeted
30 Sep 2025
Personally I think my scrap paper chart looks better
1
2
7
1,986
MIT Visualization Group retweeted
30 Sep 2025
charts should have drop shadows
1
2
4
1,471
MIT Visualization Group retweeted
6 Jul 2025
Heading to @SciPyConf this week? Learn how to build effective interactive visualizations with @vega_vis in @jonmmease and my tutorial on Vega-Altair.
We’ll demo best practices for data visualization and show how to apply them to your own charts!
4
14
1,022
MIT Visualization Group retweeted
2 Jul 2025
Added a tutorial to the website!
1
3
12
765
MIT Visualization Group retweeted
16 Jun 2025
new charting library is baking
ALT two by three grid: bar chart, horizontal bar chart, stacked bar chart, grouped bar chart, streamgraph, stacked area chart
3
19
1,360
MIT Visualization Group retweeted
5 Jun 2025
“I’m working on a big idea!”
But… what is a big idea, really? And are we just telling ourselves that to feel better about not publishing? Or superior than others?
Some personal reflections on deep work and big idea:
🔗 ryanyen2.github.io/blog/big-…
2
17
1,368
MIT Visualization Group retweeted
24 Apr 2025
I’ll be at #CHI2025 🌸
If you are excited about interpretability and human-AI alignment — let’s chat!
And come see Abstraction Alignment ⬇️ in the Explainable AI paper session on Monday at 4:20 JST
14 Apr 2025
#CHI2025 paper on human–AI alignment! 🧵
Models can learn the right concepts but still be wrong in how they relate them.
✨Abstraction Alignment✨evaluates whether models learn human-aligned conceptual relationships.
It reveals misalignments in LLMs💬 and medical datasets🏥.
ALT An overview of Abstraction Alignment, including its authors and links to the paper, demo, and code.
1
7
29
3,281
MIT Visualization Group retweeted
14 Apr 2025
#CHI2025 paper on human–AI alignment! 🧵
Models can learn the right concepts but still be wrong in how they relate them.
✨Abstraction Alignment✨evaluates whether models learn human-aligned conceptual relationships.
It reveals misalignments in LLMs💬 and medical datasets🏥.
ALT An overview of Abstraction Alignment, including its authors and links to the paper, demo, and code.
6
21
98
14,482