Sign in

Antti Oulasvirta

@oulasvirta.bsky.social
346 followers 73 following 64 posts

Computational models of human behavior. Prof at Aalto University. Group page: cbl.aalto.fi

PostsRepliesMedia
Reposted by Antti Oulasvirta
S³CIX Summer School and Symposium on Computational Interaction @s3cix.bsky.social · 14/01/2026
Call for participation: 10th Summer School & Symposium on Computational Interaction (S³CIX), University of Glasgow, Scotland. June 16-20, 2026. Summer School expanded to include Symposium. Call for Workshops (14th Feb) & Student Attendence (14th March). s3cix.computationalinteraction.org
s3cix.computationalinteraction.org
S³CIX 2026
10th Summer School and Symposium on Computational Interaction (S³CIX), University of Glasgow, Scotland.
033
Antti Oulasvirta @oulasvirta.bsky.social · 06/01/2026
Treating AI as a black box may be holding back progress. Our fresh piece in IEEE Computer with @bjo3rn.bsky.social argues that to advance generative AI, we need to stop treating algorithms and users as separate concerns.
120
Reposted by Antti Oulasvirta
Danqing Shi @danqingshi.bsky.social · 01/12/2025
Feedback in RLHF is collected from human raters who are prompted by the system to compare pairs and express preferences. What advantages do we get if humans can exhibit higher agency? doi.org/10.1111/cgf....
121
Antti Oulasvirta @oulasvirta.bsky.social · 27/11/2025
Teaching HCI in Higher Education event starting: lecture-series.hcistudio.org
020
Antti Oulasvirta @oulasvirta.bsky.social · 27/11/2025
Happy to announce that our CHI 2026 Meet-up proposal 'The Role of AI in HCI Education' has been accepted! The goal is to serve as a catalyst for a community-wide discussion on how we ought to consider AI in HCI education going forward. Please forward and join if you can!
020
Antti Oulasvirta @oulasvirta.bsky.social · 18/11/2025
Launch of the new ELLIS Institute Finland. Excited to be part it!
061
Antti Oulasvirta @oulasvirta.bsky.social · 10/11/2025
One thing I’m especially proud of in our HCI intro book is that it includes an entire section dedicated to Engineering in HCI. As interactive technologies grow more complex, these methods are more important than ever. academic.oup.com/book/60808
050
Antti Oulasvirta @oulasvirta.bsky.social · 07/11/2025
Aleksi Ikkala on stage defending his thesis “Learning to Interact: Simulating Users with RL in HCI”, with Per Ola Kristensson as the opponent and Perttu Hämäläinen as the supervisor.
100
Antti Oulasvirta @oulasvirta.bsky.social · 06/11/2025
Prof Per Ola Kristensson / Cambridge giving a talk on how to design for the emergent properties of human-AI systems at Aalto. Per Ola is the opponent of Aleksi Ikkala who is defending his doctoral thesis on Friday, with Perttu Hämäläinen as the supervisor.
110
Antti Oulasvirta @oulasvirta.bsky.social · 27/10/2025
So proud of our PhD student Yue Jiang, who defended her thesis "Computational Representations for User Interfaces" last Friday, with Brian A. Smith as the opponent.
150
Antti Oulasvirta @oulasvirta.bsky.social · 23/10/2025
Brian A. Smith giving his talk "Computers as Partners in Human Ability" today at Aalto. Impressive work. I especially appreciate his work on creating auditory interfaces that allow blind users play real-time video games like driving. Brian is Yue Jiang's opponent and visiting us today and tomorrow.
000
Antti Oulasvirta @oulasvirta.bsky.social · 15/10/2025
Just presented "WigglyEyes: Inferring Eye Movements from Keypress Data" at Ubicomp/ISWC'25. It's a method that, given keypress data only, infers how users move their eyes when they type. It uses a user simulator for data augmentation. dl.acm.org/doi/pdf/10.1... github.com/quintus0505/...
120
Antti Oulasvirta @oulasvirta.bsky.social · 14/10/2025
Ubicomp'25 starting at Dipoli at Aalto. 793 attendees this year
020
Antti Oulasvirta @oulasvirta.bsky.social · 13/10/2025
This is the 2025 cohort of the Ubicomp Doctoral Colloquium. Some of the best PhD students in this area. We're standing here in front of Dipoli, the beautiful main venue of the conference. I look forward to hearing about these students as they move on after their PhDs.
020
Antti Oulasvirta @oulasvirta.bsky.social · 12/10/2025
On Friday, @ainiputkonen.bsky.social defended her dissertation on modeling decision-making in naturalistic settings with Prof. Adam Sanborn as the opponent. It has been a joy to watch her grow and emerge as a rigorous and original researcher. Congrats Aini! aaltodoc.aalto.fi/items/cf8487...
041
Antti Oulasvirta @oulasvirta.bsky.social · 09/10/2025
Prof. Adam Sanborn giving a talk on Bayesian Brain without Probabilities at Aalto
041
Antti Oulasvirta @oulasvirta.bsky.social · 26/09/2025
John R. Platt's Strong Inference 1958 (Science) keeps giving. Reading it this morning I found this gem. To push forward HCI, we need to do the same: sit down, think, and build models that help us tease out the fundamental questions -- and only then run empirical studies. Not the other way around.
010
Antti Oulasvirta @oulasvirta.bsky.social · 25/09/2025
The textbook is much more comprehensive than any introductory class needs. That's why we offer recommendations in Preface for courses in different contexts: computer science, design, engineering, social sciences, and specialized courses. Preface here: introductiontohci.org
020
Antti Oulasvirta @oulasvirta.bsky.social · 22/09/2025
Our new textbook isn't just about the essentials of research in HCI, it also offers guidance to those who entertain HCI as their future careers. My own two favorite bits are on how to read a paper critically and selecting HCI problems that matter. academic.oup.com/book/60808
050
Reposted by Antti Oulasvirta
Danqing Shi @danqingshi.bsky.social · 17/09/2025
Thrilled to share our #UIST2025 research! We investigate how the decomposition principle can improve human feedback for LLM alignment. In a 160-participant study, our tool DxHF increases feedback accuracy by +4.7% 👉 sdq.github.io/DxHF Furui Tino @oulasvirta.bsky.social @elassady.bsky.social
021
Reposted by Antti Oulasvirta
Pedro Lopes @pedrolopes.org · 14/09/2025
@acmuist.bsky.social #uist2025 program is out: programs.sigchi.org/uist/2025/pr... ... lots of interesting papers to look forward to, see you there
programs.sigchi.org
Conference Programs
084
Reposted by Antti Oulasvirta
Jon Froehlich @jonfroehlich.bsky.social · 02/09/2025
With the CHI deadline fast approaching, I'm resharing our lab's resource on making figures for HCI papers: docs.google.com/presentation... New content suggestions always appreciated. Don't be shy to promote your own work!
docs.google.com
Makeability Lab - How to Figures
How to figures makeabilitylab.cs.uw.edu
1136
Antti Oulasvirta @oulasvirta.bsky.social · 25/08/2025
OUP now offers not only one mammoth PDF but each chapter as its own file: academic.oup.com/book/60808
academic.oup.com
Introduction to Human-Computer Interaction
Abstract. Introduction to Human-Computer Interaction provides the first comprehensive textbook on the design of computing systems for human use. The book i
0111
Antti Oulasvirta @oulasvirta.bsky.social · 20/08/2025
📢The open access version of our book is available now via OUP's site: global.oup.com/academic/pro...
0279
Antti Oulasvirta @oulasvirta.bsky.social · 31/07/2025
It's amazing to have the book in my hand now, after several years of working on it with Kasper and Per Ola. In a nutshell, it's a new textbook for introductory-level HCI courses: ✅ 10 parts, covering the whole HCI process ✅ 864 pages and 1.9 kgs ✅ Open access (!)
2368
Reposted by Antti Oulasvirta
ScaDS.AI Dresden/Leipzig @scadsai.bsky.social · 16/07/2025
🏆Anton Gasse, Alexander Lingler(@ituaustria.bsky.social), Martin Lorenz, @oulasvirta.bsky.social(@aalto.fi‬), @philwintersberg.bsky.social(@ituaustria.bsky.social) & @patebel.bsky.social won the People’s Choice Award for Best Poster @chiwork.bsky.social 2025 in Amsterdam! 🔗https://shorturl.at/D5JDO
Smiling young man standing next to a poster titled "Evaluating Attention Management Systems for Dynamic Monitoring Tasks" at a conference.
043
Antti Oulasvirta @oulasvirta.bsky.social · 23/06/2025
We had a lovely summer school last week in Paris. Thirty amazing students and postdocs, a week full of keynotes and hands-on lectures on computational methods. State-of-the-art as call as classical topics, ranging from LLM agents to Bayesian inference cixschool2025.isir.upmc.fr
010
Reposted by Antti Oulasvirta
Jeffrey P. Bigham @jeffreybigham.com · 22/06/2025
I work in the best university in the world, less than 3 hours from my rural hometown, yet superstar students travel here from all over the world… if we keep treating them badly, will centers of excellence move elsewhere? "If my kids excel, will they move away?" jeffreybigham.com/blog/2025/wh...
jeffreybigham.com
In Pittsburgh, I’m a professor at Carnegie Mellon University in the top computer science school in the world. I’ve also worked in various large technology companies, who have offices in Pittsburgh to connect with and employ Carnegie Mellon faculty and students.
0449
Antti Oulasvirta @oulasvirta.bsky.social · 19/06/2025
John Williamson lecturing about simulator-bases inference at the Comp Int summer school cixschool2025.isir.upmc.fr
010
Antti Oulasvirta @oulasvirta.bsky.social · 16/06/2025
Philipp Wintersberger giving a talk on multitasking and human-AI interaction at Aalto
020
Antti Oulasvirta @oulasvirta.bsky.social · 06/06/2025
Visualizing Knowledge 2025 starting at Aalto
010
Antti Oulasvirta @oulasvirta.bsky.social · 14/05/2025
Vera Liao giving a talk on the AI sociotecnical gap at FCAI / Aalto
280
Antti Oulasvirta @oulasvirta.bsky.social · 13/05/2025
Paul Strohmeier giving a talk at Aalto
020
Reposted by Antti Oulasvirta
Aalto University - Aalto-yliopisto @aalto.fi · 28/04/2025
Better charts and keyboards by simulating how people behave with digital interfaces: research from @oulasvirta.bsky.social & co. is where a new kind of AI meets HCI. www.aalto.fi/en/news/ai-t... ➡️ First author @danqingshi.bsky.social explains more in the thread: bsky.app/profile/danq...
aalto.fi
AI that mirrors how humans behave can drive better designs for keyboards and charts | Aalto University
The human-like performance of these AI models is also transparent, paving the way for explainable AI and better human-computer interaction.
131
Antti Oulasvirta @oulasvirta.bsky.social · 27/04/2025
I was honored to give the closing keynote at the Everyday AR through AI-in-the-Loop workshop at #chi2025 yesterday on simulated users. In a nutshell: training user models directly in simulators enables tackling more realistic problems and opens up new applications.
030
Reposted by Antti Oulasvirta
Andrés Lucero @andrikos.bsky.social · 24/04/2025
Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems #chi2025 are now online! dl.acm.org/doi/proceedi...
dl.acm.org
Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems | ACM Conferences
CHI: Conference on Human Factors in Computing Systems
0179
Reposted by Antti Oulasvirta
ELLIS @ellis.eu · 15/04/2025
🇫🇮💡 Wondering what the new @ellisinstitute.fi is all about and its #AI game plan? Check out the recent Acatiimi interview with Director @samikaski.bsky.social for insights on their mission, professorship investments, and Finland's AI impact. #Finland #ELLISInstitute
092
Reposted by Antti Oulasvirta
Andrés Lucero @andrikos.bsky.social · 15/04/2025
Annual Helsinki PreCHI event opening by @oulasvirta.bsky.social. First up, Rungjun Ma presents “Privacy Perceptions of Custom GPTs by Users and Creators.” #chi2025
041
Reposted by Antti Oulasvirta
Jacy Reese Anthis @jacyanthis.bsky.social · 04/04/2025
Should we use LLMs 🤖 to simulate human research subjects 🧑? In our new preprint, we argue sims can augment human studies to scale up social science as AI technology accelerates. We identify 5 tractable challenges and argue this is a promising and underused research method 🧪🧵 arxiv.org/abs/2504.02234
arxiv.org
LLM Social Simulations Are a Promising Research Method
Accurate and verifiable large language model (LLM) simulations of human research subjects promise an accessible data source for understanding human behavior and training new AI systems. However, resul...
3207
Reposted by Antti Oulasvirta
Andrii Matviienko @andriimatviienko.bsky.social · 31/03/2025
I am happy to share that with the joint effort of the Nordic HCI community, there is a website that accommodates Nordic reception at CHI, yearly CHI accepted works, a list of contributing institutions, and pre-chi events. www.chi-nordics.eu
chi-nordics.eu
CHI Nordics
0103
Antti Oulasvirta @oulasvirta.bsky.social · 29/03/2025
Want to learn how to build cognitive models using reinforcement learning? Join our course at #CHI2025: "C13: Introduction to Computational Cognitive Modeling"
060
Reposted by Antti Oulasvirta
Andrés Lucero @andrikos.bsky.social · 19/03/2025
#ProblemReframing: looks at whether working with #AI, namely #LLMs, benefits designers in devising high-quality problem frames. Shows how generative AI can fail at supporting realistic design tasks. 💁🏻💡🤖 #CHI2025 users.aalto.fi/~luceroa1/re... @joongishin.bsky.social @oulasvirta.bsky.social
Flowchart comparing manual, direct, free-form, and structured approaches to problem framing with designers and LLMs, highlighting the structured method’s nine-step process by Dorst.
131
Reposted by Antti Oulasvirta
Chaz Hutton @chazhutton.com · 11/12/2024
Googling Stuff: Then v Now.
This title if the comic is ‘Googling Stuff…’
The comic shows two columns: on the left is “Then” showing search results with one thing listed as “the thing you want”

On the right column is ‘Now’ - also showing search results but in this case it’s a whole bunch of stuff you don’t need:

AI TAKING A WILD STAB AT IT WITH SOME
BLATANT MISINFORMATION

SPONSORED RESULT

SPONSORED RESULT

SPONSORED RESULT

SPONSORED RESULT

PEOPLE ALSO ASK

VIEW PRODUCTS

And then right at the bottom just off screen is ‘the thing you want’
221167686347
Reposted by Antti Oulasvirta
Mike Frank @mcxfrank.bsky.social · 06/03/2025
AI models are fascinating, impressive, and sometimes problematic. But what can they tell us about the human mind? In a new review paper, @noahdgoodman.bsky.social and I discuss how modern AI can be used for cognitive modeling: osf.io/preprints/ps...
Figure 1. A schematic depiction of a model-mechanism mapping between a human learning system (left side) and a cognitive model (right side). Candidate model mechanism mappings are pictured as mapping between representations but also can be in terms of input data, architecture, or learning objective.Figure 2. Data efficiency in human learning. (left) Order of magnitude of LLM vs. human training data, plotted by human age. Ranges are approximated from Frank (2023a). (right) A schematic depiction of evaluation scaling curves for human learners vs. models plotted by training data
quantity.Paper abstract
26425
Antti Oulasvirta @oulasvirta.bsky.social · 12/03/2025
Computational models of human perception have been stuck with visual saliency, which has little ecological validity. Who looks at a display with no task in mind? One reason for this fixation has been that there simply are no high quality datasets for other tasks. Well now there is for visual search:
162
Antti Oulasvirta @oulasvirta.bsky.social · 11/03/2025
The paper presents findings on visual search in a large dataset (N=84) including over 900 real-world GUIs. And the dataset is released too
050
Antti Oulasvirta @oulasvirta.bsky.social · 10/03/2025
Now this is interesting: Selder et al. ask what makes a biomechanical model 'breathe' and study the effects of reward components on emergent movement patterns: arxiv.org/pdf/2503.02571 Reward design for human models is an open problem, we need more more work like this!
020
Reposted by Antti Oulasvirta
ELLIS Institute Finland @ellisinstitute.fi · 06/03/2025
📣 Our call for Principal Investigators in artificial intelligence and machine learning closes this Sunday, March 9! 👇
052
Reposted by Antti Oulasvirta
ELLIS Institute Finland @ellisinstitute.fi · 04/03/2025
As a Principal Investigator at ELLIS Institute Finland, you can work with some of the world's best AI + ML students. Plus: compute + infrastructure (@lumi-supercomputer.eu) & the @ellis.eu network. Read more: fcai.fi/news/2024/11... 📣 Then apply here by March 9: www.ellisinstitute.fi/PI-recruit
ellisinstitute.fi
Principal Investigator positions at ELLIS Institute Finland | ELLIS Institute Finland
Now recruiting new PIs in artificial intelligence and machine learning
095