iiinova — where your digital self keeps evolving

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 05/08/2025

With that in mind we envision Reality Proxy. Check out the video teaser of a world interactable via proxies: youtu.be/F2ul_68PrD0, and stay tuned for more at ACM UIST Conference 2025 in Busan, Korea Paper: lnkd.in/dFXdc2Bw

youtu.be

Reality Proxy: Fluid Interactions with Real-World Objects in MR via Abstract Representations

YouTube video by Blended Intelligence Research & Devices

0132

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 05/08/2025

Over the last two years we have seen an acceleration on AI, but if AI is going to enable humans in their day to day tasks, it most probably will be via XR. The issue then is if a selection has real-world consequences, we will need great precision to interact.

191

Reposted by Dr. Mar Gonzalez-Franco

John Holbein @johnholbein1.bsky.social · 03/05/2025

At least they’re being honest, right?

5474

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 28/04/2025

This precisely was something we tried to address and quantify in the VALID avatars. We found that ingroup participants were much better at determining the ethnicity of the avatars. And outgroups just had low accuracy labeling MENA, AIAN, NHPI and Hispanics. github.com/xrtlab/Valid...

060

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 21/04/2025

It lights my day whenever I see new research enabled by the easiness of use of the @msftresearch.bsky.social #RocketboxAvatars

070

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 18/04/2025

To me experiments (on an homogeneous population) with 40+ participants are suspicious. Maybe they didn’t find significance with less but just trends so they added people until it was significant. Sometimes a larger sample means higher probability of significance. murphyresearch.com/sample-size-...

murphyresearch.com

Sample Size: Is Bigger Always Better?

By now, many of us have seen the recent AT&T commercials featuring a man dressed in a suit asking a group of adorable small children seated around a table "Which is better…bigger or smaller?"

050

Reposted by Dr. Mar Gonzalez-Franco

Kasper Hornbæk @khornbaek.bsky.social · 13/04/2025

Come work with Teresa Hirzle and me in a fully-funded PhD fellowship on extended reality and behavior change. The full add is at employment.ku.dk/phd/?show=16..., the application deadline is May 12th, and we will both be at #chi2025 to discuss. If you are not, feel free to reach out in other ways.

employment.ku.dk

PhD fellowship in extended Reality for Behaviour Change at The Pioneer Centre for AI

0116

Reposted by Dr. Mar Gonzalez-Franco

Metaverse @metaverse.metaver.se · 08/04/2025

»Researchers Catalog 170+ Text Input Techniques to Improve Typing in XR« www.roadtovr... #Metaverse #VirtualWorlds #XR #VR #MR #AR #BeyondPictures

011

Reposted by Dr. Mar Gonzalez-Franco

Android @android.activitypub.awakari.com.ap.brid.gy · 08/04/2025

Researchers Catalog 170+ Text Input Techniques to Improve Typing in XR Efficient text entry witho... www.roadtovr.com/xr-text-trove-vr-a… #Guest #Articles #News #XR #Industry #News Event Attributes

011

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 05/04/2025

Just ported all my Twitter/X posts to BlueSky with @en.blueark.app for $6. It’s a small action, @bsky.app is open for everybody to train their AIs. Now everyone can use the historic of my human created content. And not only xAI. Data dignity they say…

140

Reposted by Dr. Mar Gonzalez-Franco

Michael Wiesing @vrneuroscience.bsky.social · 31/03/2025

We have a new position for someone with a strong computer science VR background to work on the PRESENCE project. This would be at the Event Lab, Institute of Neurosciences of the University of Barcelona. If you are interested, you must apply through this website: lnkd.in/d6QYQKYA #VRcademicSky

0109

Reposted by Dr. Mar Gonzalez-Franco

The XR Research Digest @xrdigest.bsky.social · 26/03/2025

Can AR-guided tunnels improve motor precision? New research tested HoloLens 2 hand-tracking with 3D holographic trajectories, showing improved performance and positive clinician acceptance. doi.org/10.1007/s100...

031

Reposted by Dr. Mar Gonzalez-Franco

Petra Isenberg @drpi.bsky.social · 25/03/2025

Interested in a Visualization/HCI PhD in France? Come join us. We have 2 positions and will accept dual-career couples as well: www.linkedin.com/jobs/view/41... jobs.inria.fr/public/class...

linkedin.com

Inria hiring PhD position in Visualization and HCI in Gif-sur-Yvette, Île-de-France, France | LinkedIn

Posted 5:08:26 PM. 📢 We are recruiting two PhD candidates to work on data visualization for non-planar displays at…See this and similar jobs on LinkedIn.

032

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 25/03/2025

You can check out the work next month at @iclr-conf.bsky.social Bi-Align (bialign-workshop.github.io) and FM-wild (fm-wild-community.github.io) workshops: “PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos” Or start playing right now :)

020

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 25/03/2025

But how do we know if our data is any good? We asked 35k humans in Prolific about how correct and useful they found the suggested actions in reference to every video. Now we opensource the new dataset alongside the human ranks. github.com/google/parse... and all the data generation prompts.

github.com

GitHub - google/parse-ego4d: Dataset and code for generating 18,000 action suggestions via LLM querries for EGO4D dataset validated by 36,171 human annotations.

Dataset and code for generating 18,000 action suggestions via LLM querries for EGO4D dataset validated by 36,171 human annotations. - google/parse-ego4d

130

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 25/03/2025

But really as it happens with all datasets, the key is on “How to make data useful?” That was our goal with PARSE-Ego4D parse-ego4d.github.io we augment the existing narrations and videos by providing 18k suggested actions using the latest of VLMs. This can be useful to train a future AI agents.

111

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 25/03/2025

Ego4D is an incredible anthropological dataset. With over 3600 hours of videos (5 months of human activities) in first person view with written narrations from all over the world ego4d-data.org/fig1.html. (Always reminds me of this movie by #IsabelCoixet youtu.be/bYI3A6WLMBU)

youtu.be

Spain in a day - Tráiler

YouTube video by GRUP MEDIAPRO

171

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 23/03/2025

But also: Not all avatars are created equal ⚠️. We did a deep study on preferences (presented at ISMAR 2023 arxiv.org/pdf/2304.01405) and realism matters quite a lot for work scenarios. most people don’t find acceptable a cartoon avatar…

010

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 23/03/2025

I love how well the work on bringing avatars to video conferences as an alternative to camera on/off is aging. Check out our work on avatars via virtual cameras on regular conferences on our paper AllTogether. www.microsoft.com/en-us/resear...

microsoft.com

AllTogether: Effect of Avatars in Mixed-Modality Conferencing Environments - Microsoft Research

We developed AllTogether, a system that provides voice-only participants with the option to be represented by an avatar in a call with other video participants. We propose avatars as a way to expand t...

130

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 21/03/2025

From the knowledge acquired during the pandemic. We can all agree that a policy of letting the virus roam through the flocks will 1) limit containing the spread and 2) increase mutations… and that can end badly. For birds and humans. But hey, I am not the secretary of health. So what do I know?

020

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 14/03/2025

@ben.roadtovr.com I know you liked LocomotionVault.github.io so you will probably like this one too

locomotionvault.github.io

Done

010

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 14/03/2025

Welcome to the family of significant VR researchers @pedrolopes.org!! I hear the banquet this year was splendid :)

151

Reposted by Dr. Mar Gonzalez-Franco

Altmetric @altmetric.com · 13/03/2025

Mike spotted this before the rest of us. 🫡 Publications from 2025 are shared more on Bluesky than on X/Twitter.

161749427

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 13/03/2025

More over... we put all of this in an interactive dataset for people to explore each of the techniques and geek around😎 xrtexttrove.github.io some are wild!

140

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 13/03/2025

Read more & dive to text input: Arpit Bhatia, Moaaz Hudhud Mughrabi, Diar Abdlkarim, Massimiliano Di Luca, Mar Gonzalez-Franco, Karan Ahuja, Hasti Seifi (2025)"Text Entry for XR Trove (TEXT): Collecting and Analyzing Techniques for Text Input in XR." ACM CHI PDF: drive.google.com/file/d/1a6TH...

drive.google.com

XRTextTrove_Camera Ready.pdf

120

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 13/03/2025

I personally think the solution will in part become a motion retargeting problem as soon as we can provide good haptic feedback. For as long as the human has to move fingers from point A to point B, we will have physical limitations to typing…

110

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 13/03/2025

3) there is a tendency to think custom hardware will solve this gap but so far it hasn’t. And keyboard format still delivers the highest wpm.

110

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 13/03/2025

2) external surfaces and fingertips/transparency of hands seem to be preferable as ways to improve performance compared to midair gestures.

100

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 13/03/2025

1) vr text input has a ceiling effect for as long as we only use 1 or 2 fingers we will never get better than hunt and peck methods. * more or less we find that every additional finger used increases 5 wpm (words per minute). Users of multi finger solutions (touch typers) can reach 40-50 wpm.

120

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 13/03/2025

Ever wondered why is so hard to write in VR/XR? We too 😅. Check this new work to appear in ACM CHI: xrtexttrove.github.io We (@arpitbhatia.bsky.social et al) analyzed 176 papers and text entry techniques inside XR and found that:

1182

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 10/03/2025

Also look at this: “mundus sine cesaribus”, the CEO of bluesky

000

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 10/03/2025

Ok! I have been using bluesky now for a bit. Unlike Mastodon, I really think it’s properly good and with enough critical mass and I am finally moving out of X. Moving forward: find me at @twimar.bsky.social

100

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 08/03/2025

Catch up with @ejgonz.bsky.social at @sxsw.com Innovation Awards 🏆. He will be presenting our example of Augmented Object Intelligence XR-objects.github.io He also rebumped the opensource github project now running Gemini Flash2. Very smooth 👍

xr-objects.github.io

Augmented Object Intelligence with XR-Objects

Augmented Object Intelligence with XR-Objects.

050

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

How do we do this? We enable users gaze memory while in an XR/VR running OCR for text. Our setup reduces the number of re-prompts to 1 in 68% of the cases. The same query without shared context can take 4-5 attempts. Future work: Include multimodal prompts beyond just text.

010

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

EmBARDiment explores: - how much we can simplify LLM prompts if the AI agent shares context and content understanding with the user (hint: a lot!). - highly homogeneous vs heterogeneous content. - long vs short contextual memory.

110

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

000

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

100

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

We will also present “Beyond the Phone: Exploring Context-Aware Interaction Between Mobile and Mixed Reality Devices" by Fengyuan Zhu et al. showcasing the many interesting ways in which we can bring our phones inside VR. Paper:...

100

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

At @IEEEVR we present “EmBARDiment: an Embodied AI Agent for Productivity in XR" by @riccardobovoHCI et al. showing how powerful AI agents can be when they are aware of the content around us, driven by contextual inputs like gaze. Web: embardiment.github.io Code: soon

100

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

020

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 06/03/2025

Next week at #IEEEVR we present “EmBARDiment: an Embodied AI Agent for Productivity in XR" by @riccardobovo.bsky.social et al. showing how powerful AI agents can be when they are aware of the content around us, driven by contextual inputs like gaze. Web: embardiment.github.io Code: coming soon

1131

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 26/02/2025

Super proud of our collaboration with academia on advancing inputs for XR receiving a recognition by @acm-sigchi.bsky.social. 🙌 @ejgonz.bsky.social, @kenpfeuffer.bsky.social, @hansgellersen.bsky.social, Hasti, Karan, Max, Andrea

2111

Reposted by Dr. Mar Gonzalez-Franco

Doğa Doğan @dogadogan.bsky.social · 27/01/2025

Stoked that 𝐗𝐑-𝐎𝐛𝐣𝐞𝐜𝐭𝐬 - our "Augmented Object Intelligence" concept from UIST'24 - was selected as a 2025 @SXSW.com 🏆 Innovation Awards Finalist!🤩 www.sxsw.com/interactive/... @twimar.bsky.social @ejgonz.bsky.social @googlesearch.bsky.social @acm-sigchi.bsky.social 🎉

sxsw.com

2025 SXSW Innovation Awards Finalists Announced

50+ finalists provide a glimpse of the future in 11 different categories ranging from Artificial Intelligence to Health & Biotech to Community Empowerment.

141

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 07/01/2025

Cool points (pun intended) Would like to see the interactivity enabled by an LLM that helps describe the context

010

Dr. Mar Gonzalez-Franco @twimar.bsky.social · 01/01/2025

I guess sometimes when we migrate we bring a baggage too.. when @davledo.bsky.social and @fbrudy.bsky.social invited me to talk at @autodeskresearch.bsky.social he prepared a super cute visual summary that deserves porting ;) challenges stand stronger now that we kind of tackled the OS in the room 🐘

040