https://xitter.cf/t.co/LMh6oTnAbq Bologna - Shanghai - Stockholm

Stockholm
Joined July 2018
Most of what @the_good_ai_lab does can be described as building a connection. A bridge between frontier AI research and humanitarian action, education, and sustainability. 🌱🧵 cv4good.thegoodailab.org w/ @MSF
1
3
7
629
Pier Luigi Dovesi retweeted
#ECCV2026 by night
2
2
34
3,099
Always thought democracy was protected by education, independent press and economic inclusion. At #ECCV I learn it was about killer drones all along! All that money wasted on universities and healthcare. Good to see we're finally sending the right message to young researchers.
1
1
82
Pier Luigi Dovesi retweeted
Closing panel at #CV4GOOD, and the room is full. Joseph Redmon, Sara Beery, Lorenz Wendt and Yann Rebois on dual use, governance, and the research agenda. Moderated by Federico Tombari. #ECCV2026
1
1
14
Pier Luigi Dovesi retweeted
Jamon Van Den Hoek at #CV4GOOD on the data gap our field rarely models. Satellite coverage isn't "everywhere, all the time" — it's uneven across time and space. And conflict zones get hit twice: sparse collection, plus embargoes and restrictions on commercial imagery. #ECCV2026
1
2
35
Pier Luigi Dovesi retweeted
Corey Scher at #CV4GOOD, on damage mapping under pressure. Ukraine: 42,000+ settlements monitored, damage in over 5% of them, 90% within 360 km of the frontline. Gaza: 58 maps in the first year, roughly one a week, shared with journalists and humanitarians. #ECCV2026
1
2
107
Pier Luigi Dovesi retweeted
Back from the break at #CV4GOOD with Sara Beery (@MIT): "Targeting Human Verification for Robust Deployment of AI in Ecology." Room D2. #ECCV2026
1
2
29
Pier Luigi Dovesi retweeted
Sara Beery at #CV4GOOD. Active learning gets evaluated inductively, on a held-out test set. But ecologists want the whole pool labeled. Evaluate transductively and rare classes suddenly beat common ones — look at the pink bars. #ECCV2026
1
1
19
Pier Luigi Dovesi retweeted
Joseph Redmon (@allen_ai) at #CV4GOOD opened with: "Can we build the panopticon, but, like, for good?" Their answer isn't a vibe, it's mechanisms. License barring military, defense, police, surveillance and extractive use. Invitation-only platform. Code fully open. #ECCV2026
1
1
2
45
Pier Luigi Dovesi retweeted
#CV4GOOD at #ECCV2026 is live🌱 Room D2, Malmömässan. Half a day where computer vision sits face to face with frontline humanitarian practice — what works in the field, what fails, what's missing. The Good AI Lab × Médecins Sans Frontières. 1st edition. cv4good.thegoodailab.org
1
1
18
Pier Luigi Dovesi retweeted
Yann Rebois (@MSF) at #CV4GOOD: "The challenge is no longer only detecting features from satellite imagery; it is turning imperfect but timely AI outputs into trusted operational support for humanitarian teams." The bottleneck is operational integration. #ECCV2026
1
2
42
Pier Luigi Dovesi retweeted
Next at #CV4GOOD: Lorenz Wendt (CDL GEOHUM, Univ. of Salzburg) on EO for humanitarian action. Pipeline in one slide: request→data integration → semi-automated analysis → spatial analysis → information products → ground validation. EO services for @MSF since 2011. #ECCV2026
1
2
51
Pier Luigi Dovesi retweeted
And we're off — @dovpie opening the 1st edition of #CV4GOOD. The question isn't whether computer vision can contribute to humanitarian action. It's how to make it reliable enough for high-stakes decisions, and accountable enough to deserve trust. Full room, D2. #ECCV2026
1
2
48
Pier Luigi Dovesi retweeted
Liner is partnering with @spoticlr at #ICLR2026 — supporting Best Paper and Travel Awards for LLM research. And to celebrate, we're giving away: ✈️ Round-trip flights + hotel to #ICML2026 in Seoul 🎁 $300 Liner Credits Follow @search_liner + repost to enter by 4/27. Liner is built for research workflows. Find papers, verify sources, and write with citations in one place. See you in 🇧🇷 and 🇰🇷! @iclr_conf @icmlconf
4
230
8
225
15,944
Pier Luigi Dovesi retweeted
From stereo vision to LiDAR fusion, and the edge cases that break them. Join the next AMD AI Research Club session where Pier Luigi Dovesi, Robotics and Autonomous Systems Lead, AMD Silo AI, explores the evolving landscape of depth foundation models with Luca Bartolomei. 📅 April 16, 2026 ⏰ 4 PM CET | 10 AM CT We’ll unpack: • Virtual pattern projection • Cross-domain depth generalization • Geometry-aware perception in complex environments Built for developers, researchers, and engineers pushing the boundaries of AI perception. 👉 Register here: webinar.amd.com/Active-Stere…
4
10
1,191
We are thrilled that our group has twelve papers accepted at #CVPR2025! 🚀 Congratulations to all of our students for this great achievement! 🎉 For more details, check out: cvg.cit.tum.de
1
23
3
127
10,974
We are presenting DiffCD tomorrow morning at #ECCV2024! Come by poster 214 to discuss how to fit neural SDFs to point clouds, from a geometric perspective
Very excited to announce our paper: "DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting" at #ECCV2024! Paper: arxiv.org/abs/2407.17058 Code/project: github.com/linusnie/diffcd
5
1
28
2,011