iiinova — where your digital self keeps evolving

Serge Belongie @serge.belongie.com · 10/09/2026

A timely topic in light of the proliferation of AI-based tools in mathematical and scientific discovery, with insights shared by thought leaders from CAISA - Det Nationale Center for AI i Samfundet, @aicentre.dk, and @nerdsitu.bsky.social in Denmark 🇩🇰 (2/2)

030

Serge Belongie @serge.belongie.com · 10/09/2026

Panel discussion at @eccv.bsky.social ECCV 2026 on The Age of LLMs: Who Is the Researcher Now? How LLMs Are Changing Search, Ideation, and Scientific Judgment, featuring @annarogers.bsky.social, @iaugenstein.bsky.social, and @robysinatra.bsky.social, moderated by Anna Rohrbach (1/2)

1153

Serge Belongie @serge.belongie.com · 08/09/2026

ECCV 2026 @eccv.bsky.social is in full swing! 🇸🇪 First stop: Visual Persuasion workshop sites.google.com/view/eccv-20...

0154

Serge Belongie @serge.belongie.com · 19/08/2026

Inspiring and thought provoking talk by @carlbergstrom.com at @aicentre.dk today on high-risk, high-return research, and why rational scientists avoid it in favor of safe, incremental projects

2151

Serge Belongie @serge.belongie.com · 20/05/2026

Fine Grained Analysis 🤝 Robotic Manipulation Evaluation MetaFine, developed in collaboration with Xiu-Shen Wei and team, provides a diagnostic meta-evaluation framework for fine-grained robotic manipulation. (1/4)

3134

Serge Belongie @serge.belongie.com · 01/05/2026

This interview provides an overview of my thoughts on how AI is developing in Europe vs. other parts of the world:

1163

Serge Belongie @serge.belongie.com · 28/04/2026

Where do we go from here? I argue that we need some "grand unified" style thinking, e.g., to marry Out of Distribution (OOD) studies with FGVC. GenAI tools perform well within-distribution, but famously confabulate in OOD settings.

131

Serge Belongie @serge.belongie.com · 28/04/2026

The presenter rehearsed his segment with a large poster of a horse, but at show time, someone replaced it with a poster of a moth. While it's evident the host spotted the mismatch, he nonetheless read the text on the TelePrompTer, describing the attributes of a horse while pointing to the moth.

https://www.digitalspy.com/fun/a339292/funny-video-home-shopping-presenter-mistakes-moth-for-horse/

110

Serge Belongie @serge.belongie.com · 28/04/2026

It turns out there's a large performance gap between the above tailored methods and leading VLMs such as Qwen and LLaVa; see the bar at the far left for iNat.

130

Serge Belongie @serge.belongie.com · 28/04/2026

State-of-the-art tailored methods for multimodal fine grained categorization, as deployed for example in the Merlin Bird ID and iNaturalist apps, achieved excellent performance using various CNN or ViT backbones circa 2021.

120

Serge Belongie @serge.belongie.com · 28/04/2026

Naming is capture. Labels supplied by humans — with all the bias that entails — confer meaning to instances that otherwise would merely be points in a high dimensional space with various measures of pairwise similarity.

110

Serge Belongie @serge.belongie.com · 28/04/2026

Fine-grained problems are characterized by (a) tightly related categories that require highly discriminative learned representations, and (b) reliance on human expertise to obtain the labels.

120

Serge Belongie @serge.belongie.com · 28/04/2026

Here is a brief overview of the talk I gave yesterday on Fine-Grained Image Analysis at the @ellis.eu Computer Vision Workshop hosted by INSAIT in Sofia, Bulgaria. Fine-grained categories sit on a spectrum with basic level categories on one end and biometrics and re-identification on the other.

120

Serge Belongie @serge.belongie.com · 28/04/2026

Challenges in Fine-Grained Image Analysis Look at this horse. The bushy tail. The big teeth. The hooves.

251

Serge Belongie @serge.belongie.com · 20/03/2026

Feeling overwhelmed by all the recent developments in video understanding? What used to require dozens of modular computational workflows involving SLAM, feature tracking, optical flow, camera calibration, multiview geometric constraints, and resnet backbones is now... (1/3)

1508

Serge Belongie @serge.belongie.com · 17/03/2026

@luciagordon.bsky.social (Harvard / P1) presents “MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training” at the @aicentre.dk Fine-Grained Analysis Collaboratory Meetup at @sdu.dk Vejle (1/2)

271

Serge Belongie @serge.belongie.com · 13/03/2026

Congratulations on your successful PhD defense today @srishtiy.bsky.social! 🎉🥂 You can learn more about Srishti's research on "Social Dimensions of AI Safety - Evaluating Values, Culture, Framing in Language & Vision Models" in this @ellis.eu spotlight: ellis.eu/news/spotlig... #WomenInELLIS

71265

Serge Belongie @serge.belongie.com · 12/02/2026

Compression is Magic One memory that stays with me from my early days of grad school in the mid-1990s was the buzz about a scrappy, yet highly effective, document classification method from CMU. [Continued on longer.blue/posts/ma2JOS... ]

031

Serge Belongie @serge.belongie.com · 30/01/2026

The main experiments from my PhD thesis took around 2 weeks to run on Berkeley's Millennium cluster (30 Sun Ultra machines) circa 1999. With that compute muscle, Jitendra, Jan, and I were able to run Shape Context matching with Thin-Plate Spline alignment followed by K-NN on the MNIST dataset. (1/3)

151

Serge Belongie @serge.belongie.com · 30/01/2026

A factor of 10 billion since 2010 😮 A couple of eye-opening slides form @sloeschcke.bsky.social's presentation at today’s @belongielab.org meeting (1/2)

2118339

Serge Belongie @serge.belongie.com · 27/01/2026

Manohar Paluri (Meta) talks about the SAM family of models for images, video, and audio at Day 2 of Machines Can Think 2026 machinescanthink.ai

000

Serge Belongie @serge.belongie.com · 26/01/2026

@yann-lecun.bsky.social beams in from a galaxy far, far away to deliver a keynote at Machines Can Think 2026 “Future AI systems will be judged not by what they can already do, but by what new tasks they can learn quickly. This requires an understanding of the world.”

130

Serge Belongie @serge.belongie.com · 26/01/2026

Machines Can Think 2026 is off to a great start with excellent keynotes by Sergey Tulyakov ( @snapinc.bsky.social) and @misovalko.bsky.social (Stealth Startup) machinescanthink.ai

12150

Serge Belongie @serge.belongie.com · 17/01/2026

The TRL vs. LFG Matrix: Mapping Tech Maturity & Organizational Will (1/6)

2182

Serge Belongie @serge.belongie.com · 14/01/2026

“AI is everywhere, but it is not everything” Amy Loutfi kicks off the 2026 WASP – Wallenberg AI, Autonomous Systems and Software Program Winter Conference in Örebro

0100

Serge Belongie @serge.belongie.com · 19/12/2025

I bookmarked this post on Quora ~8 years ago when a small startup called x.ai launched a calendar booking assistant/bot named Amy Ingram. While I only tried their system for a handful of experiments, the lukewarm review below matched my impressions of its capability.

120

Serge Belongie @serge.belongie.com · 08/12/2025

Seminar by @loicland.bsky.social @imagineenpc.bsky.social on recent advances in geospatial machine learning, including biomass estimation, at @aicentre.dk www.aicentre.dk/events/20251...

0101

Serge Belongie @serge.belongie.com · 03/12/2025

Spotted on the speaker’s display: “No Notes” indeed!

070

Serge Belongie @serge.belongie.com · 03/12/2025

A few photos from the @ellis.eu UnConference 2025 opening remarks by @vincefort.bsky.social and Søren Hauberg

2547

Serge Belongie @serge.belongie.com · 18/11/2025

Fascinating and insightful talk by @giadapistilli.com on Human-AI Companionship, presented at today’s @ellisinstitute.fi launch event in Helsinki One of the key findings is that AI chatbots fail to set boundaries when users are most vulnerable, e.g., expressing love or loneliness

160

Serge Belongie @serge.belongie.com · 13/11/2025

How it started / How it’s going See you in Copenhagen! 🇩🇰 eurips.cc #EurIPS #NeurIPS

2243

Serge Belongie @serge.belongie.com · 12/11/2025

The problem is us, with our Paleolithic vulnerabilities, our FOMO, our susceptibility to snake oil salesmen and the ELIZA effect. Say no to anthropomorphized tech solutionism and yes to stronger human institutions, fortified by ordinary technology. (11/11)

032

Serge Belongie @serge.belongie.com · 12/11/2025

Here are a couple of the points I made during yesterday’s Algoritmer, Data og Demokrati - ADD projektet Partnerkonference (Link: algoritmer.org/aktiviteter/...) (1/11)

2123

Serge Belongie @serge.belongie.com · 11/11/2025

Prof. @tokehoye.bsky.social (Aarhus University) and I have an open PhD position (jointly advised) on biodiversity monitoring with camera trap networks. Deadline: 15-Jan-2026 Please help us share this post among students you know with an interest in Machine Learning and Biodiversity! 🤖🪲🌱

12011

Serge Belongie @serge.belongie.com · 11/11/2025

Doomers, Bloomers, Deemers, Bleemers Read about Søgaard’s AGI matrix in our new CAISA Research Brief: Artificial General Intelligence and its Societal Implications caisa.dk/forskning

051

Serge Belongie @serge.belongie.com · 22/10/2025

Thank you @sarameghanbeery.bsky.social for the invitation to speak on the panel at the #CV4Ecology Workshop at @iccv.bsky.social, alongside Ryan Perroy, Joost Daniels, Justin @kitzeslab.bsky.social, and — Zooming in from the #LivingData conference in Bogotá — Tanya Berger-Wolf (1/3)

1162

Serge Belongie @serge.belongie.com · 24/06/2025

Like this, but with one more Spider-Man chilling on the ceiling

110

Serge Belongie @serge.belongie.com · 24/06/2025

Reminds me of Blade Runner 2049

020

Serge Belongie @serge.belongie.com · 24/06/2025

Keynote on opportunities in egocentric video understanding by @dimadamen.bsky.social (U. Bristol & Google DeepMind) at SCIA 2025 in Reykjavík

2150

Serge Belongie @serge.belongie.com · 23/06/2025

SCIA 2025 keynote on Deep Shape Design @pvfua.bsky.social scia2025.org/program

051

Serge Belongie @serge.belongie.com · 22/06/2025

Rasmus Larsen (DTU) makes welcome remarks at the welcome reception for SCIA 2025 Scandinavian Conference on Image Analysis June 23-25 Reykjavík, Iceland Featuring keynotes by @pvfua.bsky.social (EPFL) and @dimadamen.bsky.social (Bristol) scia2025.org

0152

Serge Belongie @serge.belongie.com · 19/06/2025

Always a pleasure to do events with @mariehoest.bsky.social 🙌🏼

120

Serge Belongie @serge.belongie.com · 13/06/2025

My favorite part of going to conferences: @belongielab.org alumni get-togethers! A big thank you to Menglin for coordinating the lunch at @cvprconference.bsky.social 🙏 Left: Tsung-Yi Lin, Guandao Yang, Katie Luo, Boyi Li; Right: Menglin Jia, Subarna Tripathi, Ph.D., Srishti, Xun Huang

0191

Serge Belongie @serge.belongie.com · 24/05/2025

Today I gave a general audience talk about AI & Society at the Bloom Festival at Søndermarken bloom.ooo It was great to get attendee feedback from all walks of life on some of the projects we are pursuing in CAISA and @aicentre.dk 📷 Stijn Janssen

1200

Serge Belongie @serge.belongie.com · 20/05/2025

P1 🤝 Gefion Advances in modern Machine Learning research need big compute, and Denmark is immensely fortunate to have a new supercomputer — Gefion — to fulfill this need (1/2)

1110

Serge Belongie @serge.belongie.com · 17/05/2025

Very cool new STEM learning platform for kids from Danish startup Hello Ada www.helloada.ai/create-with-ai

0111

Serge Belongie @serge.belongie.com · 06/04/2025

Does anyone know the source of this figure? It’s a nice illustration of the interplay between face familiarity, T-junctions, and perceived depth ordering.

182

Serge Belongie @serge.belongie.com · 03/04/2025

So far, 2,135 people have responded to the poll Søren and I posted a few days ago. Of those, 94.4% replied “Yes” to being interested in officially presenting accepted @neuripsconf.bsky.social papers in Europe. (1/7)

57924

Serge Belongie @serge.belongie.com · 31/03/2025

Great to see a familiar face at today’s @aicentre.dk seminar! @dmimno.bsky.social (Professor and Chair, Dept. of Information Science at Cornell) spoke about missed opportunities and possible paths forward for the NLP and HCI communities in the age of LLMs. (1/3)

1161