iiinova — where your digital self keeps evolving

Serge Belongie @serge.belongie.com · 02/10/2026

In Oslo today for the GBIF Science Symposium 🇳🇴🌱

Serge Belongie @serge.belongie.com · 01/10/2026

It’s ELLIS PhD application season! 🎓 @belongielab.org has openings in CV/ML; fine-grained analysis of multimodal data; generative models for images and video; narrative analysis and misinformation detection, self-supervised learning; human-in-the-loop computing. Due date: 31-Oct-2026 🎃

1125

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

Next stop at @eccv.bsky.social: X-REASON workshop on Visual Perception and Reasoning in the Interactable World, to talk about challenges in fine-grained image analysis xreason-workshop.github.io

xreason-workshop.github.io

X-REASON | ECCV 2026 Workshop

ECCV 2026 Workshop on Visual Perception and Reasoning in the Interactable World.

020

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

Reposted by Serge Belongie

ELLIS @ellis.eu · 01/09/2026

REMINDER – Call for Sessions! The ELLIS UnConference comes to Paris on 8 Dec, kicking off the @neuripseurope.bsky.social satellite event. Submit proposals for 2-hour sessions on ML and its applications—any format welcome! ⏰ Due: 15 Sept 🔗 ellis-unconference.github.io #NeurIPS2026

Call for Sessions at the 2026 ELLIS UnConference in Paris, Dec 8th.

022

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

It was our privilege to host you! ✨🔭

010

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

Reposted by Serge Belongie

Silpa Vadakkeeveetil Sreelatha @silpavs.bsky.social · 02/07/2026

Presenting RAIGen at #ICML2026 in Seoul! Can we automatically surface rare, underrepresented attributes in text-to-image diffusion models, with no prior knowledge of what they are? Come meet me in poster session! 📅 Wed Jul 8, 10:30–12:15 KST 📍 Hall A, #3308

121

Reposted by Serge Belongie

NeurIPS Europe @neuripseurope.bsky.social · 24/06/2026

NeurIPS Europe is launching a Start-Up Sponsorship Package for early-stage teams who want a seat at one of the world's premier AI events. This year, NeurIPS happens simultaneously in Atlanta, Sydney, and Paris (where we expect 4,000, researchers, engineers, founders, and students). 1/2

175

Reposted by Serge Belongie

ELLIS @ellis.eu · 24/06/2026

🎓 G-Research is supporting the #ELLISPhD Program with scholarships for 36 students across Paris 🇫🇷, Tübingen 🇩🇪, Munich 🇩🇪 & Amsterdam 🇳🇱 covering fees and living expenses from 2026–2028. Get more details: bit.ly/3QwAFBb

0113

Serge Belongie @serge.belongie.com · 23/06/2026

Thank you for the invitation @munichcenterml.bsky.social! I’m grateful for the opportunity to spread the word about @ellis.eu and present recent research on fine grained image analysis 🙌

090

Reposted by Serge Belongie

GBIF @gbif.org · 22/05/2026

🌍 25 years of enabling open access to biodiversity data. 🤝 25 years of global collaboration. 🌱 25 years of supporting research and policy worldwide. 🥳 🎂 We’re celebrating 25 years of GBIF on #InternationalDayForBiologicalDiversity, made possible by our incredible network. 💚 #BiodiversityDay

0165

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

The work aims to move embodied AI evaluation from ranking to diagnosis, and to provide a more extensible and reproducible foundation for assessing physical intelligence. (3/4)

110

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

Instead of relying on binary success rates, MetaFine disentangles manipulation competency into understanding, perception, and controlled behavior, revealing hidden failure modes in current VLA and robotic policies. (2/4)

110

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

Reposted by Serge Belongie

ELLIS @ellis.eu · 19/05/2026

🎉 7 new ELLIS Units join our network Units Franconia 🇩🇪, Grenoble 🇫🇷, and NRW 🇩🇪 strengthen existing hubs; Units Slovenia 🇸🇮and Sweden 🇸🇪 add new countries; Units Czechia 🇨🇿& Denmark 🇩🇰 expand from city to national Units. Learn more: bit.ly/4nN3vcD

0286

Reposted by Serge Belongie

NeurIPS Europe @neuripseurope.bsky.social · 17/05/2026

FAQ on NeurIPS Europe: NeurIPS Europe is an official NeurIPS 2026 satellite event taking place in Paris, France, alongside the main conference in Sydney and the other satellite event in Atlanta. NeurIPS authors can present their papers at any of the three locations, subject to space availability.

25218

Reposted by Serge Belongie

Oisin Mac Aodha @oisinmacaodha.bsky.social · 15/05/2026

🎓 Announcing the 1st Bath Summer School in Machine Learning 📅 5–7 August 2026 | 📍 University of Bath Topics: ODEs/SDEs, Bayesian methods, Self-Supervised Learning, World Models Open to PhDs, postdocs & staff at EU/UK universities www.bathmlsummerschool.org

0169

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

References: Wei et al., "Fine-Grained Image Analysis with Deep Learning: A Survey," TPAMI 2022 arxiv.org/abs/2111.06119 Yu et al., "Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation," ICLR 2026 arxiv.org/abs/2504.14988

110

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

If we want to provide researchers tools for scientific discovery, we must focus on OOD, as that is exactly where one finds the loose threads to tug that lead to old theories toppling and new theories emerging.

130

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

Is this just a matter of scale? Can we — or should we — simply shove all the expert knowledge we can collect into ever larger VLMs? Can we approach it as a mixture-of-experts and/or a matter of agentic coordination? Time will tell.

121

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

Does this mean the VLMs are dumb? Not necessarily. In many cases, the vision encoder has the capability to discriminate the classes, but it gets overruled in the process of aligning with the language modality. The following example from the Home Shopping Network provides a useful analogy.

120

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

As the Generative AI era emerged, with CLIP-style encoders and open-world chat-based interfaces, one can ask how well off-the-shelf VLMs can solve the fine grained classification problem.

110

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

In these domains, we often face the additional challenge of long-tailed distributions, meaning that some categories have abundant examples, while many categories have scant coverage.

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 · 24/03/2026

Congratulation Edwige Cyffers, @pierremarion.bsky.social, and all of team Paris on this milestone for the machine learning community! 🎉🇫🇷

1163

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

— whether one likes it or not — transformer archtectures all the way down. This new survey article by @aicentre.dk PhD students @zhaochongan.bsky.social, @jiaangli.bsky.social, et al. provides an overview of video understanding techniques spanning geometry and semantics circa 2026. (2/3)

1120

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

71275

Reposted by Serge Belongie

Danmarks Grundforskningsfond @dg.dk · 10/03/2026

– Teknologien er utrolig, ja, men den er ikke guddommelig. @serge.belongie.com fra DG's @aicentre.dk 👇🔒 www.weekendavisen.dk/samfund/aipo...

weekendavisen.dk

AIpokalypsen aflyst

Ro på. Kunstig intelligens vil tage vores arbejde og skabe en total omvæltning! Eller vil den?

073

Reposted by Serge Belongie

FGVC Workshop @fgvcworkshop.bsky.social · 03/03/2026

How does AI interact with culture? We’re thrilled to have Dr. Maria Antoniak (@mariaa.bsky.social) join us at FGVC! Her interdisciplinary work on AI in the humanities brings a new perspective to our workshop: the fine-grained categorization of the intangible parts of culture. See you at #CVPR2026!

0227

Reposted by Serge Belongie

Nico Lang @nicolang.bsky.social · 24/02/2026

Super excited to have this work out, led by our amazing Lucia Gordon (@luciagordon.bsky.social): “MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training” Project page: mmearth-bench.com Paper preprint: arxiv.org/abs/2602.06285 Code and dataset: github.com/lgordon99/mm... [1/n]

174