iiinova — where your digital self keeps evolving

We aspire to cultivate the next generation of AI researchers — those who will be the Keplers and Galileos of artificial intelligence. Researchers who will transform empirical mystery into theoretical clarity, and in doing so, redefine the foundations of intelligence itself. (7/7)

010

Like Brahe, we are navigating a universe of patterns, charting phenomena whose significance may only become clear in hindsight. Our ambition is to go beyond observation. (6/7)

We believe AI today is at a similar juncture. We are observing extraordinary capabilities in large-scale models — emergent behaviors, generalization across modalities, alignment challenges — but we lack an elegant theory to explain what we see. (5/7)

140

Brahe didn’t formulate the laws of planetary motion, nor did he have the mathematical tools to do so. But through relentless observation and accurate measurement, he assembled a foundation of data that enabled the breakthroughs of Kepler and Galileo. (4/7)

100

In front of our building stands a statue of Tycho Brahe — a tribute not just to Denmark’s scientific heritage, but to the spirit of inquiry that defines our field today (3/7)

Østervold Observatory - Wikipedia

You can read more about the old observatory (the current home of P1) in this Wikipedia article (2/7)

en.m.wikipedia.org

This morning at P1 a handful of lucky of lab members got to see the telescope while centre secretary Björg had the dome open for a building tour 🔭 (1/7)

1163

Menglin is now a research scientist at Meta in NYC (5/5)

000

On 24 downstream tasks spanning different domains, VPT beat all other transfer learning baselines, even surpassing full fine-tuning in 20 cases, while maintaining the advantage of storing significantly fewer parameters (less than 1% of backbone parameters) for each task. (3/5)

100

What is the best way to adapt large pre-trained vision models to downstream tasks in terms of effectiveness and efficiency? Drawing inspiration from the recent advances on prompting in NLP, Menglin and colleagues proposed a simple and efficient method: Visual Prompt Tuning (VPT) (2/5)

100

Belongie Lab @belongielab.org · 07/04/2025

Time to revive the Belongie Lab Throwback Thursday tradition we had started in the before times 🙌 Today's #tbt is Jia et al. "Visual Prompt Tuning," from ECCV 2022 (1/5)

1114

New study with @iaugenstein.bsky.social’s group analyzing the interplay between photos and text in the news

042

Reposted by Belongie Lab

Zhaochong An @zhaochongan.bsky.social · 11/02/2025

Thrilled to announce "Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation" is accepted as a Spotlight (5%) at #ICLR2025! Our model MM-FSS leverages 3D, 2D, & text modalities for robust few-shot 3D segmentation—all without extra labeling cost. 🤩 arxiv.org/pdf/2410.22489 More details👇

1257

Reposted by Belongie Lab

Nico Lang @nicolang.bsky.social · 24/01/2025

Recordings of the SSL4EO-2024 summer school are now released! This blog post summarizes what has been covered: langnico.github.io/posts/SSL4EO... Recordings: www.youtube.com/playlist?lis... Course website: ankitkariryaa.github.io/ssl4eo/ [1/3]

Screenshot of the course website for "SSL4EO: Self-Supervised Learning for Earth Observation"

33615

Belongie Lab @belongielab.org · 15/01/2025

Learn more about Srishti’s research at www.srishti.dev 🙌

0132

Belongie Lab @belongielab.org · 21/12/2024

From San Diego to New York to Copenhagen, wishing you Happy Holidays!🎄

0404

Bonus! Our Visipedia friends at MIT, UCL, iNat, UoE, and UMass will be presenting INQUIRE inquire-benchmark.github.io Authors: E. Vendrow, O. Pantazis, A. Shepard, G. Brostow, K. E. Jones, @oisinmacaodha.bsky.social, @sarameghanbeery.bsky.social, G. Van Horn 🗓️ 13 Dec 11 a.m. PST — 2 p.m. PST

0133

Concept Denoising Score Matching for Responsible Text-to-Image Generation openreview.net/pdf?id=Sqf4j... Authors: @silpavs.bsky.social, Sauradip Nag, @serge.belongie.com, Muhammad Awais, Anjan Dutta 🗓️ Safe Generative AI Workshop, East Exhibition Hall A - Sun 15 Dec, 8:15 a.m. PST (5/5)

openreview.net

150

NeurIPS Poster DeNetDM: Debiasing by Network Depth ModulationNeurIPS 2024

DeNetDM: Debiasing by Network Depth Modulation neurips.cc/virtual/2024... Authors: @silpavs.bsky.social*, Adarsh Kappiyath*, Abhra Chaudhuri, Anjan Dutta (* Equal contribution) 🗓️ East Exhibit Hall A-C #4309 - Thu 12 Dec 11 a.m. PST — 2 p.m. PST (4/5)

neurips.cc

130

calm-workshop-2024.github.io

🗓️ Dec 14 @mariaa.bksy.social will be speaking at the Workshop on Causality and Large Models calm-workshop-2024.github.io (3/5)

Home

First Workshop on Causality and Large Models (C♥️LM) @ NeurIPS 2024

140

NeurIPS Poster LoQT: Low-Rank Adapters for Quantized PretrainingNeurIPS 2024

LoQT: Low-Rank Adapters for Quantized Pretraining: neurips.cc/virtual/2024... Authors: @sloeschcke.bsky.social, @madstoftrup.bsky.social, @mkastoryano.bsky.social, @serge.belongie.com, @vesteinns.bsky.social 🗓️ West Ballroom A-D #6104 - Thu 12 Dec 4:30 p.m. PST — 7:30 p.m. PST (2/5)

neurips.cc

141

Belongie Lab @belongielab.org · 25/11/2024

With @neuripsconf.bsky.social right around the corner, we’re excited to be presenting our work soon! Here’s an overview (1/5)

1166

Here’s a starter pack with members of our lab that have joined Bluesky

go.bsky.app

Belongie Lab

Join the conversation

0134

Reposted by Belongie Lab

Sebastian Loeschcke @sloeschcke.bsky.social · 18/11/2024

Ever wanted to train your own 13B Llama2 model from scratch on a 24GB GPU? Or fine-tune one without compromising performance compared to full training? 🦙 You now can, with LoQT: Low-Rank Adapters for Quantized Pretaining! arxiv.org/abs/2405.16528 1/4

23111

Reposted by Belongie Lab

Jiaang Li @jiaangli.bsky.social · 19/11/2024

🤔Do Vision and Language Models Share Concepts? 🚀 We present an empirical evaluation and find that language models partially converge towards representations isomorphic to those of vision models. #EMNLP 📃 direct.mit.edu/tacl/article...

2267

Reposted by Belongie Lab

Sebastian Loeschcke @sloeschcke.bsky.social · 19/11/2024

Join us for the 𝗣𝗿𝗲-𝗡𝗲𝘂𝗿𝗜𝗣𝗦 𝗣𝗼𝘀𝘁𝗲𝗿 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 in Copenhagen! 🗓️ 𝗪𝗵𝗲𝗻: 16:00–18:00, Nov. 22, 2024 📍 𝗪𝗵𝗲𝗿𝗲: Entrance Hall, Gefion, Øster Voldgade 10, 1350 København K. Present or explore European contributions to NeurIPS 2024 and connect with colleagues. 👉 𝗜𝗻𝗳𝗼 & 𝘀𝗶𝗴𝗻-𝘂𝗽: www.aicentre.dk/events/pre-n...

1123

Reposted by Belongie Lab

Maria Antoniak @mariaa.bsky.social · 19/11/2024

I'm recruiting 1-2 PhD students to work with me at the University of Colorado Boulder! Looking for creative students with interests in #NLP and #CulturalAnalytics. Boulder is a lovely college town 30 minutes from Denver and 1 hour from Rocky Mountain National Park 😎 Apply by December 15th!

A photo of Boulder, Colorado, shot from above the university campus and looking toward the Flatirons.

9302136

Belongie Lab @belongielab.org · 19/11/2024

Thanks for the tip! We did the same for @belongielab.org 💫