Profile avatar
unireps.bsky.social
https://unireps.org Discover why, when and how distinct learning processes yield similar representations, and the degree to which these can be unified.
35 posts 133 followers 77 following
Regular Contributor

🔵🔴 Curious about unifying representations and sharing breakthrough ideas with fellow scientists? The ELLIS (@ellis.eu) UniReps Speaker Series is your chance to dive in!

🔵🔴Better late than never! We're excited to finally share pictures from the Best Paper Awards Ceremony of the last edition of #UniReps at #NeurIPS! 📸🏆 Check them out in our latest blog post: 👉 unireps.org/blog/2025/un... Congratulations again to all the authors!🎉

🚀 Did you attend the 2nd UniReps workshop on Unifying Representations in Neural Models? We’d love your feedback! Take 2 minutes to fill out our form & help shape future workshops in ML, Neuroscience, & Cognitive Science.📋 docs.google.com/forms/d/e/1F...

We had an amazing poster session! Congratulations again to all the authors🎉🎉

🎉 Good news! The fun doesn’t stop after the first social! Join us for a joint party with @neurreps.bsky.social and NeuroAI. Don’t miss out—scan the QR code to register now! 🚀

🔵🔴🎉 Stefanie Jegelka from MIT is the last speaker of our UniReps workshop, talking about "Parameter Symmetries in Neural Networks: what they affect and what to do with them"

🔵🔴 Excited to hear from Neel Nanda on "Open Problems in Universality: A mechanistic interpretability perspective" 👏

Welcome back! 🥳 Starting off after lunch is Marco Cuturi, talking about "On Using Optimal Transport Distances to Regularize Representation Learning". 🔵🔴

We are now starting the panel discussion with Matthew Leavitt, Erin Grant and Alex Williams, moderated by @clementinedomine.bsky.social 😍 What an amazing panel to share perspectives of unifying representations 🔵🔴

👏 The last presenter before the discussion session is Konstantin Hemker with his contribution titled "Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities"

Up next is Jacob S. Prince, presenting "Representation with a capital 'R': measuring functional alignment with causal perturbation" 🎉

Next in line here at UniReps workshop is "A Framework for Standardizing Similarity Measures in a Rapidly Evolving Field", presented by @nacloss.bsky.social from MIT 🔵🔴

Coming right up - "Modern Hopfield Networks meet Encoded Neural Representations - Addressing Practical Considerations" by Tanveer Syeda-Mahmood from IBM Research ✨

We continue with Chenyu Wang, presenting "An Information Criterion for Controlled Disentanglement of Multimodal Data" 👏

👏 Coming up next, @itsneuronal.bsky.social is presenting his research on “Equivalence between Representational Similarity Analysis, Centered Kernel Alignment, and Canonical Correlations Analysis.” 🔵🔴

Next up: Best Extended Abstract Award Oral Presentation! 🎉 @emcheng.bsky.social presents “Evidence from fMRI Supports a Two-Phase Abstraction Process in Language Models”. 🧠✨

We continue our workshop with the first contributed talk by Sarah E. Harvey on “What Representational Similarity Measures Imply about Decodable Information”

For our last invited talk this morning, we are thrilled to hear @phillipisola.bsky.social from MIT present ‘The Platonic Representation Hypothesis’ at the UniReps workshop! 🎤✨

We are now continuing with the talk by Prof. Sue Yeon Chung on “Computing with Neural Manifolds: Multi-level theory of neural representations in biological and artificial neural networks”

We have now Dr. @eringrant.bsky.social presenting ‘’Learning dynamics describe the computational role of (universal) representations’’

The workshop has just started with the opening remarks by @marcofm.bsky.social! Join us at **West** building Exhibition Hall C B3

🔵🔴The workshop is starting soon! Come join us in West building Exhibition Hall C B3 at 8:15 AM!

The UniReps Workshop is happening THIS SATURDAY at #NeurIPS 🤖🧠 Join us for a day of insightful talks and discussions with @sueyeonchung.bsky.social, @eringrant.bsky.social, @leavittron.bsky.social, @itsneuronal.bsky.social, @marcocuturi.bsky.social, Philip Isola, Neel Nanda and Stefanie Jegelka! 🎤

🎤 Excited to introduce our incredible panelists for the Panel on Unifying Representations in Neural Models 🔵🔴 📌 Saturday 14th Dec 11:45 am, West Exhibition Hall C 🌍🤖

🚨Excited for the UniReps workshop @neuripsconf.bsky.social ? Don't miss out on the mentorship program! 🚀 Sign up now to participate in this year's event and connect with our amazing community.🌟 👉 Sign up here docs.google.com/forms/d/1nUX... Help us spread the word—share widely! 🙌

🔵🔴We’re hosting a UniReps Workshop social🌟🥳 📍 Location: Moose's Down Under Bar & Grill, Vancouver 🗓️ Date & Time: Saturday, Dec 14 | 5:45 PM Don’t miss the chance to connect, relax, and have some fun. See you there! 🔵🔴

Very happy to share our new paper that will appear in @unireps.bsky.social We show improvements of zero-shot model stitching through invariance to symmetries in parameter space, and topological regularization of the latent spaces more info below 👇

First post on Bluesky! I’ll be attending #NeurIPS2024 in Vancouver this week. Excited to meet new people and chat about comp neuro, NeuroAI, and foundation models for neuroscience. Also keen to attend the NeuroAI, @unireps.bsky.social and @neurreps.bsky.social workshops! 🧠

Update on our similarity-repository 🚨 More than 200 similarity measures across 32 papers are now registered! We'll also be presenting our work as an oral at the @neuripsconf.bsky.social @unireps.bsky.social workshop! (1/6)