UniReps
banner
unireps.bsky.social
UniReps
@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.
Pinned
📢 We're thrilled to announce that the UniReps workshop will return to @NeurIPSConf 25 for its 3rd edition!

🔵Check our new Call for Papers at: unireps.org/2025/call-fo...

🔴Submit your work at: openreview.net/group?id=Neu...

See you in San Diego!🌴🇺🇸
Reposted by UniReps
That was fun! Thanks for the invitation :-)
📢The first UniReps x @ellis.eu speaker series in 2026 is coming!

Come join us on 15th January at 1 pm CET with
@noagarciad.bsky.social and @thwiedemer.bsky.social !
January 15, 2026 at 1:58 PM
📢The first UniReps x @ellis.eu speaker series in 2026 is coming!

Come join us on 15th January at 1 pm CET with
@noagarciad.bsky.social and @thwiedemer.bsky.social !
January 15, 2026 at 11:01 AM
📢The first UniReps x @ellis.eu speaker series in 2026 is coming!

Come join us on 15th January at 1 pm CET with
@noagarciad.bsky.social and @thwiedemer.bsky.social !
January 12, 2026 at 2:09 PM
Starting in 30 minutes! Join us on zoom!
📢The UniReps x @ellis.eu
speaker series is back! Come join us in our next appointment 18th December 4 pm CET with @meenakshikhosla.bsky.social
and Raj Magesh Gauthaman🔵🔴
December 18, 2025 at 2:31 PM
Join us tmr!
📢The UniReps x @ellis.eu
speaker series is back! Come join us in our next appointment 18th December 4 pm CET with @meenakshikhosla.bsky.social
and Raj Magesh Gauthaman🔵🔴
December 17, 2025 at 4:02 PM
📢The UniReps x @ellis.eu
speaker series is back! Come join us in our next appointment 18th December 4 pm CET with @meenakshikhosla.bsky.social
and Raj Magesh Gauthaman🔵🔴
December 12, 2025 at 10:48 AM
🔵🔴 We are now at the last invited talk of today! Eva Dyer from the University of Pennsylvania is presenting “Learning Who’s Who in the Brain: Population Context as a Key to Neuronal Identity”
December 6, 2025 at 11:22 PM
Last talk of the session: “Self-Supervised Learning from Structural Invariance” by Jungyoon Lee
December 6, 2025 at 11:10 PM
Fourth talk: “Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces” by Bahareh Tolooshams and Ailsa Shen
December 6, 2025 at 10:57 PM
Third talk: "Weight Weaving: Parameter Pooling for Data-Free Model Merging" by Levy Chaves
December 6, 2025 at 10:47 PM
Second talk: Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior by Daniel Aarao Reis Arturi ✨
December 6, 2025 at 10:39 PM
The second session of contributed talks is kicking off now.
First talk coming up: SemCLIP: A Semantic Memory Aligned Vision Language Model by Tanveer Syeda-Mahmood 🚀
December 6, 2025 at 10:19 PM
We now continue after the break with Randall Balestriero from Brown University, presenting “LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics ” 👏
December 6, 2025 at 9:42 PM
Up next, our Mentorship Panel featuring
@abeirami.bsky.social, @sarahooker.bsky.social, and @meenakshikhosla.bsky.social moderated by @icannistraci.bsky.social.

Excited to have such inspiring leaders sharing their perspectives on the current state of the ML peer-review system! 🔍✨
December 6, 2025 at 7:42 PM
Fifth and final talk of Session 1: "On Defining Neural Averaging" by Su Hyeong Lee 🧠⚡️
December 6, 2025 at 7:25 PM
Fourth talk: "Superposition disentanglement of neural representations reveals hidden alignment" by André Longon 💡🌟
December 6, 2025 at 7:13 PM
Third talk: "Universally Converging Representations of Matter Across Scientific Foundation Models" by Sathya Edamadaka and Soojung Yang 📊⚡️
December 6, 2025 at 6:59 PM
Second talk: "Neuron-Level Linguistic Selectivity in LLMs via Minimal Pairs: A Neuroscience-Inspired Framework" by Linyang He 🧠✨
December 6, 2025 at 6:46 PM
Session 1 of the Contributed Talks start now! 🚀

First talk: Neural Embedding Alignment Reveals Nonlinear Latent Transformations across Brain Regions by Stephen Keeley
December 6, 2025 at 6:39 PM
Reposted by UniReps
Did you know that you could create hybrids across different neural net architectures—*without* updating the weights??

Come check out my poster at the UniReps @unireps.bsky.social workshop at 3:45pm today at #NeurIPS! (Or you can already browse the posters on the wall in 20D throughout the day.) 😃
December 6, 2025 at 5:47 PM
Reposted by UniReps
I thought this was a fascinating way to motivate model merging: to be able to *interpolate* between model classes, rather than be forced into discrete choices. (models trained on different datasets, models of different sizes, etc.)

"Interpolation and alignment are two sides of the same coin."
December 6, 2025 at 6:11 PM
It’s our pleasure to welcome @dmelis.bsky.social from Harvard SEAS to UniReps 2025, presenting “From Discrete to Continuous: Interpolating Models, Datasets, and Representations!” 🔁📊

Join us in Ballroom 20D for more exciting discussions on representational alignment!
December 6, 2025 at 5:41 PM
We now continue with Prof. Nikolaus Kriegeskorte from Columbia University, presenting "Meaningful and Powerful Model Comparisons"!
December 6, 2025 at 5:04 PM
We are thrilled to announce our first invited talk this morning, featuring Prof. Rose Yu (@yuqirose.bsky.social) from UC San Diego, presenting “Fantastic Symmetries and Where to Find Them” at the UniReps workshop! 🎤✨
December 6, 2025 at 4:34 PM
Welcome to UniReps 2025 🔵🔴 Opening remarks by
@marcofm.bsky.social We have an exciting day ahead of us - join us at *Ballroom 20d* for amazing talks, posters and discussions on representational alignment!
December 6, 2025 at 4:19 PM