UniReps
https://unireps.org
Discover why, when and how distinct learning processes yield similar representations, and the degree to which these can be unified.
- That was fun! Thanks for the invitation :-)
- Join us in one hour! 📣 @noagarciad.bsky.social @thwiedemer.bsky.social
- [Not loaded yet]
- 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."
- 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!
- Thread of French and Dutch research institutes slowly unsubscribing from web of science (and thence impact factors).
- [Not loaded yet]
- 📢 Save the date! Join us for the next @ellis.eu x @unireps.bsky.social Speaker Series! 📅18th November – 16:00 CEST 📍https://ethz.zoom.us/j/66426188160 🎙️Speakers: Keynote Talk by Yilun Du & Flash Talk by Sihyun Yu
- [Not loaded yet]
- [Not loaded yet]
- Honored & looking forward to give this lecture tomorrow @ucl-neuroai.bsky.social!
- 🧠✨ How closely do AI models mirror the human brain? Join us for @irisgroen.bsky.social’s talk: “Alignment of visual representations in AI and human brains: beyond object recognition” 📅 8th September @unireps.bsky.social x @ucl-neuroai.bsky.social meetup 🔗 Zoom link: ethz.zoom.us/j/66426188160 1/4
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
- [Not loaded yet]
