iiinova — where your digital self keeps evolving

Reposted by Samuel Lippl

UniReps @unireps.bsky.social · 02/10/2026

🔵🔴Still thinking about submitting to UniReps? Good news: we’ve extended the submission deadline to October 10th (AOE)! We’d love to see your work and look forward to welcoming you to UniReps! 🔴 Call for papers: unireps.org/2026/call-fo... 🔵 Submit here: openreview.net/group?id=Uni...

unireps.org

Call For Papers | UniReps Workshop

Unifying Representations in Neural Models

157

Reposted by Samuel Lippl

UniReps @unireps.bsky.social · 05/10/2026

🔵🔴 Join us for the 4th edition of UniReps on December 12, 2026, in Paris! Working on these or similar topics? Submit your paper by the extended deadline: October 10 (AoE) Submit at: t.co/lA6ci1epeF full CFP: t.co/EvBFdvZfLu

0127

Reposted by Samuel Lippl

UniReps @unireps.bsky.social · 25/09/2026

NeurIPS decisions not quite what you hoped for? We look forward to having you at UniReps! December 12th, 2026 in Paris. Submission deadline October 4th AOE. Call for papers: unireps.org/2026/call-fo... Submit here: openreview.net/group?id=Uni...

unireps.org

Call For Papers | UniReps Workshop

Unifying Representations in Neural Models

056

Reposted by Samuel Lippl

UniReps @unireps.bsky.social · 04/09/2026

📣 Call for Papers: UniReps Workshop in Paris! We invite work exploring why, when, and how distinct learning processes yield similar representations across AI, neuroscience & cognitive science. 📅 Deadline: Oct 4 (AoE) unireps.org/2026/call-fo...

unireps.org

Call For Papers | UniReps Workshop

Unifying Representations in Neural Models

034

Reposted by Samuel Lippl

UniReps @unireps.bsky.social · 14/08/2026

🚀 UniReps 4th Edition is coming! 🌍✨ We’re aiming to host a UniReps satellite event around NeurIPS 2026 in Paris! Join us to connect, collaborate, and shape the future of representation learning. Your voice matters! Let us know which dates work best for you. docs.google.com/forms/d/e/1F...

docs.google.com

Call for Partecipation - UniReps 4th Edition

We’re excited to announce that we’re organizing the 4th edition of UniReps as a satellite event in Paris and would love your help in choosing the best date for the community. Your feedback will ensure...

074

Samuel Lippl @sflippl.bsky.social · 03/08/2026

Really excited about this project! If you want to chat about repulsion and representational changes in hippocampus, come by our poster at #CCN2026 tomorrow at 9:30!

0122

Reposted by Samuel Lippl

Anna Schapiro @annaschapiro.bsky.social · 01/08/2026

Here's where to find the Penn Computational Cognitive Neuroscience Lab at Cognitive Computational Neuroscience next week! See you in NYC!

0367

Samuel Lippl @sflippl.bsky.social · 11/07/2026

Excited to present this paper that was led by Luke today at the CompLearn workshop (2nd poster session, starting at 4). If you want to chat about how simple learning systems can learn relational rules but also memorize exceptions to those rules, come by!

0121

Samuel Lippl @sflippl.bsky.social · 08/07/2026

Excited to be presenting this paper tomorrow! If you want to hear more about this, please come to the poster session tomorrow at 2:30pm @icmlconf.bsky.social.

292

Samuel Lippl @sflippl.bsky.social · 08/07/2026

This was a great collaboration with Nicolas Anguita, Francesco Locatello, @saxelab.bsky.social, @mmondelli.bsky.social, @flaviamancini.bsky.social, and @clementinedomine.bsky.social. If you want to hear more, please come chat at the poster session tomorrow (starting at 5pm).

000

Samuel Lippl @sflippl.bsky.social · 08/07/2026

Main takeaway: Fine-tuning behavior is strongly shaped by the inductive bias inherited from pretraining and network initialization.

110

Samuel Lippl @sflippl.bsky.social · 08/07/2026

Beyond the idealized setting: → We extend the analysis to imperfect pretraining → In ResNets and Transformers, we show that a negative relative scale improves generalization when tasks rely on a sparse subset of pretrained features

100

Samuel Lippl @sflippl.bsky.social · 08/07/2026

→ We derive exact generalization curves via replica theory, linking initialization parameters, data structure, and sample size

100

Samuel Lippl @sflippl.bsky.social · 08/07/2026

→ A key control knob: the relative scale of weights across layers

100

Samuel Lippl @sflippl.bsky.social · 08/07/2026

→ This induces four distinct fine-tuning regimes, including a previously overlooked regime that enables both reuse and refinement

100

Samuel Lippl @sflippl.bsky.social · 08/07/2026

📌 Key ideas: → Pretraining hyperparameters shape the model’s inductive bias, controlling whether fine-tuning reuses pretrained features or learns new ones

100

Samuel Lippl @sflippl.bsky.social · 08/07/2026

We investigate pretraining + fine-tuning in diagonal linear networks as a tractable model, deriving an exact characterization of fine-tuning behavior.

100

Samuel Lippl @sflippl.bsky.social · 08/07/2026

Pretraining + fine-tuning powers modern ML, but we lack a theoretical understanding of how pretraining actually shapes downstream learning. In our new @icmlconf.bsky.social paper, we address this gap! 📅 July 9th, Poster #4502 Session 8! 🧵 arxiv.org/pdf/2602.20062

Diagram with "l-order" on the x-axis and "Pretraining dependence" on the y axis. The diagram highlights that only the upper right triangle is a possible region and highlights four distinct regimes: (I) a rich, pretraining independent regime, (II) a lazy, pretraining-dependent regime, (III) lazy, pretraining-independent regime, and (IV) a rich, pretraining dependent regime. Different initialization parameters move us between these regimes.

1193