Alexandra Proca

How do task dynamics impact learning in networks with internal dynamics? Excited to share our ICML Oral paper on learning dynamics in linear RNNs! with @ClementineDomi6 @mpshanahan @PedroMediano openreview.net/forum?id=KGOcr…

In summary, we expand the study of superposition to recurrent architectures, enabling us to study how temporal information acts as a capacity constraint and affects feature geometry. Our work highlights how superposition affects dynamics and is shaped by time.

We induce spatial superposition by using 5D input (A-E) and temporal superposition by increasing k. As memory demand (k) increases, the RNN drops features in favor of representing others for a longer duration. This representational tradeoff leads to a strategy that is all-or-none

Excited to share our ICLR Oral paper, co-lead with Pratyaksh Sharma, and with @lucas_prie @PedroMediano! We study how feature geometry is shaped by memory demands in RNNs, introducing the concept of temporal superposition. openreview.net/forum?id=7cMzT…

1/ Deep learning is going to have a scientific theory. We can see the pieces starting to come together, and it's looking a lot like physics! We're releasing a paper pulling together these emerging threads and giving them a name: learning mechanics. 🔨 arxiv.org/pdf/2604.21691 🔧

📢Join us for the next UniReps x @ELLISforEurope speaker series happening on 29th April at 4:00 PM CET with @neurosacramento and Paul Friedrich!👾

📢The next UniReps x @ELLISforEurope speaker series event is happening on 26 February at 4:00 PM CET with @orvieto_antonio and @SaraKangaslahti . Don’t miss it!🚀

Excited to share new work @icmlconf by Loek van Rossem exploring the development of computational algorithms in recurrent neural networks. Hear it live tomorrow, Oral 1D, Tues 14 Jul West Exhibition Hall C: icml.cc/virtual/2025/p… Paper: openreview.net/forum?id=3go0l… (1/11)

@orvieto_antonio Thanks so much!!

cool work on linear rnn theory!!

@NicolasZucchet @ClementineDomi6 @mpshanahan @PedroMediano Thanks Nicolas!

@a_proca @ClementineDomi6 @mpshanahan @PedroMediano Nice work congrats!

How do task dynamics impact learning in networks with internal dynamics? Excited to share our ICML Oral paper on learning dynamics in linear RNNs! with @ClementineDomi6 @mpshanahan @PedroMediano openreview.net/forum?id=KGOcr…

@akjagadish @ClementineDomi6 @mpshanahan @PedroMediano Thanks Akshay!☺️

@a_proca @ClementineDomi6 @mpshanahan @PedroMediano Looks really cool. Congratulations Alex! 🎉