f mode collapse, all my homies hate mode collapse π€π
f mode collapse, all my homies hate mode collapse π€π
Come and check out our poster on the UniReps workshop at @neuripsconf.bsky.social !
Thanks again to the amazing Giovanni Marchetti, Martina Scolamiero, and Danica Kragic β€οΈ
See more at: arxiv.org/abs/2409.10967
π¨ PhD position alert! π¨
I'm hiring a fully funded PhD student to work on mechanistic interpretability at @uva-amsterdam.bsky.social. If you're interested in reverse engineering modern deep learning architectures, please apply: vacatures.uva.nl/UvA/job/PhD-...
I am in Vancouver for NeurIPS 2024 until December 16th if you want to meet, DM or email me.
We have two accepted papers from my lab:
1. Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers, on Wednesday, East Exhibit Hall A-C #2010 (1/3)
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 π
First time being cited.
Ever since I started my Masters here at Amsterdam everything feels so surreal.
Back in Peru I had almost given up on the idea of doing research and now it scares me that it feels somewhat achievable.
Iβm just so happy and thankful and aaaa
peace out and thanks (again) π«‘
LoRA et al. enable personalised model generation and serving, which is crucial as finetuned models still outperform general ones in many tasks. However, serving a base model with many LoRAs is very inefficient! Now, there's a better way: enter Prompt Generation Networks, presented today #BMVC
also try torch.compile, itβs free performance gains :)
π¨ Happening today! π¨
β° 4 PM CET / 10 AM EST
π©βπ» Zoom link is in the link below
π’ You can attend in person in L3.36, Science Park, University of Amsterdam
Join us for this exciting talk! :)
Soon, @erikjbekkers.bsky.social and @davidmknigge.bsky.social will give a talk elaborating even further on geometry-grounded representation learning in a NeurReps seminar. Make sure to mark the date! :)
β° November 21st, 4 PM CET
π www.neurreps.org/speaker-seri...
Yesterday, @erikjbekkers.bsky.social presented his vision on equivariance to IvI (at UvA), showcasing recent work on geometry-grounded representation learning - addressing fundamental limitations in geometric reasoning of current AI systems. π€
Exciting times ahead for geometric deep learning! π π€©