Trending
Diego Canez's Avatar

Diego Canez

@dgcnz

Self-supervised Learning, Efficient DL University of Amsterdam https://github.com/dgcnz

35
Followers
88
Following
3
Posts
17.11.2024
Joined
Posts Following

Latest posts by Diego Canez @dgcnz

Video thumbnail

f mode collapse, all my homies hate mode collapse πŸ˜€πŸ‘Š

07.01.2025 16:26 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0
Post image

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 ❀️

See more at: arxiv.org/abs/2409.10967

07.12.2024 13:48 πŸ‘ 12 πŸ” 4 πŸ’¬ 0 πŸ“Œ 0
PhD Position in Mechanistic Interpretability PhD Position in Mechanistic Interpretability

🚨 PhD position alert! 🚨

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-...

02.12.2024 19:36 πŸ‘ 21 πŸ” 11 πŸ’¬ 0 πŸ“Œ 1

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)

09.12.2024 23:03 πŸ‘ 11 πŸ” 4 πŸ’¬ 1 πŸ“Œ 0
Post image

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 πŸ‘‡

07.12.2024 13:48 πŸ‘ 24 πŸ” 7 πŸ’¬ 1 πŸ“Œ 0
Post image

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.

I’m just so happy and thankful and aaaa

peace out and thanks (again) 🫑

05.12.2024 16:13 πŸ‘ 3 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

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

26.11.2024 07:28 πŸ‘ 31 πŸ” 5 πŸ’¬ 1 πŸ“Œ 0

also try torch.compile, it’s free performance gains :)

24.11.2024 21:28 πŸ‘ 2 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

🚨 Happening today! 🚨

⏰ 4 PM CET / 10 AM EST
πŸ‘©β€πŸ’» Zoom link is in the link below
🏒 You can attend in person in L3.36, Science Park, University of Amsterdam

Join us for this exciting talk! :)

21.11.2024 09:07 πŸ‘ 14 πŸ” 4 πŸ’¬ 0 πŸ“Œ 0
Post image

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! :)

⏰ November 21st, 4 PM CET
πŸ”— www.neurreps.org/speaker-seri...

19.11.2024 16:14 πŸ‘ 18 πŸ” 5 πŸ’¬ 1 πŸ“Œ 3
Post image Post image

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. πŸ€–
Exciting times ahead for geometric deep learning! 🌐 🀩

19.11.2024 16:11 πŸ‘ 39 πŸ” 6 πŸ’¬ 1 πŸ“Œ 0