Ana Sanchez-Fernandez

43 posts

Ana Sanchez-Fernandez

Ana Sanchez-Fernandez

@ana_sanchezf

Machine learning for drug discovery, microscopy imaging data 🔬 | PhD student @jkulinz within the EU project @AiddOne

Vienna, Austria Katılım Ağustos 2022
81 Takip Edilen130 Takipçiler
Sabitlenmiş Tweet
Ana Sanchez-Fernandez
Ana Sanchez-Fernandez@ana_sanchezf·
Excited to share our latest work! “𝐂𝐥𝐨𝐬𝐢𝐧𝐠 𝐭𝐡𝐞 𝐃𝐨𝐦𝐚𝐢𝐧 𝐆𝐚𝐩 𝐢𝐧 𝐁𝐢𝐨𝐦𝐞𝐝𝐢𝐜𝐚𝐥 𝐈𝐦𝐚𝐠𝐢𝐧𝐠 𝐛𝐲 𝐈𝐧-𝐂𝐨𝐧𝐭𝐞𝐱𝐭 𝐂𝐨𝐧𝐭𝐫𝐨𝐥 𝐒𝐚𝐦𝐩𝐥𝐞𝐬”
Ana Sanchez-Fernandez tweet media
English
1
2
9
522
Ana Sanchez-Fernandez
Ana Sanchez-Fernandez@ana_sanchezf·
Excited to share our latest work! “𝐂𝐥𝐨𝐬𝐢𝐧𝐠 𝐭𝐡𝐞 𝐃𝐨𝐦𝐚𝐢𝐧 𝐆𝐚𝐩 𝐢𝐧 𝐁𝐢𝐨𝐦𝐞𝐝𝐢𝐜𝐚𝐥 𝐈𝐦𝐚𝐠𝐢𝐧𝐠 𝐛𝐲 𝐈𝐧-𝐂𝐨𝐧𝐭𝐞𝐱𝐭 𝐂𝐨𝐧𝐭𝐫𝐨𝐥 𝐒𝐚𝐦𝐩𝐥𝐞𝐬”
Ana Sanchez-Fernandez tweet media
English
1
2
9
522
Ana Sanchez-Fernandez retweetledi
Günter Klambauer
Günter Klambauer@gklambauer·
AI for biomedical imaging breaks when you change the lab, device, or batch. New paper fixes this using the control samples already in your experiment. The forgotten controls (and meta-learning) were the answer all along. P: arxiv.org/abs/2604.20824
Günter Klambauer tweet media
English
0
8
17
891
Ana Sanchez-Fernandez retweetledi
Ana Sanchez-Fernandez retweetledi
Günter Klambauer
Günter Klambauer@gklambauer·
Measuring AI Progress in Drug Discovery - A NEW LEADERBOARD IN TOWN 2015-2025: turns out that there's hardly any improvement. AI bubble? GPT is at 70% for this task, whereas the best methods get close to 85%. P: arxiv.org/abs/2511.14744 Leaderboard: huggingface.co/spaces/ml-jku/…
Günter Klambauer tweet media
English
2
11
24
6.8K
Ana Sanchez-Fernandez retweetledi
Korbinian Poeppel
Korbinian Poeppel@KorbiPoeppel·
Ever wondered how linear RNNs like #mLSTM (#xLSTM) or #Mamba can be extended to multiple dimensions? Check out "pLSTM: parallelizable Linear Source Transition Mark networks". #pLSTM works on sequences, images, (directed acyclic) graphs. Paper link: arxiv.org/abs/2506.11997
Korbinian Poeppel tweet media
English
4
42
136
15.1K
Ana Sanchez-Fernandez retweetledi
Andreas Auer
Andreas Auer@AndAuer·
We’re excited to introduce TiRex — a pre-trained time series forecasting model based on an xLSTM architecture.
Andreas Auer tweet media
English
5
21
71
14.8K
Ana Sanchez-Fernandez retweetledi
Günter Klambauer
Günter Klambauer@gklambauer·
The Machine Learning for Molecules workshop 2024 will take place THIS FRIDAY, December 6. Tickets for in-person participation are "SOLD" OUT. We still have a few free tickets for online/virtual participation! Registration link here: moleculediscovery.github.io/workshop2024/
English
2
22
50
9K
Ana Sanchez-Fernandez retweetledi
Niklas Schmidinger
Niklas Schmidinger@smdrnks·
We are excited to introduce Bio-xLSTM! TLDR: we extend xLSTM to genomic, protein and molecular domains and find that it is a proficient generative model, learns rich representations and can perform in-context learning.
English
1
12
28
4K
Ana Sanchez-Fernandez retweetledi
Günter Klambauer
Günter Klambauer@gklambauer·
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences xLSTM also shines for DNA, proteins and small molecules -- can handle large-range interactions and huge context! P: arxiv.org/abs/2411.04165
Günter Klambauer tweet media
English
0
39
154
19.5K
Ana Sanchez-Fernandez retweetledi
Thomas Schmied
Thomas Schmied@thsschmied·
Transformers can be slow for real-time applications like robotics. We study if modern recurrent architectures, like xLSTM and Mamba, can be faster alternatives. Experiments on 432 tasks show that they compare favourably in terms of performance and speed 🎃 arxiv.org/abs/2410.22391
Thomas Schmied tweet media
English
3
44
214
29.4K