Assistant Professor in Machine Learning at @BristolUni. Research Associate at @Oxford_Man_Inst. Previously PostDoc at @UniofOxford and PhD at @uc3m.
Oxford, UK
Joined October 2012
- Tweets60
- Following1.8K
- Followers235
- Likes1.2K
Fernando Moreno-Pino retweeted
Congratulations to our 80 new Cosmos grantees!
Our largest cohort to-date will be building prototypes for AI that supports human autonomy or truth-seeking (in partnership with @TheFIREorg.)
The projects range from wearable AI for memory and cryptographic tools for scientific collaboration to a benchmark based on pre-1940 thought on machines and autonomy.
Our grantees come from sixteen countries, including the US, UK, Nigeria, Ethiopia, South Korea, Costa Rica, India, and Czechia.
They join a community of Cosmos grantees and fellows whose projects have grown into companies, non-profit research organizations, and papers published at leading venues like ICML, COLM, and IEEE.
Read what all eighty are working on: blog.cosmos-institute.org/p/…
Fernando Moreno-Pino retweeted
In the last couple of months, we have witnessed significant advances in Industry-scale World Models. Yet, for the broader community, the gap between reading about these models and deploying them remains disappointingly wide.
Today we're releasing Nano World Models: a minimalist, batteries-included repo for advancing world model science.
🧵 (1/9)
Fernando Moreno-Pino retweeted
Part I of a Bayesian’s take on (Kalman) filtering—without Bayes.
I will cover filtering and applications—from classical tracking problems to time-series forecasting, sequential learning for neural networks, and fully-online reinforcement learning
gerdm.github.io/posts/filter…
🚀 Today at #NeurIPS2024!
Join us for our presentation on “Rough Transformers: Lightweight Continuous-Time Sequence Modelling with Path Signatures”.
🕚 Time: 11:00–14:00.
📍 Room #2006, East Exhibit Hall.
Discover how to train much more efficient (& continuous!) Transformers!
Work done at @UniofOxford - @Oxford_Man_Inst.
📊 Poster: neurips.cc/virtual/2024/post….
📄 Paper: openreview.net/forum?id=gXWm….
🚀 Exciting news! Thrilled to share that our paper on Rough Transformers has been accepted at @NeurIPSConf !🧠
We’ve developed a method to make Transformers more efficient and resilient with temporal data using path signatures. Check it: arxiv.org/abs/2405.20799 🙌
#NeurIPS2024
A little late, but happy to announce that our paper on Rough Transformers ⛰️ has been accepted at @NeurIPSConf!
We present a way to make Transformers for temporal data more efficient and robust to irregular sampling through path signatures!
Read on!
#neurips2024
(1/7)
Fernando Moreno-Pino retweeted
We introduce Geometry-Informed Neural Networks to train shape generative models
without any data (!!), combining learning under constraints, neural fields as a suitable representation, and generating diverse solutions to under-determined problems:
🖥️: arturs-berzins.github.io/GIN…
Fernando Moreno-Pino retweeted
📢 Exciting opportunity to work with an outstanding team of researchers! 📢
Feel free to reach out to us if you want to know more details about the ongoing projects!
We seek a postdoc (2-yr) at DTU specialising in generative modelling. Focus on diffusion & score-based models applied to physical systems.
Interested? Contact me or learn more: groups.google.com/g/ml-news/…
Check out our ongoing work: arxiv.org/abs/2405.05981
Please RT! #Postdoc
Fernando Moreno-Pino retweeted
Happy to share that our outlier-robust Kalman filter (WoLF 🐺) has been accepted to #ICML!
arxiv.org/abs/2405.05646
We propose a novel filtering algorithm that is provably robust and has similar computation cost to the KF.
Now, why care about robust filtering?
Fernando Moreno-Pino retweeted
I am honored to announce that we will organize the "Next Generation of Sequence Modeling Architectures" workshop at ICML 2024 this year in Vienna. The workshop will take place on Friday, the 26th of July. The workshop page is: sites.google.com/view/ngsmwo…
Fernando Moreno-Pino retweeted
As the @icmlconf discussion period is ending please go back to the papers you are reviewing and reread the autor responses. Did they address your concerns? If so, update your score. If not, add a specific response, not "I decided to keep my score". Do justice to time and effort🙏
It was a pleasure to hear Prof. @geoffreyhinton's insights on the future of AI and the direction researchers should take to address its potential risks
Yesterday, Oxford University hosted Prof @geoffreyhinton, the ‘Godfather of AI’, to deliver its annual Romanes Lecture at the Sheldonian Theatre.
Watch in full ⬇️ #OxfordAI
ox.ac.uk/news/2024-02-20-rom…
Fernando Moreno-Pino retweeted
If you have ever felt frustrated or a little bit stupid when learning a new skill, come feel that with me while we learn how to use @QuPath. It's fine! It's normal! We can get through it together.
Will you join me?
youtu.be/MBrAVUsUdio
Fernando Moreno-Pino retweeted
Huge congratulations to @Laura_nicolass and cosupervsors @ArrateMunoz @jpascau on her recently defended PhD👩🎓 🚀🥳a truly creative work merging registration🧩and colour theory🎨for #digitalpathology + #immunohistochemistry image analysis👩💻🧑⚕️The fun starts right with the title💍👑
Great personal news! 🎉
After successfully defending my PhD thesis, I am starting a Postdoctoral Researcher position at the @UniofOxford within the @Oxford_Man_Inst. I will be working at the intersection of Deep Learning and Quantitative Finance!
See you all soon in Oxford! 🇬🇧
Fernando Moreno-Pino retweeted
It is finally published!:
ABANICCO: A New Color Space for Multi-Label Pixel Classification and Color Analysis
mdpi.com/2207960
Fernando Moreno-Pino retweeted
📰Excited to introduce our latest paper “Learnable Graph Convolutional Attention Networks”!
arxiv.org/abs/2211.11853
Joint work by the awesome team @javaloyML, @amitzeani, and @IValeraM.
🔎 Sidenote: Let's meet at #NeurIPS2022!
🧵 (1/n)
Fernando Moreno-Pino retweeted
We have brought ABANICCO to #SPAOM2022 @SPAOM5
Come and discuss all the possible applications of our automatic color analysis method!
📍poster 3
Fernando Moreno-Pino retweeted
ABANICCO: A New Color Space for Multi-Label Pixel Classification and Color Segmentation
deepai.org/publication/abani…
by Laura Nicolás-Sáenz et al. including @jpascau, @ArrateMunoz
#Classifier #ComputerVision