Sabitlenmiş Tweet
I'm quite happy to share that after submitting my PhD in September last year, I finally defended my PhD at @rptu_kl_ld 😁😁.
It was a long journey in @DFKI filled with experiences and learning 🤖
English
Francisco Mena
208 posts
Francisco Mena
@fmenat14
Researcher @GFZ_Potsdam | PhD @rptu_kl_ld | MSc @usantamaria | ex researcher @DFKI & visitor @inria | Enjoying research in AI/ML 🤖. Now ➡️ #AI4EO 🛰️
Germany Katılım Haziran 2021
681 Takip Edilen118 Takipçiler
I'm quite happy to share that after submitting my PhD in September last year, I finally defended my PhD at @rptu_kl_ld 😁😁.
It was a long journey in @DFKI filled with experiences and learning 🤖
English
Francisco Mena retweetledi
We are now accepting applications for the 2026 Cambridge ELLIS Summer School on Probabilistic Machine Learning, 13 - 17 July - Cambridge. Application deadline: 17 May. More info: ellis.eng.cam.ac.uk/summer-school/
English
I am also very happy to share that we got accepted for #CVPR 2026 with this amazing paper! #ai #cvf #ieee #ml
Kwang Moo Yi@kwangmoo_yi
Adamkiewicz et al., "When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators" Interesting that while we have "better" image generators, their usefulness as synthetic data generators is declining. Do we need a pivot?
English
I'm traveling 🚄 towards Copenhagen 🇩🇰 for #Eurips. Happy to catch up if you are around 😀
English
English
I'm happy to share that our new paper in Multi-modal co-learning for Earth observation got published in the ML journal🌍📡
Here, we show how models trained on multiple sensor modalities can boost single-modality inference
🔗 link.springer.com/article/10.100…
English
We combine contrastive learning + modality-discriminative losses to structure features into shared and specific subspaces. Tested on four EO benchmarks (classification & regression) → consistent gains over both EO and ML state-of-the-art.
English
Francisco Mena retweetledi
📢 Join us for a webinar on "Benchmarking and Enhancing Geospatial Foundation Models Capabilities"
👩🏻💻 Speaker: Valerio Marsocci from the ESA Φ-lab
🗓️ Date: Thursday, 06 November 2025
🕚 Time: 10:00 AM UTC
Register today: loom.ly/yed5lug
#IEEEGRSS #GRSS #IADF #TechnicalCommittee #Webinar #ESA #Geospatial #PANGAEA #GFMs
English
Francisco Mena retweetledi
📢 Please retweet: We're recruiting **PhD students and Postdocs** at UC Berkeley & UCSF!
Please apply if you are interests in AI for healthcare, statistics/causal inference, or medical vision-language models.
For more details, check out this link: forms.gle/1rZHBoH8f8fu27…
English
Francisco Mena retweetledi
📢 Join us for a webinar on "Deep Learning for SAR Image Analysis"
👩🏻💻 Speaker: Michael Schmitt from University of the Bundeswehr Munich
🗓️ Date: Thursday, 09 October 2025
🕚 Time: 10:00 AM CEST (UTC+2)
Register today: loom.ly/AY7I9Xk
#IEEEGRSS #GRSS #IADF #TechnicalCommittee #Webinar #AI #MachineLearning #ComputerVision
English
Francisco Mena retweetledi
📢 Join us for a webinar on "From Efficient Foundation Models to AI Agents for Foundation Model Recommendation to Advance Earth Observation"
👩🏻💻 Speakers: Prof. Begüm Demir, Technische Universität Berlin
🗓️ Date: Thursday, 16 October 2025
🕚 Time: 8:00 AM ET (UTC-5)
Sponsored by: IEEE GRSS Germany Chapter
Register today: loom.ly/X84E8tk
#IEEEGRSS #GRSSWebinar #GRSSGermanyChapter #AIAgents #EarthObservation
English
Francisco Mena retweetledi
🚀 Job Alert Friday! 🚀
Exciting Opportunity at @GFZ_Potsdam
💼 Research Associate: Scientific Programming
👉 Apply now: gfz.de/en/career/job-…
Explore more opportunities in Data Science, Machine Learning and AI within @helmholtz_en: helmholtz-hida.de/en/jobs/job-of…
English
Francisco Mena retweetledi
*ACL Findings is a great initiative and should be applied to other AI/ML venues.
Shangbin Feng@shangbinfeng
Seems to me the "findings of *ACL" decision is really wise and visionary (5 years ago), compared to the "had to reject because of venue limit" thing
English
Francisco Mena retweetledi
I am looking for PhD students and postdocs to join our group in beautiful Munich at the Technical University of Munich and Helmholtz Munich.
PhD application info:
drive.google.com/file/d/1PM-y0s…
postdoc application info:
drive.google.com/file/d/1ripNnM…
Please help me spread the word! 🤗
English
Considering the current substantial use of computational resources in deep learning research and its consequential impact on the carbon footprint 👣, it is important to look for systematic ways that lead us to reduce the search space of model configurations
English
In our paper, we found out that instead of trying all possible combinations, the search could be reduced to a 2-step sequential search: 1) search for the best encoder architecture with early/input fusion, 2) with the encoder selected in (1), search for the best fusion strategy.
English
It is possible to reduce the number of experiments when searching for the best combination of encoder architecture and fusion strategy for crop classification 🌱🚜?
Spoiler alert: In our recent paper, we show that it can!
doi.org/10.1016/j.jag.…
English