Sabitlenmiş Tweet
Federico Pernici
1.1K posts
Federico Pernici
@FedPernici
Computer Vision, Machine Learning, Deep Learning, AI. Associate Professor at University of Florence | DINFO | MICC. Opinions are my own.
University of Florence, Italy Katılım Eylül 2010
1.4K Takip Edilen731 Takipçiler
📄 "λ-Orthogonality Regularization for Compatible Representation Learning"
🪧 Simone Ricci (@ricciunifi) is presenting at #NeurIPS2025. Poster #2503, Exhibit Halls C, D, E. Work carried out at @miccunifi. Feel free to stop by and discuss. @NeurIPSConf
English
λ-Orthogonality: a tiny near-orthogonal adapter with a controllable λ "knob" to balance geometry preservation and adaptation. Enables backward-compatible embeddings (no full backfill) with near new-model performance and <50% gallery updates. @NeurIPSConf #NeurIPS2025
Simone Ricci@ricciunifi
Excited to present our #NeurIPS2025 paper on "λ-Orthogonality Regularization for Compatible Representation Learning" today! 🎉 Come chat with me at Poster #2503 in Exhibit Halls C, D, E 📅 Fri, Dec 5 | 🕚 11am – 2pm PST #MachineLearning #AI #Compatibility #RepresentationLearning
English
Encouraging to see compatibility discussed in this NeurIPS workshop. The theoretical understanding of the problem’s structure is still limited, with room for useful progress. @NeurIPSConf #NeurIPS2025
sites.google.com/view/ccfm-neur…
Fartash Faghri@FartashFg
Is your AI keeping Up with the world? Announcing #NeurIPS2025 CCFM Workshop: Continual and Compatible Foundation Model Updates When/Where: Dec. 6-7 San Diego Submission deadline: Aug. 22, 2025. (opening soon!) sites.google.com/view/ccfm-neur… #FoundationModels #ContinualLearning
English
Federico Pernici retweetledi
Congratulations to @geoffreyhinton for winning the Nobel Prize in physics!!
English
Federico Pernici retweetledi
BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
English
Federico Pernici retweetledi
I sooo much agree with this. Academic jobs require juggling too many balls with barely any support (grant writing, teaching, managing a research group, supervising students and … research). Take two hrs everyday before you look at email and social media.
search.app/nnTKNba5Dqv8Eu…
English
Apple🍏shows interest in strategies for evolving🔄compatible🤝language models that minimize inconsistencies with previous versions:
arxiv.org/abs/2407.09435
English
Federico Pernici retweetledi
🚨 30 mins to go! Catch our papers at #CLVision boards #268 and #275. Don't miss out! #CVPR2024 @CVPR ✨👀
Niccolò Biondi@NiccoBio
Excited to present our papers at the #CLVision workshop during #CVPR2024 @CVPR! 📜✨ Visit board #268 for our CVPR highlight paper and board #275 for our second paper. Come check them out! 👀
English
@DataScienceHarp Thanks for the response! I was actually thinking about to precompute a 2D projection of all embeddings, possibly using t-SNE or similar, to completely avoid any model or GPU use.
English
@FedPernici Yeah you can for sure run this on CPU, the embedding model is small enough but it may take a bit longer. In the colab with GPU it took like under a minute to generate embeddings
English
Writing articles on Hugging Face >>> Medium.
This should be the community standard for where to share.
I just published my first article, which will help you find research at this years #CVPR that's most interesting to you!
huggingface.co/blog/harpreets…
#CVPR2024
English
Proceedings for #CVPR2024 are available📘. Useful for navigating the extensive content:
openaccess.thecvf.com/CVPR2024
and the workshops at openaccess.thecvf.com/CVPR2024_works…
English
If you're using a mobile device, simply tap📲on the points to reveal titles of #CVPR2024 papers 📄
English
Explore #CVPR2024 papers📄clustered by topics using PCA-tSNE-KMeans on title embeddings, processed with the sentence-transformer from Hugging Face🤗. Hover to reveal paper titles! Access the interactive visualization here: tinyurl.com/52zx9ma9
@CVPR 🌐
English
Check out our highlight poster🌟: "Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements" at #CVPR2024. Full details 🔍 available on arXiv: arxiv.org/abs/2405.02581 @CVPR 📚
English
🔍Exploring #CVPR2024 papers📚clustered by PCA-tSNE-KMeans on title embeddings. Interactive visualization here: tinyurl.com/52zx9ma9
Federico Pernici@FedPernici
The CVPR 2024 accepted papers list is now available at cvpr.thecvf.com/Conferences/20…. It includes our "Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements" #CVPR2024 #ComputerVision #AIResearch
English