alessio ansuini

Excited to share that 2/2 papers from our Lab (LADE) were accepted to #NeurIPS2025 (one spotlight 🎉) Great work from all the students and collaborators involved! @AreaSciencePark @aleserra1998 @lorebasile @francescortu @lucrevaleriani @DiegoDoimo @ansuin @FrancescoLocat8

On the #BiodiversityDay2025 we are honored to support biodiversity conservation in Madagascar. Thanks to @TWAS-@Sissa-Lincei fellowship, @AreaSciencePark and the University of Antananarivo are using AI for monitoring wood exploitation in Madagascar.

📢Are you a scientist whose work can be applied to reach new heights in the study of pathogens? 👩‍🔬👨‍💻 The International Conference on Pandemic Preparedness is your unmissable chance to connect in a multidisciplinary network 🤝#overview" target="_blank" rel="nofollow noopener">pathogen-ri.eu/conference/#ov… 1/4 #prpconference2024

It was a great pleasure to deliver a LADE seminar at @AreaSciencePark in #Trieste! Big thanks to Francesca Cuturello and Alessio Ansuini @ansuin for having me here! scientific-events.areasciencepark.it/event/raffaell…

Please help me #RT this 2-years postdoc position #Bioinformatics / #DataScience at the crossing of single-cell #Genomics and #longreads sequencing. With @UniTrieste and @AreaSciencePark in Trieste! Fun work, people and science: more on #LinkedIn linkedin.com/jobs/view/3792…

Open expression of interest for two postdoc positions in #cancer #datascience at @AreaSciencePark and @UniTS on a joint project led by @gcaravagna and me. Join us to develop cool computational methods for single-cell and long-read data! More info👉 shorturl.at/lptNT

Great opportunity last week to teach at the PhD Summer School on self-supervised learning @DTU_compute We discussed how we use geometry to understand LLMs representations with @ansuin Thanks @Tweetteresearch for the invite Slides coming soon😊 #beyondreductionism

@john_fish @robertlufkinmd Interesting... Are there any references that explain this or similar mechanisms? Thanks!

Honoured to be part of this amazing project! #DPCfam is a great method, and we are just scratching the surface of what it can do. Stay tuned...

We increase protein family annotation of the Unified Human Gastrointestinal Proteome (UHGP) using DPCfam clustering. Nice effort by our PhD Federico Barone @areasciencepark, @elena_tea @ansuin and great collaboration with Marco Punta @CosrLab Preprint: bit.ly/42bV3HY

Less than 3 days left to join us! If you are a data engineer and you have a crush for challenging scientific problems you can't lose this opportunity! linkedin.com/jobs/view/3554…

We are building an AI-powered Large Research Infrastructure, and we need Data Engineers to make it real. Deadline is approaching!!! linkedin.com/jobs/view/3554…

See you at @workshopMLSB to discuss our work “The geometry of hidden representations of protein language models”. Great collaboration with @lucrevaleriani, Francesca Cuturello, @ansuin at @AreaSciencePark! biorxiv.org/content/10.110… 👇Summary below

Call for papers❗️ Special session “Pruning in Artificial Neural Networks” @ DeLTA 2022 (12-14 July 2022) Deadline for paper submission is May 19th! More details here 👉 delta.scitevents.org/PANN.aspx

#jobopportunity One research scholarship for machine learning with a new approach on Industrial datasets! Deadline approaching: Thursday 10.03 (still 48 hours!) areasciencepark.it/lavora-in-area…

Fantastic job opportunity in Area Science Park (Trieste, ITALY)! Permanent position as a Research Technologist to manage our HPC infrastructure. Apply here: lnkd.in/egRkKutx Contacts: alessio.ansuini@areasciencepark.it stefano.cozzini@areasciencepark.it #jobopportunity

@UriCohen42 @jakhmack Hope this long stream of tweets was useful!

@jakhmack @ansuin Interesting! Can you speculate on why ID increases in the initial layers, and why is it low for the pixel layer (if I got it right)?

Ill not be at #Neurips2019, but @ansuin @sissaschool is presenting work that I helped with, "Intrinsic dimension of data representations in deep neural networks", arxiv.org/abs/1905.12784 Poster Tomorrow Tue 10:45-12:45, East Exhibition Hall B + C #169.

@UriCohen42 @jakhmack Maybe a test would be to repeat the same analysis on artificially generated data with complex and controllable symmetries (we were close to obtaining one, on the other hand the artificial dataset we used in the paper was too small to do such tests properly.)

@UriCohen42 @jakhmack We cannot say that this really explains what is observed in ImageNet, that has much more complex features than MNIST (such as textures, pose, etc...), but we think this mechanism may be at work also there.

@UriCohen42 @jakhmack We thought that, in getting rid of the irrelevant feature, the network produced representations, in the first layers, in which the relevant features emerged more prominently, and this resulted in an increase of their intrinsic dimension.