🎉 Two papers at #SIGIR2026!
🐱 CATS: Clustering + Thompson Sampling for smarter negative mining in RecSys. +20% NDCG@10.
✂️ Load-sensitive Selective Pruning: dynamic embedding dimensionality for dense retrieval under load. +400% queries served.
See you in Melbourne! #IR#RecSys
Giulia Iadisernia is a first-year PhD student in Data Science at Sapienza, supervised by Fabrizio Silvestri a.
Her research focuses on the #trustworthiness and #explainability of LLMs.
She also collaborates with the Applied Research Team at the Bank of Italy.
Alessia Borghini is a first-year PhD student in the National Doctorate in AI supervised by Fabrizio Silvestri.
Her research focuses on Mechanistic Interpretability for #AISafety, aiming to understand LLMs and improve alignment and reliability.
Fell free to reach out!!
Your VLM gives the same answer before and after a tiny image change. So it's robust, right?
Wrong.
In our new paper, we show that VLMs can preserve their predictions while their internal representations drift to regions normally occupied by completely unrelated images.
🧵👇
Alessio Borgi is a PhD student in Graph Neural Networks & Generative AI—bridging geometry, topology, and diffusion models for robotics, vision, and biomedical AI. Feel free to contact him for collaborations. #AI#GNN#GenerativeAI#Robotics#RSTLess#Sapienza
Gavriel Di Nepi is a first-year PhD student in Data Science at Sapienza under the supervision of prof. @fabreetseo . His research focuses on human-inspired memory for #AI to boost performance and reasoning, in collaboration with @bakerhughesco. #RSTLess#Sapienza
Meet Maria Vittoria Vestini, 1st-year PhD student in Data Science at Sapienza University of Rome, supervised by @fabreetseo. Her research explores interactions and learning dynamics between large and small language models.
Learn more: rstless.it#RSTLess#Sapienza
By combining the expressive power of sheaves with a principled treatment of directionality, our method achieves consistent relative accuracy improvements over prior methods.
- We introduce the notion of Directed Cellular Sheaves over directed hypergraphs
- From this construction, we derive the Directed Sheaf Hypergraph Laplacian, a complex-valued Hermitian operator that unifies and generalizes existing graph and hypergraph convolutional operators.
5/5
This offers a complementary perspective on mechanistic interpretability:
from finding circuits to shaping and composing them during learning.
Looking forward to discussions at #ICLR!
Thanks to Samuele Fonio, Simone Monaco Nicola Saccomanno and @fabreetseo !
1/5 Composable Sparse Subnetworks via the Maximum-Entropy Principle will be presented at #ICLR2026 🎉
👉 openreview.net/forum?id=IHwx5…
It’s about circuits, sparsity, and compositionality, with a training-time loss that shapes how circuits form. Congrats @frances55037016 !
4/5
Crucially, these circuits are composable.
We show they can be recombined into generalist models, behaving like modular building blocks rather than isolated explanations.
3/5 We introduce a training-time objective that steers circuit formation toward specific concepts.
After training, we use pruning to extract class-specific circuits: functional subnetworks specialized for a subset of classes.
2/5 Most mechanistic interpretability work finds circuits post hoc, after training a model.
We ask a different question:
can we control which concepts shape circuits during training?
Paper accepted at #AISTATS2026!!
𝐑𝐚𝐧𝐤 𝐋𝐢𝐟𝐭𝐢𝐧𝐠 𝐚𝐧𝐝 𝐑𝐚𝐧𝐝𝐨𝐦 𝐍𝐨𝐧-𝐋𝐢𝐧𝐞𝐚𝐫 𝐌𝐚𝐩𝐬: once the size of a one-hidden-layer neural network exceeds a threshold, the hidden representations are linearly independent with high probability.
#RSTLess#Sapienza
@chiaradercoli is 1st-year PhD student in the National Doctorate in AI, supervised by @pl219_Cambridge .
🔬 AI for Medicine | Digital Twins | ODEs
🧬 RNA pathways (T1D, Periodontitis)
🤖 LLMs for clinical & biomedical data
Open to collaborations! feel free to reach out
1 Followers 121 FollowingPhD @ Sapienza University & University of Cambridge | Graph Neural Networks, Geometric Deep Learning & Topological Deep Learning
99 Followers 263 FollowingPostdoc researcher @KTHuniversity in CS, got my PhD at @UniPadova.
Working on data mining algorithms for Temporal Networks and Social Network Analysis 👀
749 Followers 768 FollowingI replicate our skills with machines to realize what does (not) really make us humans.
AI Postdoc @MIT, prev @UniofOxford & @SapienzaRoma, fndr @BetterScholar
0 Followers 14 Following🤖 PhD researcher in Computer Vision @ ALCOR Lab Sapienza 🐛 Partnering with Tecnoseta for the new Made in Italy silk 4.0 📖 Passionate about education
2K Followers 2K FollowingOpen-source interpretability to seize the means of prediction. Postdoc w/ @davidbau @ndif_team @Northeastern. Prev: @GroNLP, @amazonscience
2K Followers 2K FollowingNLP postdoc at @SheffieldNLP
Ex @Imperial_NLP PhD, @Apple AI/ML Scholar, @UCL MSc
Model robustness and now uncertainty quantification
681 Followers 233 FollowingAsst. Prof. @HU_LMD | Research Interest: RecSys/Music/Finance/Fashion
Opinions are my own and do not represent my affiliation.
124 Followers 445 FollowingMember of the @italiaNLP_Lab at the Institute for Computational Linguistics of Pisa, Italy. Bass and guitar player when i have some spare time ;-)
208 Followers 291 FollowingPostDoc at the Polytechnic University of Bari. In love with RecSys, Graph Learning, Knowledge Graphs and Differential Privacy.
3K Followers 1K FollowingProfessor of Data Science @ITUkbh Copenhagen, member of @nerdsitu & @AiCentreDK. Before: @BellLabs, @YahooResearch, @IUBloomington, @ISI_Fondazione fellow.
959 Followers 334 FollowingI am a researcher, taking the human perspective in the interaction with intelligent systems. Yes, that integrates research on technologies AND humans...
1K Followers 1K FollowingPhD in Comp Sci., former DECRA, Senior Lecturer, @RMITComputing, @AdmsCentre. CM Camaleão, Capoeira @ACDP_Australia. Percussionist at @Wombatuque.
681 Followers 233 FollowingAsst. Prof. @HU_LMD | Research Interest: RecSys/Music/Finance/Fashion
Opinions are my own and do not represent my affiliation.
124 Followers 445 FollowingMember of the @italiaNLP_Lab at the Institute for Computational Linguistics of Pisa, Italy. Bass and guitar player when i have some spare time ;-)
815 Followers 561 FollowingResearch Scientist @Spotify · Working with IR, RecSys, NLP · PhD from @tudelft · ex @AmazonScience · https://t.co/SMu8BlyfIb
2K Followers 2K FollowingNLP postdoc at @SheffieldNLP
Ex @Imperial_NLP PhD, @Apple AI/ML Scholar, @UCL MSc
Model robustness and now uncertainty quantification
180 Followers 324 FollowingAI Researcher at MediaTek Research | PhD from @UniPadova, prev. intern at Meta AI, Samsung AI | Graph Representation Learning | Graph Neural Networks.
1K Followers 1K FollowingPhD in Comp Sci., former DECRA, Senior Lecturer, @RMITComputing, @AdmsCentre. CM Camaleão, Capoeira @ACDP_Australia. Percussionist at @Wombatuque.
21K Followers 11 FollowingBot. I daily tweet progress towards machine learning and computer vision conference deadlines. Maintained by @chriswolfvision.
3K Followers 1K FollowingAssoc. Prof. @manningcics. Assoc. Director of the Center for Intelligent Information Retrieval (CIIR). Interested in IR, NLP & ML.
876 Followers 618 FollowingMember of Technical Staff at @cohere 👩🏻💻 | PhD in Natural Language Processing from the University of Edinburgh 🎓 | (she/her)
291 Followers 965 FollowingEditor-in-Chief of the Intl J. of Network and Distributed Comp. Former scientific Coord. @BasmatiEUK and Coord. of @ACCORDION project. Co-director of PAI Lab.
777 Followers 2K FollowingPROFILE NO LONGER IN USE ➡️ https://t.co/nkPTlCfVbD
Researcher (opinion change, probabilistic models, and other social networks stuff)
771 Followers 885 FollowingAssociate Professor of ML at the University of Pisa (Italy).
Deep Randomized Neural Networks, Reservoir Computing, Stable Architectures, Deep Learning 4 Graphs