Excited to share that 2/2 papers from our Lab @AreaSciencePark were accepted to #NeurIPS2025 (one spotlight 🎉) Great work everyone! @alexpietroserra.bsky.social @francescortu.bsky.social @lbasile.bsky.social @lvaleriani.bsky.social @diegodoimo.bsky.social @maiorca.xyz @locatelf.bsky.social

Our study is now published on JCIM🎉 We expanded and refined the preprint thanks to the insightful feedback from reviewers! paper: pubs.acs.org/doi/10.1021/... code: github.com/RitAreaScien...

Evolutionary Constraints Guide AlphaFold2 in Predicting Alternative Conformations and Inform Rational Mutation Design

Investigating structural variability is essential for understanding protein biological functions. Although AlphaFold2 accurately predicts static structures, it fails to capture the full spectrum of f...

pubs.acs.org

🔥 Two PhD positions open @UniTrieste funded by @AreaSciencePark! 🔥 Join the Laboratory of Data Engineering to advance research in AI and its scientific applications. We’re looking for motivated students ready to dive into interdisciplinary research in deep learning and AI.

Really excited to share our latest interpretability work on multimodal models! The communication between image and text is localised in a single token in multimodal-output vision-language models. Paper: arxiv.org/html/2412.0664… Happy to discuss it at #NeurIPS2024 More below 👇

Francesco Ortu@francescortu.bsky.social · 2y ago

🚨 🚨 Excited to share our latest paper, now on #arXiv! 🖼️ We studied how unified VLMs, trained to generate both text and images (e.g., Meta's Chameleon), exchange information between modalities, comparing them to standard VLMs. 📄 Paper: arxiv.org/abs/2412.06646 Deep dive: 👇

We will present our work tomorrow on "The representation landscape of few-shot learning and fine-tuning in LLMs" #NeurIPS2024 Poster Session East 1 Wednesday h. 11-14 Number #3303 Great work with @diegodoimo.bsky.social @alexpietroserra.bsky.social @ansuin arxiv.org/abs/2409.03662 More 👇

The representation landscape of few-shot learning and fine-tuning in large language models

In-context learning (ICL) and supervised fine-tuning (SFT) are two common strategies for improving the performance of modern large language models (LLMs) on specific tasks. Despite their different nat...

arxiv.org

@diegodoimo.bsky.social · 2y ago

Just landed in Vancouver to present @neuripsconf.bsky.social the results of our new work! Few-shot learning and fine-tuning change the layers inside LLMs in a dramatically different way, even when they perform equally well on multiple-choice question-answering tasks. 🧵1/6

Nice start of @neuripsconf.bsky.social! Our work with @francescortu.bsky.social and @diegodoimo.bsky.social on the Competition of Mechanisms to understand counterfactuality in LLMs featured in the "Causality for LLMs" workshop :-) Check out our ACL2024 paper aclanthology.org/2024.acl-long.…