NLP & Interpretability | PhD Student @ University of Trieste & Laboratory of Data Engineering of Area Science Park | Prev MPI-IS
Francesco Ortu
Loading...
Excited to share that 2/2 papers from our Lab @AreaSciencePark were accepted to #NeurIPS2025 (one spotlight š)
Great work everyone!
@alexpietroserra.bsky.social @francescortu.bsky.social @lbasile.bsky.social @lvaleriani.bsky.social @diegodoimo.bsky.social @maiorca.xyz @locatelf.bsky.social
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.ā¦
Thanks again, @diegodoimo.bsky.social and @albecazzaniga.bsky.social , for the fantastic mentorship and support! šš They are also attending #NeurIPS, so feel free to reach out to them to discuss our results. Iām excited to keep pushing forward on these topics! š
Thanks to the amazing team at LADE @areasciencepark: @lvaleriani.bsky.social @lbasile.bsky.social @AlessioAnsuini @diegodoimo.bsky.social @albecazzaniga.bsky.social š
It was super fun to take our first step in interpreting multimodal LLMs, working closely with the brilliant @alexpietroserra.bsky.social and @EmanuelePanizon
ā This shows that, starting from the mid-layers, a single token effectively summarizes all 1024 image tokens!
ā This does not occur in models fine-tuned for visual understanding (such as Pixtral).
