Advertisement Β· 728 Γ— 90

Posts by Alberto Cazzaniga

Post image

Excited to share that 2/2 papers from our Lab @AreaSciencePark were accepted to #NeurIPS2025 (one spotlight πŸŽ‰)

Great work everyone!

@alexpietroserra.bsky.social @francescortu.bsky.social @lbasile.bsky.social @lvaleriani.bsky.social @diegodoimo.bsky.social @maiorca.xyz @locatelf.bsky.social

6 months ago 7 2 0 0
Preview
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...

Our study is now published on JCIMπŸŽ‰

We expanded and refined the preprint thanks to the insightful feedback from reviewers!

paper: pubs.acs.org/doi/10.1021/...
code: github.com/RitAreaScien...

7 months ago 10 4 0 1
LinkedIn This link will take you to a page that’s not on LinkedIn

πŸ”— Apply through the University of Trieste β†’ How to apply lnkd.in/dppFWuGS

Deadline is approaching: spread the word, and get in touch for more info!
alberto.cazzaniga@areasciencepark.it

LADE website: lnkd.in/dV5sxrxe

10 months ago 0 0 0 0

πŸ’‘ Our interests include (but are not limited to):
- AI for biological systems
- Reasoning and planning
- Interpretability

πŸ“ Location: Trieste, Italy

 🚨 🚨 🚨 Deadline: June 6th, 2025

10 months ago 0 0 0 0

πŸ”₯ Two PhD positions open @UniTrieste funded by @AreaSciencePark!Β πŸ”₯

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.

10 months ago 3 2 2 0

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 πŸ‘‡

1 year ago 5 1 0 0

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 πŸ‘‡

1 year ago 3 1 0 0
Post image

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.…

1 year ago 9 1 0 0