Diego retweeted
🤖Seminar Series
Next week, Giorgos Nikolaou and Tommaso Mencattini (@EPFL) will present "Language Models are Injective and Hence Invertible". @GiorgosNik02 @tommaso_mncttn
📅Nov 27, 11 CET (Online)
👉Register to attend: bit.ly/4ieKRYq
Diego retweeted
📢 Update: the seminar by @ZhijingJin (Max Planck Institute / University of Toronto), scheduled for today at @AreaSciencePark, has been postponed.
New date coming soon — stay tuned!
I just landed in Vancouver to present @NeurIPSConf the findings of our new work!
Few-shot learning and fine-tuning change the hidden layers of LLMs in a dramatically different way, even when they perform equally well on multiple-choice question-answering tasks.
🧵1/6
⚒️We applied an advanced density-based clustering algorithm, showing its potential as an interpretability tool and in guiding novel strategies for the effective finetuning of LLMs.
🧵5/6
This work is a collaboration with a team of talented researchers @AreaSciencePark of Trieste, Italy.
Special thanks to @aleserra1998 , @ansuin and @albecazzaniga for their contribution!
If you are @NeurIPSConf don't miss our Poster tomorrow Dec 11, at 11am!!
🧵6/6
Can changes in the geometry of hidden representations of transformers help identify the layers that encode semantic-rich features of data?
Join our poster presentation @NeurIPS2023.
Session 4, Poster #506.
#deeplearning #AreaSciencePark
arxiv.org/abs/2302.00294
Diego retweeted
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