Davide (@Comment98) header
Davide (@Comment98) profile picture
Joined March 2014
Photo by Davide (@Comment98)Photo by Davide (@Comment98)Photo by Davide (@Comment98)Photo by Davide (@Comment98)Photo by Davide (@Comment98)
Privacy, Memorization, Multimodal reasoning, and the surge of protoknowledge (non-archival in L2M2 Workshop) ! This is our contribution to #ACL2025NLP to better understand #LLMs We want to know your POV! See you in Vienna! We are hiring.
5
1
8
491
easily the best poster I’ve seen at #ACL2025 so far!! @znz8
3
6
1
114
8,096
Willing to know how to remove Private Information from trained #LLMs ? Private Memorization Editing is for you! #ACL2025NLP #ACL2025 w/ @esruzzetti @commentino @znz8 – at Vienna, Austria
5
11
343
Do you want to discuss your views on #Psycoanalysis for #LLMs? Are you more interested in #Psychiactric of #LLMs? Or in performing #ArtificialBrain #Surgery? #NLProc We are ready to interact you! The #Humancentric #ArtificialIntelligence @unitorvergata has a new X accout
3
1
9
880
#ACL2025NLP #ACL2025 'r'u a brave researcher willing to see a different standpoint? Do you want to start working again on modeling? We are waiting you for a tantalizing Position Paper challenging the status-quo. 6.00-7.30 X3/X4 Come and see what's in these obscure matrices!
1
2
10
361
It seems that @Scopus has changed its policy: now, citations to preprints are not counted for the related accepted papers appearing in Scopus. Is this the case? Please, @Scopus, let us know the reason for this insane change of policy!
4
3
296
Would you like to know how to preserve privacy in LLMs and stay ahead of emerging threats? 📄 Explore our latest survey on the topic! Shoutout to @mmiranda_17 for his debut paper! 🎉 arxiv.org/abs/2408.05212
Large Language Models are powerful but have significant privacy implications when trained on public data. We provide here a comprehensive survey on current threats and available solutions arxiv.org/abs/2408.05212 📜
3
21
917
Is this an issue for #KDD2024 practitioners?
Large Language Models are powerful but have significant privacy implications when trained on public data. We provide here a comprehensive survey on current threats and available solutions arxiv.org/abs/2408.05212 📜
1
3
212
#UnboxingTransformer If you are in #ACL2024NLP #ACL2024, we are sure: 1) you can try to solve our challenge uniroma2-my.sharepoint.com/:… 2) and, then, you can apply to the OPEN POSITION in our lab. Competitive salary in an astonishing location #ML #NLProc pica.cineca.it/uniroma2/f4-2…
7
8
647
🎉 HAPPY BIRTHDAY #LUFFY !🎉 Thank you for joining us in the celebration for Luffy's birthday on May 5th! You couldn't make it? No worries! We definitely care about you so we have arranged a special giveaway! You may win this special Shikishi illustrated by Keiichi ICHIKAWA coming right off our studio in Tokyo! To participate : 👉 Follow @ToeiAnimationEU 👉 RT this post Only 1 lucky winner will be chosen on May 13th. T&C applies : toei-animation.com/terms-and… #OnePiece #LuffyBirthday2024
135
2,690
53
6,684
7,194,365
#NLProc It's today! The #LLM that will replace me has been presented!
3
12
460
My transformation in #LLM has started :-/ with the Master's Thesis of Simone Abbate This thesis develops a chatbot based on an open-source #LLM with #RAG methodology. The chatbot provides responses to questions over the #NLProc course of Prof. @znz8 SCARY!!!!
3
9
449
Clic-it means to follow very interesting talks to improve the knowledge, but also meet old and new friends! Many thanks @CLiC_it_conf! #clicit2023 #NLProc @AILC_NLP – at Venice, Veneto
5
11
316
If you export your chat history from ChatGPT, you get the system prompt(s) for free, no jailbreaking or similar needed
49
203
32
3,114
560,865
Our new album is out today It's called Gangbusters Melody Club It's our 5th studio album and it has 12 songs Go give it some love, or at least a listen caravanpalace.ffm.to/gmclub
48
363
70
1,202
75,244
#NLProc #LLMs #LLM #ML #Challenge #UnboxingTransformers RT or give us the 4 matrices Transformers are ruling current #AI used as #LLMs Can they also do simple next-token predictions?
2
9
436