←
Davide Buscaldi508 posts
Davide Buscaldi avatar

Davide Buscaldi

@davidebus

Maître de conférences @LipnLab, @univ_spn Professeur Chargé de Cours au DIX, @Polytechnique +papà / escrime / violoncelle

◷ Joined October 2009▧ 44 Photos and videos
Davide Buscaldi avatar
Davide Buscaldi@davidebus·5 Mar 2025

Just a heads up: this account will not be updated anymore. I'll still be active on my accounts on Mastodon and LinkedIn.

Davide Buscaldi avatar
Davide Buscaldi@davidebus·2 May 2024

I'm very happy to announce that the paper "Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation" authored by Hugo Attali, myself and Nathalie Pernelle has been accepted at #icml2024 !!! Congratulations Hugo for your hard work!

Davide Buscaldi avatar
Davide Buscaldi@davidebus·5 Apr 2024

New low in reviewing quality: R3:"why didn't you test your method on dataset X and Y?" -> results for datasets X and Y are in the result table I mean, it doesn't even require one to have read the paper, just a look at the tables and figures... (this is at KDD btw)

Andrew Ng avatar
⟳ Davide Buscaldi retweeted
Andrew Ng@AndrewYNg·13 Mar 2024

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by @akollegger of @neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here! deeplearning.ai/short-course…

3:46