Edoardo D'Amico

Research Scientist @Spotify | Generative AI & Recommender System | building minlit in my free time.

[Edoardo D'Amico @edoardo_damico_]

https://t.co/C6oC7hCTuV

[Google Research @GoogleResearch]

Experience AI Scientist, a novel multi-agent system designed to automate the end-to-end scientific research pipeline. Meet Jinsung Yoon and Rui Meng today at 6:00pm at the Google booth (#B206) to learn how complex workflows reliably accelerate AI discovery. #ICML2026

[Edoardo D'Amico @edoardo_damico_]

https://t.co/ydGXpukMHg

[Kamil Ciosek @MLciosek]

For anyone worried their LLM might be making stuff up, we made a budget‐friendly truth serum (semantic entropy + Bayesian). See for yourself: https://t.co/gq8oFP5Eqr
Paper: https://t.co/s6SuQW4sAM

[ACM RecSys @ACMRecSys]

Pro tip from #RecSys2024: If you're coming to Italy by plane, don't embark on the wrong flight. While Bali may be tempting, we also have beaches and sunshine in Bari.

So, go for Bari; with the r of RecSys!

[Aonghus Lawlor @aonghuslawlor]

Aayush and Edoardo presenting their work on Scalable Slate Recoomendation at RecSys in Singapore ⁦@insight_centre⁩ ⁦@UCDCompSci⁩ ⁦@edoardo_damico_⁩ ⁦@aayushsingharoy⁩ #recsys2023

[Edoardo D'Amico @edoardo_damico_]

It is with great pleasure that I announce that our paper titled "Scalable Deep Q-Learning for Session-Based Slate Recommendation" has been accepted as a short paper at RecSys 2023! 🎉
Can't wait to present our research at the conference!
#RecSys2023 @insight_centre @UCDCompSci

[Edoardo D'Amico @edoardo_damico_]

@oconnorn Thank you !

[Aonghus Lawlor @aonghuslawlor]

⁦@edoardo_damico_⁩ presenting his work on “Pure Spectral Graph Embeddings” at PAKDD23 #pakdd ⁦@insight_centre⁩ ⁦@UCDCompSci⁩

[Mark Tenenholtz @marktenenholtz]

Some papers that were rejected:

• PPO (used to train ChatGPT)
• SVM
• SIFT
• YOLO
• GELU
• LSTM
• Dropout
• RoBERTa
• MinTrace
• PageRank
• Kalyan Filters
• Transformer-XL
• Word2Vec (poster)
• Viola-Jones Face Detector

And that’s why open research is good.

[Edoardo D'Amico @edoardo_damico_]

In 2022, I spent 344 hours training 6,843 models on @wandb! My #longestrun, zany-sunset-11, trained for 49 hours. Here's its collector card, with an image generated by DALL·E 2 from @OpenAI: https://t.co/METe5E6VS3

[Edoardo D'Amico @edoardo_damico_]

Proud of it !

[Giovanni Gabbolini @GGabbolini]

Our paper "On the instability of embeddings for recommender systems:the case of Matrix Factorization" just got accepted at ACM SAC '21! 🚀
Joint work with @amico_edoardo, Cesare Bernardis and @crmpla67

[Yann LeCun @ylecun]

A couple papers from 2016.
Sort of like those doomsday movies with the ignored scientist warning of impending doom.

[Edoardo D'Amico @edoardo_damico_]

Happy to announce that I have concluded my first month as a PhD student at @insight_centre,
started investigating about graph-based recommender systems.

Looking forward to the @recsyschallenge 2020!