Dario Di Palma (@dariodipalma_) 's Twitter Profile
Dario Di Palma

@dariodipalma_

PhD student at @PolibaOfficial | @sisinflab
Interested in Recommender Systems, Large Language Models and Conversational Agent

ID: 866669287016189952

linkhttps://github.com/DarioDiPalma-DDP calendar_today22-05-2017 14:57:14

22 Tweet

52 Followers

135 Following

Claudio Pomo (@scne) 's Twitter Profile Photo

Get ready for #EvalRS2023 at #KDD, where we'll deep dive into RecSys evaluations, tackling fairness, bias, robustness, & trustworthiness of #RecSys. Don't miss out! Submit your papers & join our thrilling hackathon with amazing awards & prizes! Learn more: reclist.io/kdd2023-cup/

Get ready for #EvalRS2023 at #KDD, where we'll deep dive into RecSys evaluations, tackling fairness, bias, robustness, & trustworthiness of #RecSys. Don't miss out!
Submit your papers & join our thrilling hackathon with amazing awards & prizes! Learn more: reclist.io/kdd2023-cup/
Pan Lu (@lupantech) 's Twitter Profile Photo

🔥Thrilled to release LLaMa-Adapter Multimodal! 🎯Now supporting text, image, audio, and video inputs powered by #ImageBind. 🧵6 💻Codes for inference, pretraining, and finetuning ➕ checkpoints: github.com/ZrrSkywalker/L… demo: llama-adapter.opengvlab.com abs: arxiv.org/abs/2304.15010

🔥Thrilled to release LLaMa-Adapter Multimodal!

🎯Now supporting text, image, audio, and video inputs powered by #ImageBind. 🧵6

💻Codes for inference, pretraining, and finetuning ➕ checkpoints:
github.com/ZrrSkywalker/L…
demo: llama-adapter.opengvlab.com
abs: arxiv.org/abs/2304.15010
Daniele Malitesta (@dmalitesta) 's Twitter Profile Photo

We taught you how to run #reproducible experiments for #graph #collaborativefiltering at #UMAP2023. Now, we'll show you how we used this tool to disentangle the graph CF #performance. Our paper on the reproducibility of graph CF has been accepted at #RecSys2023 🎉🎉 (1/2)

AK (@_akhaliq) 's Twitter Profile Photo

DreamDiffusion: Generating High-Quality Images from Brain EEG Signals paper page: huggingface.co/papers/2306.16… paper introduces DreamDiffusion, a novel method for generating high-quality images directly from brain electroencephalogram (EEG) signals, without the need to translate

DreamDiffusion: Generating High-Quality Images from Brain EEG Signals

paper page: huggingface.co/papers/2306.16…

paper introduces DreamDiffusion, a novel method for generating high-quality images directly from brain electroencephalogram (EEG) signals, without the need to translate
Massimo (@rainmaker1973) 's Twitter Profile Photo

Matt Baker's poster Evolution of the Alphabet looks at nearly 3,800 years of the alphabet’s evolution, tracing it from Egyptian hieroglyphs to the present forms we use today [source, read more: buff.ly/3t9qEvq]

Matt Baker's poster Evolution of the Alphabet looks at nearly 3,800 years of the alphabet’s evolution, tracing it from Egyptian hieroglyphs to the present forms we use today 

[source, read more: buff.ly/3t9qEvq]
Calc Consulting (@calccon) 's Twitter Profile Photo

Where did I come up with the idea for weightwatcher ? I used to be a quant at Blackrock. And as a quant, my job was to find signal in the noise.

Where did I come up with the idea for weightwatcher ? I used to be a quant at Blackrock. And as a quant, my job was to find signal in the noise.
Vincenzo Paparella (@vinc_papa) 's Twitter Profile Photo

Delighted to share that "Broadening the Scope: Evaluating the Potential of Recommender Systems beyond prioritizing Accuracy", w/ Dario Di Palma, Walter Anelli, Tommaso Di Noia got accepted to LBR track at #RecSys2023. 🍾🍾

Alberto Carlo Maria Mancino (@alberto_mancino) 's Twitter Profile Photo

Virtual Poster Session 3 Online at #SIGIR2023. Take a look at my presentation of "Denoise to Protect: A Method to Robustify Visual Recommenders from Adversaries": an effective method for protecting recommendations by denoising item images dl.acm.org/doi/10.1145/35…

Virtual Poster Session 3 Online at #SIGIR2023. 
Take a look at my presentation of "Denoise to Protect: A Method to Robustify Visual Recommenders from Adversaries": an effective method for protecting recommendations by denoising item images
dl.acm.org/doi/10.1145/35…
Dario Di Palma (@dariodipalma_) 's Twitter Profile Photo

Exciting discussions and fresh insights at #PERSPECTIVES2023! 🧠💡 Delving deep into the world of Recommender Systems at the ACM Recommender Systems Workshop. Stay tuned for innovative perspectives on evaluation! #RecSys #AI #WorkshopBuzz 📚🤖 By Christine Bauer and Alan Said

Exciting discussions and fresh insights at #PERSPECTIVES2023! 🧠💡 Delving deep into the world of Recommender Systems at the ACM Recommender Systems Workshop. Stay tuned for innovative perspectives on evaluation! #RecSys #AI #WorkshopBuzz 📚🤖

By <a href="/christine_bauer/">Christine Bauer</a>  and <a href="/alansaid/">Alan Said</a>
Dario Di Palma (@dariodipalma_) 's Twitter Profile Photo

It was an interesting keynote at #RecTour2023 🌍🗝️ by Andrea Marchini from Expedia Group! Exploring 'Fast, Flexible, and Personalized: Leveraging Bandits for Travel Recommendations.' 🌄🏖️ #TourismRecommendations #RecSys

It was an interesting keynote at #RecTour2023 🌍🗝️ by Andrea Marchini from <a href="/ExpediaGroup/">Expedia Group</a>! Exploring 'Fast, Flexible, and Personalized: Leveraging Bandits for Travel Recommendations.' 🌄🏖️ #TourismRecommendations #RecSys
Brendan Bycroft (@brendanbycroft) 's Twitter Profile Photo

Project #2: LLM Visualization So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)

Santiago (@svpino) 's Twitter Profile Photo

I want to show you a clever trick you didn't know before. Imagine you have six months' worth of data. You want to build a model, so you take the first five months to train it. Then, you use the last month to test it. This is a common approach for building machine learning

I want to show you a clever trick you didn't know before.

Imagine you have six months' worth of data. You want to build a model, so you take the first five months to train it. Then, you use the last month to test it.

This is a common approach for building machine learning
Andrej Karpathy (@karpathy) 's Twitter Profile Photo

# CUDA/C++ origins of Deep Learning Fun fact many people might have heard about the ImageNet / AlexNet moment of 2012, and the deep learning revolution it started. en.wikipedia.org/wiki/AlexNet What's maybe a bit less known is that the code backing this winning submission to the

# CUDA/C++ origins of Deep Learning

Fun fact many people might have heard about the ImageNet / AlexNet moment of 2012, and the deep learning revolution it started.
en.wikipedia.org/wiki/AlexNet

What's maybe a bit less known is that the code backing this winning submission to the
Giovanni Maria Biancofiore (@gmbiancofiore) 's Twitter Profile Photo

📢 Excited to share our chapter “Conversational User Interfaces and Agents” in Human-Centered AI: An Illustrated Scientific Quest (Springer HCI Series)! 🔗 doi.org/10.1007/978-3-… #HumanCenteredAI #HCI #NLP #ConversationalAgent #Research #SpringerAI

Felice Antonio Merra (@merrafelice) 's Twitter Profile Photo

At a coffe break of #RecSys2024, I and Dario Di Palma asked ourselves: ‘Do LLMs Memorize Recommendation Datasets?’ Then, we tried to answer it and the result of ‘A Preliminary Study on MovieLens-1M’ has been accepted at #SIGIR2025 In Pills? Big LLMs can memorize the testset :/

At a coffe break of #RecSys2024, I and <a href="/DarioDiPalma_/">Dario Di Palma</a> asked ourselves: ‘Do LLMs Memorize Recommendation Datasets?’

Then, we tried to answer it and the result of ‘A Preliminary Study on MovieLens-1M’ has been accepted at #SIGIR2025

In Pills? Big LLMs can memorize the testset :/
Sumit (@_reachsumit) 's Twitter Profile Photo

Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M Dario Di Palma et al. reveal that popular LLMs have memorized substantial portions of MovieLens-1M, with memorization directly correlating to recommendation performance. 📝arxiv.org/abs/2505.10212