Antonela
@tommantonela89
Followers
163
Following
571
Media
47
Statuses
284
PhD in Computer Science. 📖📖 🤓🌎✈️ 🇦🇷 🇬🇧 🇫🇷 🇮🇹 🇧🇷 🇩🇪🇩🇰 . Researcher at @CONICETDialoga. #socialmedia #recommendersystems
Tandil, Argentina
Joined June 2018
RT @DuiaUnicen: Gracias Joaquín por la gran charla!.Nos llevamos muchas ideas sobre cómo usar NLP y LLMs para fortalecer la verificación, e….
0
1
0
RT @DuiaUnicen: Gracias @adiazpace por la charla inspiradora sobre agentes de IA y su potencial transformador! 💡 Nos quedamos con muchas id….
0
2
0
RT @DuiaUnicen: Ciclo de charlas de la DUIA:🤖💼 Agentes de IA que automatizan tareas, colaboran con humanos y transforman procesos. @adiazpa….
0
2
0
RT @DuiaUnicen: 🧠📊 Ciclo de charlas DUIA: ¿Cómo puede la IA fortalecer el periodismo y la lucha contra la desinformación?.Joaquín Saralegui….
0
3
0
RT @DuiaUnicen: 📢 ¡Se vienen dos charlas imperdibles!.🔹 IA y periodismo con Joaquín Saralegui.🔹 Agentes de IA en procesos productivos con A….
0
2
0
RT @jm_rodrig: 🚨 New research alert! 🚨. Excited to share that @tommantonela89 and I have published "Countering the Spread: An Approach to….
ieeexplore.ieee.org
Although social media generally provides a safe and enjoyable experience, it can also serve as a quick and easy means for spreading false news, misinformation, and other harmful content. These...
0
1
0
🎉 Check out our new paper on llm agents!.
📷 Exciting news! Our paper " Architecture Exploration and Reflection meet LLM-based Agents" has been accepted at #ICSA2025! w/Antonela (@tommantonela89) and Rafael Capilla. Here's a quick overview of what we've been working 📷1/5
0
0
4
RT @jm_rodrig: You can read our latest paper "Leveraging User History with Transformers for News Clicking: The DArgk Approach". A transform….
dl.acm.org
0
1
0
RT @DrCh0le: "Human Centered AI is *not* putting the human in a circle or robots" but also "humans are complex" 🤭 @mark_riedl invites us t….
0
3
0
Results showed that the proposed technique can outperform traditional and SOTA aggregation techniques, both in terms of relevance and diversity/novelty. LLMs didn't contribute as much as we expected, but they still helped to further improving recommendations’ relevance.
1
0
0
We focused on whether MCTS can improve the beyond-accuracy quality of recommendations. LLMs couldn't be left out :) So, we also evaluated whether LLMs could help in better assessing group satisfaction.
1
0
0
So, we treated the aggregation problem as a search problem and used Monte Carlo Tree Search (MCTS) to explore and evaluate the potencial sequences of recommendations.
1
0
0
A common approach is to aggregate the rankings obtained for each group member using Social Choice Theory strategies. But, these strategies often select items independently. While items may be individually relevant, the overall sequence might lack diversity, novelty, or fairness.
1
0
0
I'm happy to share that our paper "Leveraging Monte Carlo Tree Search for Group Recommendation" has been accepted at #recsys2024. 😁🥳. w/@adiazpace . @ACMRecSys. A mini-🧵
1
2
7
📢📢 ACM TORS Special Issue #recsys for #Good, submission deadline extended to 24. December 2024! More info: w/@RecSysMare, @noemi_mauro1, @alansaid, @navatintarev
0
5
8
RT @RecSysMare: ACM TORS Special Issue on #Recommender #Systems for #Good, submission deadline extended to 24. December 2024. https://t.co/….
0
2
0
RT @adiazpace: I'm happy to share that our paper "Helping novice architects to make quality design decisions using LLM-based assistants" ha….
0
1
0