Thomas Palmeira
@thomaspalmeira.bsky.social
Working with #LLMs #NLP #Speech for Multilingual, Low-Resource, and Efficient ML
PhD Track at @Polytechnique and @TelecomParis. Science saves lifes! #EMNLP2024 #LoG2024 #NeurIPS2024
http://thomas-ferraz.github.io
https://linktr.ee/_thomaspf
PhD Track at @Polytechnique and @TelecomParis. Science saves lifes! #EMNLP2024 #LoG2024 #NeurIPS2024
http://thomas-ferraz.github.io
https://linktr.ee/_thomaspf
Pinned
Excited to kick off my Bluesky sharing that I just presented our LLM Self-Correction paper at #EMNLP2024! 🎉 We propose a benchmark and a solution for LLMs on multi-constrained instruction following.
Check it: bit.ly/DeCRIM
Super exciting discussion there and lots of new ideas coming out from it!
Check it: bit.ly/DeCRIM
Super exciting discussion there and lots of new ideas coming out from it!
I’M BACK TO THE ALPS! 🏔️⛷️🇫🇷
I am excited to share that I have started a position as a Research Scientist at @naverlabseurope.bsky.social . I'll be working on exciting topics around Memory and Reasoning in LLMs and AI Agents.
I am excited to share that I have started a position as a Research Scientist at @naverlabseurope.bsky.social . I'll be working on exciting topics around Memory and Reasoning in LLMs and AI Agents.
April 23, 2025 at 7:18 PM
I’M BACK TO THE ALPS! 🏔️⛷️🇫🇷
I am excited to share that I have started a position as a Research Scientist at @naverlabseurope.bsky.social . I'll be working on exciting topics around Memory and Reasoning in LLMs and AI Agents.
I am excited to share that I have started a position as a Research Scientist at @naverlabseurope.bsky.social . I'll be working on exciting topics around Memory and Reasoning in LLMs and AI Agents.
A report about judges from Portuguese Courts using LLMs for rulings that cited laws or precedents that don’t exist…
An interesting fact about LLMs is that they are trained using RLHF, a technique to make model learn to generate more relevant and useful responses.
www.publico.pt/2024/11/24/s...
An interesting fact about LLMs is that they are trained using RLHF, a technique to make model learn to generate more relevant and useful responses.
www.publico.pt/2024/11/24/s...
Erros crassos em acórdão levam advogados a suspeitar de inteligência artificial
Caso de adjudicações suspeitas na Misericórdia de Lisboa suscita decisão do Tribunal da Relação que cita leis e jurisprudência inexistentes. Querem julgar arguidos por crimes de que não são acusados.
www.publico.pt
November 28, 2024 at 3:54 PM
A report about judges from Portuguese Courts using LLMs for rulings that cited laws or precedents that don’t exist…
An interesting fact about LLMs is that they are trained using RLHF, a technique to make model learn to generate more relevant and useful responses.
www.publico.pt/2024/11/24/s...
An interesting fact about LLMs is that they are trained using RLHF, a technique to make model learn to generate more relevant and useful responses.
www.publico.pt/2024/11/24/s...
Happy to share our paper "Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media" being presented tomorrow at #LoG2024!
🗓 Tue, Nov 28
⏰ 15h GMT
Virtual
Paper: arxiv.org/pdf/2410.19193
Join us to discuss combating disinformation with GNNs! 🧵 (1/5)
🗓 Tue, Nov 28
⏰ 15h GMT
Virtual
Paper: arxiv.org/pdf/2410.19193
Join us to discuss combating disinformation with GNNs! 🧵 (1/5)
November 28, 2024 at 1:47 PM
Happy to share our paper "Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media" being presented tomorrow at #LoG2024!
🗓 Tue, Nov 28
⏰ 15h GMT
Virtual
Paper: arxiv.org/pdf/2410.19193
Join us to discuss combating disinformation with GNNs! 🧵 (1/5)
🗓 Tue, Nov 28
⏰ 15h GMT
Virtual
Paper: arxiv.org/pdf/2410.19193
Join us to discuss combating disinformation with GNNs! 🧵 (1/5)
Response from HF ethicist about the HF Bluesky scrapped dataset everyone is freaking about
I don't have the answer to the "why" my colleague did it. However, he heard what users had to say, recognized it wasn't an ethical thing to do, and took it down right away. The difference here would be that, maybe, private companies would neither communicate about it nor take it down if asked.
November 28, 2024 at 1:38 PM
Response from HF ethicist about the HF Bluesky scrapped dataset everyone is freaking about
Excited to kick off my Bluesky sharing that I just presented our LLM Self-Correction paper at #EMNLP2024! 🎉 We propose a benchmark and a solution for LLMs on multi-constrained instruction following.
Check it: bit.ly/DeCRIM
Super exciting discussion there and lots of new ideas coming out from it!
Check it: bit.ly/DeCRIM
Super exciting discussion there and lots of new ideas coming out from it!
November 25, 2024 at 4:32 PM
Excited to kick off my Bluesky sharing that I just presented our LLM Self-Correction paper at #EMNLP2024! 🎉 We propose a benchmark and a solution for LLMs on multi-constrained instruction following.
Check it: bit.ly/DeCRIM
Super exciting discussion there and lots of new ideas coming out from it!
Check it: bit.ly/DeCRIM
Super exciting discussion there and lots of new ideas coming out from it!