Presenting in front of a live audience was an amazing experience :) hope we nailed it! Thanks ACL 2025

BTW.... dalle-mega from Boris Dayma 🖍️ is now openly accessible on Hugging Face ⚡️ To download it (10GB): git clone huggingface.co/dalle-mini/dal…

This week Google researchers announced Minerva, an internally developed project that can answer mathematical questions and tackle other complex topics such as physics. 1/5

Hey #NLProc, I built this little tool to make working with Hugging Face 🤗Transformers a bit easier. If you want to directly access whole-word embeddings hassle-free, give it a try! 👉GitHub: github.com/Riccorl/transf…

YouTube is free education. But 99% don’t know the best spots on its virtual campus. Here are the top channels to accelerate your learning:

Three papers accepted at NeurIPS'22 (!!) 1) Efficiently training low-curvature neural networks (arxiv.org/abs/2206.07144), w/ Kyle Matoba, 𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞, François Fleuret We propose to build NNs that are "as linear as possible", and thus eliminate excess model curvature.

Presentiamo il più grande LLM italiano realizzato dal gruppo di ricerca RSTLess della Sapienza Università di Roma. Il team di ricerca dietro Fauno comprende Andrea Bacciu, Giovanni Trappolini, Prof Emanuele Rodolà , Andrea Santilli e il Prof Fabrizio Silvestri . github.com/RSTLess-resear…

LIMA : LLaMA 65B + 1000 supervised samples = {GPT4, Bard} level performance. From @MetaAI arxiv.org/abs/2305.11206

MMS: Massively Multilingual Speech. - Can do speech2text and text speech in 1100 languages. - Can recognize 4000 spoken languages. - Code and models available under the CC-BY-NC 4.0 license. - half the word error rate of Whisper. Code+Models: github.com/facebookresear… Paper:

QLoRA: 4-bit finetuning of LLMs is here! With it comes Guanaco, a chatbot on a single GPU, achieving 99% ChatGPT performance on the Vicuna benchmark: Paper: arxiv.org/abs/2305.14314 Code+Demo: github.com/artidoro/qlora Samples: colab.research.google.com/drive/1kK6xasH… Colab: colab.research.google.com/drive/17XEqL1J…

Still can't handle the indecisiveness between Barbie and Oppenheimer? 😫💥 Don't fret! Come to the presentation of our new perspective paper, "Multimodal Neural Databases", where we lay out the vision for database-like queries on multimodal data. Tomorrow SIGIR 2023, 1.30pm GMT+8

Redefining Retrieval in RAG A nice comprehensive study that focuses on the components needed to improve the retrieval component of a RAG system. Confirms that the position of relevant information should be placed near the query. The model will struggle to attend to the

🤯 Think adding nonsense to RAG systems is madness? Our new paper says otherwise! We found that including random documents boost accuracy by 30+%, challenging old paradigms and showing the complexity of integrating retrieval w/ language generation. #RAGSystems #surprisingresults

This is actually huge: - No SFT stage (e.g., Zephyr used 200k examples) - Preference tuning with 7K examples only (other models trained with at least 60k samples) I've put a lot of care & love building the DPO version of the amazing Capybara dataset from LDJ so I'm

Llama 3 is insanely moving fast. People are really pushing Llama 3 to its limits in incredible ways. 10 wild examples (and use cases)

Don't miss Andrea Bacciu and Cesare Campagnano ’s presentation on Thursday at LREC COLING 2024 .They’ll be sharing their paper "DanteLLM: Let’s Push Italian LLM Research Forward!”, coauthored with Fabrizio Silvestri and Giovanni Trappolini . Room London @  Lingotto Conference Centre, 3.30 pm CET.

Today Andrea Bacciu  has presented the paper "DanteLLM: Let’s Push Italian LLM Research Forward!” LREC COLING 2024 , coauthored by Cesare Campagnano Giovanni Trappolini and Fabrizio Silvestri . Here is the preprint aclanthology.org/2024.lrec-main… #LLM #Research #LREC #PhD

Congratulations to Cesare Campagnano who defended his #PhD #thesis entitled "Foundational Advancements of Large Language Models: Current and Future Implications", advised by Gabriele Tolomei , co-advised by Fabrizio Silvestri . He will now start his #postdoc in our group. #LLM #NLP #Research

Congratulations to our very own Antonio Mallia, Cesare Campagnano, and @JackPertschuk – as well as their co-authors – on their accepted #ECIR2025 research papers! 🎉 They continue to push the state-of-the-art forward on information retrieval, and we as an industry are better for it!

We are very excited to share that the work of Cesare Campagnano , Antonio Mallia , @JackPertschuk and Fabrizio Silvestri has been accepted to #ECIR2025 as a #shortpaper. See you in #Lucca. ECIR2025 Pinecone #AI #Research #IR #industry