Iacopo Vagliano

TRIPOD-LLM is out! Check out our consensus guidelines for reporting #LLM research in biomedicine. TRIPOD-LLM is intended to be a living guideline to keep up with the rapid advances in #LLMs/Gen AI. Kudos to lead author @JackGallifant

Il nostro presidente, Gianluigi Greco, è stato intervistato da Rai News. Nell’intervento ha spiegato alcuni dei modi in cui l’AI può aiutare la nostra società. Scopriamo di più insieme: rainews.it/video/2024/09/int… #AIxIA #IntelligenzaArtificiale #AI

And another 3 year postdoc position in our neuro-symbolic AI group (lr.cs.vu.nl), this one on reasoning about the harmfulness of internet memes, a really hard multimodal problem that will need both learning & reasoning. linkedin.com/jobs/view/40872…

Just 6 years ago. This NLP reviewer was 100% certain that prompt engineering to unify all NLP problems in a single neural network and just ask it any question was completely misguided and rejected the paper. It would then be cited by the GPT2 and 3 papers. Thanks @arxiv!

How to write a grant? 1. Write it for the reviewer, not you, the applicant. 2. Communicate in stories. 3. Make your story cohesive—leave no puzzling gaps. 4. Make your story resonate to keep the reviewer reading. 5. Accept chance and noise in peer-review. pnas.org/doi/epub/10.1073/pn…

✨EXCITING NEWS! Registration for the 3rd Learning on Graphs conference is now open 📷 It is virtual, free to attend, livestreamed, and recorded 📷forms.gle/eYiDCopJGUc8pxgX8

Here are 9 AI datasets still dominated by humans 👇 It shows the insane amount of value left to capture Will these tasks be solved through ad-hoc LLM engineering by companies or directly by LLM providers? Thanks to @ldjconfirmed for the data!

AKOrN is here: arxiv.org/pdf/2410.13821. It replaces threshold units with generalized Kuramoto oscillators. It dynamically binds neurons, generates waves of activations, is adversarially robust, calibrated for uncertainty, and can reason. If you ask me: this is the next big thing!

This year’s #NobelPrize laureate in physics John Hopfield created an associative memory that can store and reconstruct images and other types of patterns in data. The Hopfield network can store patterns and has a method for recreating them. When the network is given an incomplete or slightly distorted pattern, the method can find the stored pattern that is most similar. Read more about the research that led to this year’s physics prize: bit.ly/3Bi9H8u

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

OpenAI's o1-preview is the king 👑 of code generation but is super slow and expensive 😱 This and other insights of analyzing >80 LLMs in the deep dive blog post from the DevQualityEval v0.6 for generating quality code 👇 - OpenAI’s o1-preview and o1-mini are slightly ahead of Anthropic’s Claude 3.5 Sonnet in functional score, but are MUCH slower and chattier. - DeepSeek’s v2 is still the king of cost-effectiveness, but GPT-4o-mini and Meta’s Llama 3.1 405B are catching up. - o1-preview and o1-mini are worse than GPT-4o-mini in transpiling code - Best in Go is o1-mini, best in Java GPT4-turbo, best in Ruby o1-preview Please support our work for the community by liking and sharing this post! 🙏 All the details and how we will solve the "ceiling problem" in the deep dive symflower.com/en/company/blo… (2x the content as the previous one!)

🌸📖 I am literally *proud* to announce that our book *Recommendation with #Generative Models* is now available online! A great collaboration with brilliant minds, covering everything from fundamentals to more advanced #GenRecSys models and new application areas: arxiv.org/abs/2409.15173 - Ch. 1: "Motivation & Benefits of Gen-RecSys" - Ch. 2: "Foundations" (for educational purposes) - Ch. 3: "ID-based/Collaborative Models" (AR, GANs, VAEs, Diffusion, Flor-based) - Ch. 4: "LLMs" (seq-to-seq, encoder-only, conversational) - Ch. 5: "Multimodal Models" (DALL-E, Stable Diffusion) - Ch. 6: "Evaluation" (impact, performance metrics, LLM eval) - Ch. 7: "Social & Ethical Risks" (new challenges, risks, social, ethical) #AI #RecommenderSystems #GenerativeModels #LLMs #Foundationmodels #evaluation #risks

Transformer by hand✍️ Excel ~ I designed this exercise to show the core math of a Transformer model is to combine columns (attention), combine rows (feed forward), and repeat.👇Join the 'AI Math' community. 👇Download xlsx.

I read "Bias/Variance is not the same as Approximation/Estimation" which is a really nice read on what the title says. There is still so much to be learnt from some of these "simple" equations and decompositions openreview.net/forum?id=4TnF…

RAG and Beyond Microsoft Research presents a survey that introduces a RAG task categorization method that helps to classify user queries into four levels according to the type of external data required and the focus of the task. Also summarizes key challenges in building robust data-augmented LLM applications and the most effective techniques for addressing them.

My lab published a total of 32 cutting-edge papers at the last #ICML, #ICLR, #NeurIPS & #AISTATS - many by my first year PhD students! Do you want your career visible from the very start and where it matters most? Apply for a PhD with us at @Cambridge_Uni: vanderschaar-lab.com/join-th…