Iacopo Vagliano

Assistant professor of #health #datascience at @amsterdamumc, location @UvA_Amsterdam

[Iacopo Vagliano @maponaso]

Needed update to tripod and tripod AI or reporting LLM studies!

[Danielle Bitterman, MD @dbittermanmd]

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

[elvis @omarsar0]

Don't do RAG

Proposes cache-augmented generation (CAG) to eliminate retrieval latency and minimize retrieval errors.

What is CAG?

CAG aims to leverage the capabilities of long-context LLMs by preloading the LLM with all relevant docs in advance and precomputing the key-value (KV) cache.

The preloaded context helps the model to provide contextually accurate answers without the need for additional retrieval during runtime.

When to apply CAG?

It's a useful alternative to RAG for cases where the documents/knowledge for retrieval are of limited, manageable size.

My thoughts: As LLMs advance in capabilities, I suspect that what we know as RAG today could change significantly either architecturally or how it's optimized. CAG is one in a growing list of developments and new ideas that have emerged recently to address limitations like poor retrieval relevancy and latency. There could also be hybrid methods that combine preloading with selective retrieval.

Don't sleep on long-context LLMs. They are here to stay.

[Frank Hutter @FrankRHutter]

The data science revolution is getting closer. TabPFN v2 is published in Nature: https://t.co/Ybb15pnZ5P On tabular classification with up to 10k data points & 500 features, in 2.8s TabPFN on average outperforms all other methods, even when tuning them for up to 4 hours🧵1/19

[Iacopo Vagliano @maponaso]

Spunti interessanti per chi vuole sapere di più sull'IA e le sue possibili applicazioni.

[AIxIA @AI_x_IA]

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: https://t.co/0qnsNEUHeG

#AIxIA #IntelligenzaArtificiale #AI

[Iacopo Vagliano @maponaso]

Nice opportunity in a great group!

[Frank van Harmelen @FrankVanHarmele]

And another 3 year postdoc position in our neuro-symbolic AI group (https://t.co/NHFTzYCmrB), this one on reasoning about the harmfulness of internet memes, a really hard multimodal problem that will need both learning & reasoning.
https://t.co/dtNgKFunA6

[Xavier Bresson @xbresson]

Thank you for tuning in!

Slides for my talk "Integrating Graph Neural Networks and Large Language Models"

https://t.co/GFxmfdh2cK

[Iacopo Vagliano @maponaso]

An example to keep in mind when deciding about preprints. Thanks Richard for sharing it.

[Richard Socher @RichardSocher]

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!

[Iacopo Vagliano @maponaso]

@michaelcochez opening the learning on graph conference Amsterdam #LoG AMS @LogConference

[Iacopo Vagliano @maponaso]

Nice hints!

[Itai Yanai @ItaiYanai]

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.
https://t.co/wHZ065DNlm

[LeibnizPostDocs @LeibnizPostDocs]

🚨 Are PostDocs Alright? 🚨

Join us on 27.11.2024, for a joint event by @LeibnizPostDocs & German Postdoc Network as we discuss the latest findings from the Leibniz PostDoc survey!

🕛12:00-13:00 CET

Register now: https://t.co/eKrdJ0Q9Yf

#postdocs #IchBinHanna

[Iacopo Vagliano @maponaso]

Don't miss it!

[Learning on Graphs Conference 2026 @LogConference]

✨EXCITING NEWS! Registration for the 3rd Learning on Graphs conference is now open 📷 It is virtual, free to attend, livestreamed, and recorded 📷https://t.co/HGQdXOBRal

[Ai2 @allen_ai]

Meet Tülu 3 -- a set of state-of-the-art instruct models with fully open data, eval code, and training algorithms.

We invented new methods for fine-tuning language models with RL and built upon best practices in the community to scale synthetic instruction and preference data.

Demo, GitHub, technical report, and models below 👇

[Iacopo Vagliano @maponaso]

📢 25 november komen we in actie tegen de bezuinigingen op onderwijs en onderzoek. Laat ook je stem horen voor toegankelijk onderwijs, tegen ontslagen en tegen de langstudeerboete. Teken de petitie een kom in actie! https://t.co/ha1ZsirXO7

[Rohan Paul @rohanpaul_ai]

Incredible LLM Creation Visualization in this Site.

Click on each section, like Embedding, LayerNorm, Self Attention, and it will show you the mechanics of that section .

(link in comment)

[Iacopo Vagliano @maponaso]

@MihaelaVDS @uni_copenhagen @JEKlopotowska

[Matthew Berman @MatthewBerman]

.@MistralAI launched a ton of new AI features/models today!

The best part? It's all absolutely free.

Here's everything you need to know: 👇

[Iacopo Vagliano @maponaso]

If you look for new research challenges in NLP, here you are with an inspiration

[Maxime Labonne @maximelabonne]

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!

[Fabien Gandon @fabien_gandon]

📢 Call for Papers: Exploring the History of the Web, from Inception to Present @TheWebConf 2025 @TheOfficialACM

📃 2-4 pages paper submission 12/12/2024

👉 https://t.co/D6FxbTwTjh

#TheWebConf25 #WebHistory #InternetHistory #www
cc @w3c @CERN @Inria @timberners_lee @oshaniws

[Xavier Bresson @xbresson]

G-Retriever (https://t.co/BSDZxKwdLP) that leverages the strengths of GraphRAG, LLMs, and GNNs, has now been integrated into the PyG library.

Thanks to @jure and the @PyG_Team team for making this possible!

[Rohan Paul @rohanpaul_ai]

Great read - "Understanding LLMs: A Comprehensive Overview from Training to Inference"

The journey from self-attention mechanism to the final LLMs.

This paper reviews the evolution of large language model training techniques and inference deployment technologies.

--------

→ The evolution of LLMs and current training paradigm

Training approaches have evolved from supervised learning to pre-training and fine-tuning, now focusing on cost-efficient deployment. Current focus is on achieving high performance through minimal computational resources.

→ Core architectural components enabling LLMs' success

The Transformer architecture with its self-attention mechanism forms the backbone. Key elements include encoder-decoder or decoder-only designs, enabling parallel processing and handling long-range dependencies.

→ Key challenges in training and deployment

Main challenges include massive computational requirements, extensive data preparation needs, and hardware limitations. Solutions involve parallel training strategies and memory optimization techniques.

→ The role of data and preprocessing in LLM development

High-quality data curation and preprocessing are crucial. Steps include filtering low-quality content, deduplication, privacy protection, and bias mitigation.

🔍 Critical Analysis & Key Points:

→ Data preparation strategies drive model quality

Processing raw data through sophisticated filtering, deduplication and cleaning pipelines directly impacts model performance.

→ Parallel training techniques enable massive scale

Using data parallelism, model parallelism and pipeline parallelism allows training billion-parameter models efficiently.

→ Memory optimization is crucial for inference

Techniques like quantization, pruning and knowledge distillation help deploy large models with limited resources.