Filippo Guerranti @ NeurIPS25

PhD student @TU_Muenchen | ML for Graphs and Relational Data

[Filippo Guerranti @ NeurIPS25 @guerrantif]

Our #NeurIPS2025 paper, NicheFlow, is out. In his thread, @k_sakalyan walks through how we model the evolution of cellular microenvironments in spatial transcriptomics. Worth reading if you want the details. Thanks @ale__palmaa @fabian_theis @guennemann.

[Kristiyan Sakalyan @k_sakalyan]

Our paper “Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow” has been accepted at #NeurIPS2025!

@ale__palmaa @guerrantif @fabian_theis @guennemann

(@TU_Muenchen × @HelmholtzMunich × @MunichCenterML × @MdsiTum )

🧵

[Stephan Günnemann @guennemann]

This is happening today:
Wed, Dec 3, 2025 • 4:30 PM – 7:30 PM PST
Exhibit Hall C,D,E #3715

Looking forward to the discussions!

[Amine Ketata @amine_ketata]

Excited to share that my first PhD paper, which introduces a new diffusion model for relational databases, has been accepted to #NeurIPS2025! We will be presenting it this week in San Diego. ☀️🌴

Joint work with @ludke_david, @SchwinnLeo, and @guennemann.

🧵 1/

[Filippo Guerranti @ NeurIPS25 @guerrantif]

Always happy to chat about graphs, generative models, or spatial omics while in San Diego. 🌊

See you there!

1️⃣https://t.co/SLhn6YL4yl
2️⃣https://t.co/2sBx3MkKUo
3️⃣ https://t.co/eRanXcREOn

#MachineLearning #GraphML #GenerativeModels #SpatialTranscriptomics

[Filippo Guerranti @ NeurIPS25 @guerrantif]

Heading to San Diego for #NeurIPS2025! 🌴☀️

I’ll be presenting 3 recent papers covering generative models for hierarchies, spatiotemporal tissue dynamics, and long-range graph learning.

If you're around, drop by and say hi! 👋

Here’s the schedule 🧵👇

[Filippo Guerranti @ NeurIPS25 @guerrantif]

3️⃣ #LRGWN: Long-Range Graph Wavelet Networks

We combine local polynomial filters with global spectral filters to efficiently model long-range interactions in graphs.

📍 NPGML Workshop (Hall F) | Poster #26 🕒 Sun 7 Dec, 9:00–9:30 PST
(w/ F. Forte @geisler_si @guennemann)

[Tim Tomov @timtomov]

Can we actually tell when LLMs know or don’t know?

For questions with a single answer, that works. But once ambiguity enters - several answers are correct - current methods collapse, confusing model with data uncertainty.

w/ @dfuchsgruber @TomWollschlager @guennemann

[1/4]🧵

[NiklasKemper @kemper_ni]

The hunt for increased WL expressivity has led to many new GNNs but limited real-world success.
So what are we missing? Can we find a better objective? We answer these questions in our new paper: https://t.co/jrNtzM9mdY
Joint work /w @TomWollschlager @guennemann 🧵 (1/6)

[Filippo Guerranti @ NeurIPS25 @guerrantif]

Quick clarification on the first figure:
- Linearization does not preserve structure, but does not require model changes.
- Graph encoders preserve structure, but typically require model changes.

[Filippo Guerranti @ NeurIPS25 @guerrantif]

Injecting structure into LLMs with no changes to the architecture?
SAFT🧃
Structure-aware LLM fine-tuning for AMR-to-text. New SOTA + no model changes!

📍#SKnowLLM, KDD, Toronto 🇨🇦
🗓️ Aug 4, 1–5pm · Room 717
📄 https://t.co/sgBzmEHzDa
w/ R. Kamel, @geisler_si, @guennemann

1/5

[Filippo Guerranti @ NeurIPS25 @guerrantif]

5/5

If you’re working on LLMs for structured data (graphs, trees, AMRs, and so on) stop by!

We’ll be at the KDD Workshop on Structure Knowledge for LLM #SKnowLLM

📍Toronto 🇨🇦 · MTCC · Room 717
🕐 August 4th, 1–5pm

SAFT: Structure-Aware Fine-Tuning for LLMs

[Filippo Guerranti @ NeurIPS25 @guerrantif]

4/5

🏆 Results?
SAFT improves across models and dataset scales:

· +3.5 BLEU vs prior SOTA (no extra data)
· Improves generalization on long + complex graphs
· Compatible with LLaMA, Qwen, Gemma, etc.

[Simon Geisler @geisler_si]

Do you think your LLM is robust?⚠️With current adversarial attacks it is hard to find out since they optimize the wrong thing! We fix this with our adaptive, semantic, and distributional objective.

By @guennemann's lab & @GoogleAI, w/ @cais support

Here's how we did it. 🧵

[Hannes Stark @HannesStaerk]

Monday with @n_gao96 in the reading group "Learning Equivariant Non-Local Electron Density Functionals" https://t.co/RfDtZSmO03

Join us on zoom at 9am PT / 12pm ET / 6pm CET: https://t.co/R8d1EHxLCx

[Jan Schuchardt @SchuchardtJan]

Deep learning with differential privacy can protect sensitive information of individuals. But what about groups of multiple users?

We answer this question in our #NeurIPS2024 paper https://t.co/PemQWF3PAq

Joint work w/ @mihail_sto @ArthurK48147 @guennemann. #Neurips (1/7)

[Amine Ketata @amine_ketata]

Excited to share that my master's thesis on "molecular graph generation in latent Euclidean space" was accepted at @GRaM_workshop and selected for an oral presentation.

If you are at @icmlconf on Saturday, make sure to stop by.