
ML for Structured Data | PhD @TU_Muenchen | Curr. @nvidia, prev. @MSFTResearch
Munich, Bavaria
Joined October 2012
- Tweets62
- Following312
- Followers145
- Likes199
Pinned Tweet
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.
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 )
🧵
4
359
Filippo Guerranti retweeted
The paper and pretraining code for @Nvidia Kumo Tabular are out!
This includes optimized pretraining, many updates to the prior including a distributional numerical converter, and an ablation study! The largest gains come from scaling and interleaved row-colum attention.
Today we share the NVIDIA Kumo Tabular technical report as well as the training recipe! 🚀
Trained entirely on synthetic tables, Kumo Tabular-L leads 8 benchmark suites. All 3 model sizes achieve Pareto-optimal accuracy vs. inference time.
Arxiv: arxiv.org/abs/2611.23001
HuggingFace: huggingface.co/nvidia/Kumo-T…
GitHub: github.com/NVIDIA/structured…
Filippo Guerranti retweeted
Today we share the NVIDIA Kumo Tabular technical report as well as the training recipe! 🚀
Trained entirely on synthetic tables, Kumo Tabular-L leads 8 benchmark suites. All 3 model sizes achieve Pareto-optimal accuracy vs. inference time.
Arxiv: arxiv.org/abs/2611.23001
HuggingFace: huggingface.co/nvidia/Kumo-T…
GitHub: github.com/NVIDIA/structured…
Filippo Guerranti retweeted
Discrete flow matching usually changes one component per edit in a fixed-size state. Can we extend it to general actions, like inserting whole molecular fragments?
Introducing Trajectory Matching 🧵
New paper with M. Lienen, @ludke_david, @guennemann
Filippo Guerranti retweeted
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!
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 retweeted
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/
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 🧵👇
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)
Always happy to chat about graphs, generative models, or spatial omics while in San Diego. 🌊
See you there!
1️⃣openreview.net/forum?id=d2Eo…
2️⃣openreview.net/forum?id=5ofJ…
3️⃣ arxiv.org/abs/2509.06743
#MachineLearning #GraphML #GenerativeModels #SpatialTranscriptomics
5
171
Filippo Guerranti retweeted
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]🧵
Filippo Guerranti retweeted
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: arxiv.org/abs/2509.01254
Joint work /w @TomWollschlager @guennemann 🧵 (1/6)
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
📄 arxiv.org/abs/2507.13381
w/ R. Kamel, @geisler_si, @guennemann
1/5
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.
1
1
60
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
1
79
Filippo Guerranti retweeted
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. 🧵
















