Lorenzo Basile retweeted
In JEPA, are we preventing collapse in the representation we actually use downstream?
TLDR: not necessarily. A high-rank projected representation does not guarantee a non-collapsed backbone.
λ-JEPA is designed to target this gap. arxiv.org/abs/2609.35288
Lorenzo Basile retweeted
Check out DEVIL, now out in @NatureComms!
DEVIL is a Bayesian, GPU‑powered framework for single‑cell differential expression that lets you analyze cohorts with millions of cells from multiple patients without losing statistical rigor.
📄doi.org/10.1038/s41467-026-7…
Lorenzo Basile retweeted
Happy to announce that one of my PhD papers is out!
We build and analyse a synthetic WGS cohort of >200 samples with complete evolutionary ground truth: caravagnalab.github.io/SCOUT…
Joint effort with @GiorgiaGandolf1 and thanks to all co-authors and supervisors! Thread below!
🧬 New preprint: SCOUT (Synthetic Cohort Of Universal Tumours)
A benchmark for cancer WGS where the entire tumour evolutionary history is known.
📊 7 tumour models
🧪 24 biopsies
💾 223 FASTQs
🗄️ >27 TB of data!
#CancerGenomics #tumourevolution
caravagnalab.github.io/SCOUT…
Lorenzo Basile retweeted
🎨Activation steering can reliably push a text-to-image generator toward a visual concept, but at a cost: each concept needs its own estimation.
⚡HyperTransport (HT) predicts the intervention directly, matching per-concept SOTA at 3–4 orders of magnitude less cost.
[1/6]
Lorenzo Basile retweeted
Steering generative models with LinEAS is:
– parameter-efficient
– fine-grained
– data-efficient
– robust across models and modalities
Come check it out at #NeurIPS2025!
🗓️ Dec 5 • 4:30–7:30 PM PST
📍 Exhibit Hall C,D,E #3604
🚀 Excited to share LinEAS, our new activation steering method accepted at NeurIPS 2025! It approximates optimal transport maps e2e to precisely guide 🧭 activations achieving finer control 🎚️ with ✨ less than 32 ✨ prompts!
💻github.com/apple/ml-lineas
📄arxiv.org/abs/2503.10679
Lorenzo Basile retweeted
Come find us at
NeurIPS Poster Session 6 #1114 4PM - 7PM
to hear how multimodal models develope localized image-text communication in their internal representations.
#NeurIPS2025
@alexserra1998 @francescortu @lorebasile @DiegoDoimo
Excited to present "The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models" at #NeurIPS2025 and #EurIPS2025!
📍NeurIPS: Poster Session 6 #1114 (Fri Dec 5 4pm-7pm)
📍EurIPS: Poster Session D3 #88 (Wed Dec 3 10:30am-12:30pm)
🧵👇
Lorenzo Basile retweeted
🤖Seminar Series
Next week, Giorgos Nikolaou and Tommaso Mencattini (@EPFL) will present "Language Models are Injective and Hence Invertible". @GiorgosNik02 @tommaso_mncttn
📅Nov 27, 11 CET (Online)
👉Register to attend: bit.ly/4ieKRYq
Lorenzo Basile retweeted
Excited to share that 2/2 papers from our Lab (LADE) were accepted to #NeurIPS2025 (one spotlight 🎉)
Great work from all the students and collaborators involved!
@AreaSciencePark @aleserra1998 @lorebasile @francescortu @lucrevaleriani @DiegoDoimo @ansuin @FrancescoLocat8
Lorenzo Basile retweeted
Thrilled to announce that our paper is accepted at #NeurIPS 2025!! See you in San Diego! 🇺🇸
Lorenzo Basile retweeted
I just landed in Vancouver to present @NeurIPSConf the findings of our new work!
Few-shot learning and fine-tuning change the hidden layers of LLMs in a dramatically different way, even when they perform equally well on multiple-choice question-answering tasks.
🧵1/6
Lorenzo Basile retweeted
✨ Meet #ResiDual, a novel perspective on the alignment of multimodal latent spaces!
Think of it as a spectral "panning for gold" along the residual stream. It improves text-image alignment by simply amplifying task-related directions! 🌌🔍
arxiv.org/abs/2411.00246
[1/6]
