← Back to all news
arXiv Machine Learning By Rapha\"el Bonnet-Guerrini, Johann Ioannou-Nikolaides, Inar Timiryasov, Vincenzo Piuri

Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders

Read the original on arXiv Machine Learning →

The paper applies sparse autoencoders to a neutrino foundation model trained on IceCube data, uncovering a validated atlas of physical concepts within the model’s internal representation. Causal analysis shows the direction reconstruction head largely ignores this atlas, whereas an uncertainty head trained on the same representation effectively uses quality and brightness features, improving angular resolution from 20.2° to 3.2° at 20% efficiency. These findings demonstrate that mechanistic interpretability can expose latent physics and guide the design of downstream tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

Hugging Face Trending Papers
Jun 10

Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics

Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This raises a central evaluation and interpretability question: when a foundation-style model can reproduce known continuum dynamics, what internal mechanism supports that behavior, is the internal behaviour consistent with known physics, and how does it relate to where the emulator succeeds or fails?

benchmarkssafety
More like this →
arXiv Machine Learning
Jun 5

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

arXiv:2603. 19312v3 Announce Type: replace Abstract: Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision to avoid representation collapse.

By Lucas Maes, Quentin Le Lidec, Damien Scieur, Yann LeCun, Randall Balestriero
ragdiffusion
More like this →