Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field. In this work we present RoboJEPA, a wo...
Artem Zholus, Nicolas Beltran-Velez, Jian-Hao Yuan et al.· 0 citations
Transformers and state-space models (SSMs) are the two dominant families of sequence models, and a central open question is how far the analytical knowledge built for transformers transfers to SSMs. We address this through the lens of layer importance which underpins compression, selective fine-tuning, and interpretabi...
Istabrak Abbes, Nizar Islah, Irina Rish et al.· 0 citations
Residue Embedding Diversity (RED), a metric for protein quality assessment orders of magnitude cheaper than likelihood, and a calibration task that measures model alignment with natural evolutionary distributions are introduced.
Lola Le Breton, David Heurtel-Depeiges, Douglas C. Millar et al.· bioRxiv· 1 citation
Motivation Antimicrobial resistance (AMR) has been identified as a top global public health threat. Accurate AMR phenotype prediction from whole-genome sequencing data is an essential tool for accelerating clinical decision-making and mitigating resistance spread. Although many previous works have explored the use of t...
Alex Aselstyne, E. Karthik, Meriem El Azami et al.· bioRxiv· 0 citations
A novel architecture incorporating an explicit private working memory is proposed and it is demonstrated that this mechanism restores consistency with a fixed hidden state, establishing private state as a necessary component for PSIT-capable language agents.
Davide Baldelli, Alipanah Parviz, A. Zouaq et al.· arXiv.org· 2 citations
This work uses encoders producing sparse latents in training Sparse Koopman Autoencoders without basin labels or other regime annotations to identify sparse latents and their corresponding supports as label-free, interpretable regime variables for Koopman learning in nonlinear systems with multiple local dynamical laws...