arXiv Machine Learning By Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit

From Performance to Viability: A Bootstrap Framework for Latent-Space Representation Learning in Adaptive Biological Systems

Read the original on arXiv Machine Learning →

arXiv:2606. 01374v1 Announce Type: new Abstract: Observable performance is commonly used to characterize biological systems.

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.

arXiv Machine Learning
Jul 14

From Performance to Representational Adequacy: A Representational Bootstrap Framework for Adaptive Biological Systems

arXiv:2606. 01374v3 Announce Type: replace Abstract: Observable performance is commonly used to characterize biological systems, yet aggregated outputs may remain insufficient for uniquely resolving observational conditions, and richer multivariate representations may retain substantial ambiguity.

By Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit
arXiv Machine Learning
Jul 14

From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint

arXiv:2605. 15862v2 Announce Type: replace Abstract: Understanding adaptive biomechanical systems requires distinguishing observable performance, static multivariate representation, longitudinal displacement, and internal approximation of observed change.

By Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit
arXiv Computation and Language
Sep 18

JEPA-Anything: Learning Predictive Models across Different Worlds

JEPA-Anything is a domain‑agnostic framework that uses orthogonal predictive factorization (OPF) to decompose latent targets into complementary factors, learn them via dedicated pathways, and recombine them for shared prediction. The method is evaluated across seven diverse domains—vision, biology, clinical trajectories, control, molecular dynamics, physical fields, and weather—showing improvements on 10 dynamics tasks, reduced error on Interventional Pong, and lowest one‑step and 100‑step molecular errors among compared methods. Experimental validation includes a factor‑nominated biological intervention that succeeded in cell co‑cultures, organoids, tumor fragments, and mice, and latent orbital modes that recover the Keplerian scaling exponent.

By Taoyong Cui, Zhongyao Wang, Xinyue Xu, Weiyang Liu, Zhaochen Yu, Yuying Zhang, Qiang Gao, Mengyue Yang, Wanli Ouyang, Pheng Ann Heng, Yingcheng Wu, Zhenfei Yin, Ling Yang