arXiv:2606. 11657v1 Announce Type: cross Abstract: Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition.
By Katherine Rosenfeld, Maike Sonnewald
arXiv:2508. 12448v2 Announce Type: replace-cross Abstract: In-context learning (ICL) lets large language models (LLMs) solve new tasks from prompts alone, across an ever-widening range of domains, yet the mechanisms underlying this ability remain poorly understood.
By Yeongwoo Song, Jaeyong Bae, Dong-Kyum Kim, Hawoong Jeong
The paper investigates why latent neural surrogate solvers, which compress physical system dynamics into a lower‑dimensional space, often fail during long‑horizon autoregressive rollouts. It demonstrates that training the latent representation only for reconstruction leads to instability, and proposes a set of training interventions—Koopman operator learning, Hamming noise injection, and multi‑step rollout fine‑tuning—that align the latent space with long‑horizon forecasting. These interventions reduce long‑rollout error by about 40 % and achieve accuracy comparable to full‑resolution models while using far fewer floating‑point operations and GPU memory, enabling stable extrapolation in mesoscale crystal‑plasticity simulations of high‑cycle fatigue.
By Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek, Benjamin A. Jasperson, Vivek Oommen, David L. Damm, Krishna Garikipati, Remi Dingreville
arXiv:2606. 14990v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK.
By Naiyu Yin, Yue Yu
ChannelFlow-Tools is an open‑source, configuration‑driven pipeline that generates machine‑learning‑ready datasets for three‑dimensional obstructed channel flows. It combines procedural obstacle geometry generation across six shape families, signed‑distance‑field voxelisation, lattice‑Boltzmann simulation, and packaging into ML‑ready tensors, all driven by reproducible configuration files. The pipeline is validated through mesh‑integrity audits, SDF representation checks, solver benchmarks, and data‑integrity audits, and it has been used to train surrogate models (3D U‑Net, FNO, U‑FNO) that learn geometry‑to‑flow mappings and exhibit physically interpretable behaviour on out‑of‑distribution splits.
By Shubham Kavane, Lukas Schr\"oder, Kajol Kulkarni, Fernando Gonzalez, Harald Koestler
arXiv:2605. 29283v2 Announce Type: replace-cross Abstract: Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution.
By Mengdi Chu, Yang Liu, Ayan Biswas, Han-Wei Shen