The study introduces RegimeShift‑Surrogates, a streaming benchmark that tests surrogate models across eight tasks and multiple regimes. It compares revalidation—choosing the model with lowest current‑window validation loss—to stateful adaptive controllers and finds that revalidation consistently outperforms stateful methods, achieving lower mean log regret in most task‑scenario combinations. The results suggest that fresh validation evidence is more valuable than carrying over past evidence when dealing with distribution shifts.
By Harshil Lodhiya
arXiv:2607. 23667v1 Announce Type: cross Abstract: A flow surrogate validated on a simple regime is often taken as evidence that the approach will carry to a richer one.
By Georg Winkler, Martin Stoll
arXiv:2603. 17057v2 Announce Type: replace-cross Abstract: Active multi-fidelity surrogate modeling is developed for multi-condition airfoil shape optimization to reduce high-fidelity CFD cost while retaining RANS-consistent aerodynamic metrics.
By Isaac Robledo, Alberto Vilari\~no, Arnau Mir\'o, Oriol Lehmkuhl, Carlos Sanmiguel Vila, Rodrigo Castellanos
arXiv:2606. 06827v1 Announce Type: new Abstract: Transfer in coordinate networks is often measured by warm-start gain, but whether that gain reflects source-specific structure or generic weight reuse is less clear.
By D Yang Eng
The paper introduces a correction framework that grounds a CFD-trained deep learning surrogate model for aerospace aerodynamics using wind‑tunnel pressure‑sensor (PSP) data. By training a correction network on spatially registered PSP measurements at two Mach numbers, the authors adjust the surrogate’s predictions without retraining its core parameters, achieving improved agreement with experimental pressure distributions—especially at the wing suction peak and shock location. The grounded surrogate matches measurements within 2.3–2.7% of the Cp range on unseen angles of attack and outperforms simple interpolation between measured states.
By Nitin Nagesh Kulkarni, Dheeraj Vemula, Yin Yu, Peter Lyu, Juan J. Alonso
The paper investigates why the train‑validation performance gap widens during fine‑tuning of pretrained models. It proposes a dynamic structural explanation: as training proceeds, updates shift from broadly reusable features to more example‑specific ones, increasing gradient heterogeneity and the gap. Experiments on synthetic ResMLP hierarchies, NLP models (RoBERTa, DeBERTa, Qwen) across six datasets, and vision models (ResNet‑18) confirm that higher reliance on private features correlates with larger accuracy gaps, supporting the proposed account.
By Yuchen Li, Mingyu Du, Zongqi Fan, Ken-Tye Yong, Nguyen H. Tran
arXiv:2609.38638v1 Announce Type: cross
Abstract: Pickup trucks account for 14% of new light-duty vehicles produced in the United States, yet are among the least aerodynamic. Their open cargo bed add...
By Riddhiman Raut, Yin Yu, Aashwin Anand Mishra, Michael Emory, Thomas Economon, Peter Lyu, Juan J. Alonso
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
By Yuyang Shen
The paper introduces a schema‑adaptive action‑conditioned Joint‑Embedding Predictive Architecture (SAAC‑JEPA) for cross‑machine CNC transfer when only a subset of sensors overlap between source and target machines. Experiments show that pretraining does not improve source‑only forecasting, but a carefully selected action‑conditioned JEPA model achieves a zero‑shot RMSE of 0.546 on the target, outperforming persistence but falling short of certain baseline models. Ablation studies reveal that adding RevIN improves RMSE but harms calibration, and limited post‑lock adaptation can further reduce error.
By Ayoub Louaye Bouaziz, Matthieu Ostertag, Anton Demasles
The study measured the impact of a single training example on a GPT‑2 model by running 24 counterfactual experiments. 32 models were trained from scratch on OpenWebText, and at a specific training step a single batch row was replaced with a 194‑token passage under three conditions (fluent prose, fabricated subject, random characters) or left unchanged. Results showed that the passage was learned from one exposure and decayed, with measurable differences in cross‑entropy up to 50 steps after injection but no lasting effect at the final step.
By Zachary Speck, Asa Shepard
The study investigates whether a curated same-family neural network experiment can guide large language model (LLM)-based improvements for a low-performing target model under equal generation and evaluation budgets. Using TuneNNGen, an extension of NNGPT, the authors compare source-guided generation with target-only generation on CIFAR-10, SVHN, Imagenette, and CIFAR-100 datasets, achieving significant accuracy gains across these benchmarks. The results demonstrate that the benefits depend on source-target compatibility and LLM adaptation, rather than merely on stored source accuracy.
By Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov
arXiv:2606. 27354v1 Announce Type: cross Abstract: Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical task: once trained, they struggle to correct their own constraint violations and extrapolate beyond the training distribution.
By Haina Jiang, Liam Wang, Peng-Chen Chen, Min Seop Kwak, Seungryong Kim, Brian Bell, Jeong Joon Park