Recent developments in 3D vision have enabled significant progress in inferring neural fluid fields and realistic rendering of fluid dynamics. However, these methods require dense captures of real-world flow, which demand specialized lab setups, making the process costly and challenging. Scientific machine learning (SciML) foundation models, pretrained on extensive simulations of partial differential equations (PDEs), encode rich multiphysics knowledge and thus provide promising sources of domain priors for inferring fluid fields. Nevertheless, the transferability of these foundation models to real-world vision problems remains largely underexplored. In this work, we demonstrate that SciML foundation models can significantly reduce the data costs of inferring real-world 3D fluid dynamics with improved generalization. Our method leverages strong forecasting capabilities and meaningful representations of SciML foundation models. We equip neural fluid fields with a novel collaborative training that utilizes augmented frames, and fluid features extracted by our foundation model. We demonstrate significant advancements in both quantitative metrics and visual quality over previous methods, improving 9∼36% peak signal-to-noise ratio (PSNR) in future prediction with$25 \sim 50 \%$reduction in the number of training frames, thereby showcasing the practical applicability of SciML foundation models in real-world fluid dynamics. We release our code at: https://github.com/delta-lab-ai/SciML-HY.

We present PDE-Controller, a framework that enables large language models (LLMs) to control systems governed by partial differential equations (PDEs). Traditional LLMs have excelled in commonsense reasoning but fall short in rigorous logical reasoning. While recent AI-for-math has made strides in pure mathematics, areas of applied mathematics, particularly PDEs, remain underexplored despite their significant real-world applications. Our approach enables LLMs to transform informal natural language instructions into formal specifications, and then execute reasoning and planning steps to improve the utility of PDE control. We build a holistic solution comprising datasets (both human-written cases and 2 million synthetic samples), math-reasoning models, and novel evaluation metrics, all of which require significant effort. Our PDE-Controller significantly outperforms the latest open-source and GPT models in reasoning, autoformalization, and program synthesis, achieving up to a 62% improvement in utility gain for PDE control. By bridging the gap between language generation and PDE systems, we demonstrate the potential of LLMs in addressing complex scientific and engineering challenges. We promise to release all data, model checkpoints, and code upon acceptance.

We present PANORAMIA, a privacy leakage measurement framework for machine learning models that relies on membership inference attacks using generated data as non-members. By relying on generated non-member data, PANORAMIA eliminates the common dependency of privacy measurement tools on in-distribution non-member data. As a result, PANORAMIA does not modify the model, training data, or training process, and only requires access to a subset of the training data. We evaluate PANORAMIA on ML models for image and tabular data classification, as well as on large-scale language models.