Simulating and controlling physical systems described by partial differential equations (PDEs) are crucial tasks across science and engineering. Recently, diffusion generative models have emerged as a competitive class of methods for these tasks due to their ability to capture long-term dependencies and model high-dimensional states. However, diffusion models typically struggle with handling system states with abrupt changes and generalizing to higher resolutions. In this work, we propose Wavelet Diffusion Neural Operator (WDNO), a novel PDE simulation and control framework that enhances the handling of these complexities. WDNO comprises two key innovations. Firstly, WDNO performs diffusion-based generative modeling in the wavelet domain for the entire trajectory to handle abrupt changes and long-term dependencies effectively. Secondly, to address the issue of poor generalization across different resolutions, which is one of the fundamental tasks in modeling physical systems, we introduce multi-resolution training. We validate WDNO on five physical systems, including 1D advection equation, three challenging physical systems with abrupt changes (1D Burgers' equation, 1D compressible Navier-Stokes equation and 2D incompressible fluid), and a real-world dataset ERA5, which demonstrates superior performance on both simulation and control tasks over state-of-the-art methods, with significant improvements in long-term and detail prediction accuracy. Remarkably, in the challenging context of the 2D high-dimensional and indirect control task aimed at reducing smoke leakage, WDNO reduces the leakage by 33.2% compared to the second-best baseline.

Despite the excellent real-world predictive performance of modern machine learning (ML) methods, many scientists remain hesitant to discard traditional physical-conceptual (PC) approaches due mainly to their relative interpretability, which contributes to credibility during decision-making. In this context, a currently underexplored aspect of ML is how to develop "minimally-optimal" representations that can facilitate better "insight regarding system functioning". Regardless of how this is achieved, it is arguably true that parsimonious representations better support the advancement of scientific understanding. Our own view is that ML-based modeling of geoscientific systems should be based in the use of computational units that are fundamentally interpretable by design. This paper continues our exploration of how the strengths of ML can be exploited in the service of better understanding via scientific investigation. Here, we use the Mass Conserving Perceptron (MCP) as the fundamental computational unit in a generic network architecture consisting of nodes arranged in series and parallel to explore several generic and important issues related to the use of observational data for constructing input-state-output models of dynamical systems. In the context of lumped catchment modeling, we show that physical interpretability and excellent predictive performance can both be achieved using a relatively parsimonious "distributed-state" multiple-flowpath network with context-dependent gating and "information sharing" across the nodes, suggesting that MCP-based modeling can play a significant role in application of ML to geoscientific investigation.

Often, these changes are driven by different environments or internal states in which the system operates, and we refer to context variables as those variables that indicate this change in causal mechanisms. An example are the causal relations in soil moisture-temperature interactions and their dependence on soil moisture regimes: Dry soil triggers a dependence of soil moisture on latent heat, while environments with wet soil do not feature such a feedback, making it a context-specific property. Crucially, a regime or context variable such as soil moisture need not be exogenous and can be influenced by the dynamical system variables - precipitation can make a dry soil wet - leading to joint systems with endogenous context variables. In this work we investigate the assumptions for constraint-based causal discovery of context-specific information in systems with endogenous context variables. We show that naive approaches such as learning different regime graphs on masked data, or pooling all data, can lead to uninformative results. We propose an adaptive constraint-based discovery algorithm and give a detailed discussion on the connection to structural causal models, including sufficiency assumptions, which allow to prove the soundness of our algorithm and to interpret the results causally. Numerical experiments demonstrate the performance of the proposed method over alternative baselines, but they also unveil current limitations of our method.

Big data is transforming scientific progress by enabling the discovery of novel models, enhancing existing frameworks, and facilitating precise uncertainty quantification, while advancements in scientific machine learning complement this by providing powerful tools to solve inverse problems to identify the complex systems where traditional methods falter due to sparse or noisy data. We introduce two innovative neural operator frameworks tailored for discovering hidden physics and identifying unknown system parameters from sparse measurements. The first framework integrates a popular neural operator, DeepONet, and a physics-informed neural network to capture the relationship between sparse data and the underlying physics, enabling the accurate discovery of a family of governing equations. The second framework focuses on system parameter identification, leveraging a DeepONet pre-trained on sparse sensor measurements to initialize a physics-constrained inverse model. Both frameworks excel in handling limited data and preserving physical consistency. Benchmarking on the Burgers' equation and reaction-diffusion system demonstrates state-of-the-art performance, achieving average $L_2$ errors of $\mathcal{O}(10^{-2})$ for hidden physics discovery and absolute errors of $\mathcal{O}(10^{-3})$ for parameter identification. These results underscore the frameworks' robustness, efficiency, and potential for solving complex scientific problems with minimal observational data.

One-shot Federated learning (FL) is a powerful technology facilitating collaborative training of machine learning models in a single round of communication. While its superiority lies in communication efficiency and privacy preservation compared to iterative FL, one-shot FL often compromises model performance. Prior research has primarily focused on employing data-free knowledge distillation to optimize data generators and ensemble models for better aggregating local knowledge into the server model. Prior research has primarily focused on employing datafree knowledge distillation to optimize data generators and ensemble models for better aggregating local knowledge into the server model. However, these methods typically struggle with data heterogeneity, where inconsistent local data distributions can cause teachers to provide misleading knowledge. Additionally, they may encounter scalability issues with complex datasets due to inherent twostep information loss: first, during local training (from data to model), and second, when transferring knowledge to the server model (from model to inversed data). In this paper, we propose FedSD2C, a novel and practical one-shot FL framework designed to address these challenges. FedSD2C introduces a distiller to synthesize informative distillates directly from local data to reduce information loss and proposes sharing synthetic distillates instead of inconsistent local models to tackle data heterogeneity. Our empirical results demonstrate that FedSD2C consistently outperforms other one-shot FL methods with more complex and real datasets, achieving up to 2.6 the performance of the best baseline.

Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were predominately repurposed from academic datasets such as VQA, AI2D, and ChartQA. These datasets target simplistic tasks, and only provide phrase-level answers without any intermediate rationales. To address these challenges, we introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales designed to elicit CoT reasoning. Using only open models, we create a dataset containing 12M instruction-response pairs to cover diverse, reasoning-intensive tasks with detailed and faithful rationales. Experiments demonstrate that training MLLMs on this dataset significantly improves reasoning capabilities, achieving state-of-the-art performance on benchmarks such as MathVerse (+8.1%), MMMU-Pro (+7%), and MuirBench (+13.3%). Additionally, the model demonstrates notable improvements of up to 4% on non-reasoning-based benchmarks. Ablation studies further highlight the importance of key components, such as rewriting and self-filtering, in the dataset construction process.

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based methods, and various other topics (including a very brief discussion of RL+LLMs).

Advancements in computational fluid mechanics have largely relied on Newtonian frameworks, particularly through the direct simulation of Navier-Stokes equations. In this work, we propose an alternative computational framework that employs variational methods, specifically by leveraging the principle of minimum pressure gradient, which turns the fluid mechanics problem into a minimization problem whose solution can be used to predict the flow field in unsteady incompressible viscous flows. This method exhibits two particulary intriguing properties. First, it circumvents the chronic issues of pressure-velocity coupling in incompressible flows, which often dominates the computational cost in computational fluid dynamics (CFD). Second, this method eliminates the reliance on unphysical assumptions at the outflow boundary, addressing another longstanding challenge in CFD. We apply this framework to three benchmark examples across a range of Reynolds numbers: (i) unsteady flow field in a lid-driven cavity, (ii) Poiseuille flow, and (iii) flow past a circular cylinder. The minimization framework is carried out using a physics-informed neural network (PINN), which integrates the underlying physical principles directly into the training of the model. The results from the proposed method are validated against high-fidelity CFD simulations, showing an excellent agreement. Comparison of the proposed variational method to the conventional method, wherein PINNs is directly applied to solve Navier-Stokes Equations, reveals that the proposed method outperforms conventional PINNs in terms of both convergence rate and time, demonstrating its potential for solving complex fluid mechanics problems.

Crystal plasticity (CP) modeling is a vital tool for predicting the mechanical behavior of materials, but its calibration involves numerous (>8) constitutive parameters, often requiring time-consuming trial-and-error methods. This paper proposes a robust calibration approach using Bayesian optimization (BO) to identify optimal CP model parameters under fatigue loading conditions. Utilizing cyclic data from additively manufactured Hastelloy X specimens at 500 degree-F, the BO framework, integrated with a Gaussian process surrogate model, significantly reduces the number of required simulations. A novel objective function is developed to match experimental stress-strain data across different strain amplitudes. Results demonstrate that effective CP model calibration is achieved within 75 iterations, with as few as 50 initial simulations. Sensitivity analysis reveals the influence of CP parameters at various loading points on the stress-strain curve. The results show that the stress-strain response is predominantly controlled by parameters related to yield, with increased influence from backstress parameters during compressive loading. In addition, the effect of introducing twins into the synthetic microstructure on fatigue behavior is studied, and a relationship between microstructural features and the fatigue indicator parameter is established. Results show that larger diameter grains, which exhibit a higher Schmid factor and an average misorientation of approximately 42 degrees +/- 1.67 degree, are identified as probable sites for failure. The proposed optimization framework can be applied to any material system or CP model, streamlining the calibration process and improving the predictive accuracy of such models.

Unsupervised pretraining has been transformative in many supervised domains. However, applying such ideas to reinforcement learning (RL) presents a unique challenge in that fine-tuning does not involve mimicking task-specific data, but rather exploring and locating the solution through iterative self-improvement. In this work, we study how unlabeled prior trajectory data can be leveraged to learn efficient exploration strategies. While prior data can be used to pretrain a set of low-level skills, or as additional off-policy data for online RL, it has been unclear how to combine these ideas effectively for online exploration. Our method SUPE (Skills from Unlabeled Prior data for Exploration) demonstrates that a careful combination of these ideas compounds their benefits. Our method first extracts low-level skills using a variational autoencoder (VAE), and then pseudo-relabels unlabeled trajectories using an optimistic reward model, transforming prior data into high-level, task-relevant examples. Finally, SUPE uses these transformed examples as additional off-policy data for online RL to learn a high-level policy that composes pretrained low-level skills to explore efficiently. We empirically show that SUPE reliably outperforms prior strategies, successfully solving a suite of long-horizon, sparse-reward tasks. Code: https://github.com/rail-berkeley/supe.