Molecular generation conditioned on textual descriptions is a fundamental task in computational chemistry and drug discovery. Existing methods often struggle to simultaneously ensure high-quality, diverse generation and fast inference. In this work, we propose a novel causality-aware framework that addresses these challenges through two key innovations. First, we introduce a Causality-Aware Transformer (CAT) that jointly encodes molecular graph tokens and text instructions while enforcing causal dependencies during generation. Second, we develop a Variational Mean Flow (VMF) framework that generalizes existing flow-based methods by modeling the latent space as a mixture of Gaussians, enhancing expressiveness beyond unimodal priors. VMF enables efficient one-step inference while maintaining strong generation quality and diversity. Extensive experiments on four standard molecular benchmarks demonstrate that our model outperforms state-of-the-art baselines, achieving higher novelty (up to 74.5\%), diversity (up to 70.3\%), and 100\% validity across all datasets. Moreover, VMF requires only one number of function evaluation (NFE) during conditional generation and up to five NFEs for unconditional generation, offering substantial computational efficiency over diffusion-based methods.

This study presents a novel hybrid approach that combines Graph Neural Networks (GNNs) with Reynolds-Averaged Navier Stokes (RANS) equations to enhance the accuracy of mean flow reconstruction across a range of fluid dynamics applications. Traditional purely data-driven Neural Networks (NNs) models, often struggle maintaining physical consistency. Moreover, they typically require large datasets to achieve reliable performances. The GNN framework, which naturally handles unstructured data such as complex geometries in Computational Fluid Dynamics (CFD), is here integrated with RANS equations as a physical baseline model. The methodology leverages the adjoint method, enabling the use of RANS-derived gradients as optimization terms in the GNN training process. This ensures that the learned model adheres to the governing physics, maintaining physical consistency while improving the prediction accuracy. We test our approach on multiple CFD scenarios, including cases involving generalization with respect to the Reynolds number, sparse measurements, denoising and inpainting of missing portions of the mean flow. The results demonstrate significant improvements in the accuracy of the reconstructed mean flow compared to purely data-driven models, using limited amounts of data in the training dataset. The key strengths of this study are the integration of physical laws into the training process of the GNN, and the ability to achieve high-accuracy predictions with a limited amount of data, making this approach particularly valuable for applications in fluid dynamics where data is often scarce.

Q-learning has become an important part of the reinforcement learning toolkit since its introduction in the dissertation of Chris Watkins in the 1980s. The purpose of this paper is in part a tutorial on stochastic approximation and Q-learning, providing details regarding the INFORMS APS inaugural Applied Probability Trust Plenary Lecture, presented in Nancy France, June 2023. The paper also presents new approaches to ensure stability and potentially accelerated convergence for these algorithms, and stochastic approximation in other settings. Two contributions are entirely new: 1. Stability of Q-learning with linear function approximation has been an open topic for research for over three decades. It is shown that with appropriate optimistic training in the form of a modified Gibbs policy, there exists a solution to the projected Bellman equation, and the algorithm is stable (in terms of bounded parameter estimates). Convergence remains one of many open topics for research. 2. The new Zap Zero algorithm is designed to approximate the Newton-Raphson flow without matrix inversion. It is stable and convergent under mild assumptions on the mean flow vector field for the algorithm, and compatible statistical assumption on an underlying Markov chain. The algorithm is a general approach to stochastic approximation which in particular applies to Q-learning with "oblivious" training even with non-linear function approximation.