Diffusion models, as a type of generative models, have achieved impressive results in generating images and videos conditioned on textual conditions. However, the generation process of diffusion models involves denoising for dozens of steps to produce photorealistic images/videos, which is computationally expensive. Unlike previous methods that design ``one-size-fits-all'' approaches for speed up, we argue denoising steps should be sample-specific conditioned on the richness of input texts. To this end, we introduce AdaDiff, a lightweight framework designed to learn instance-specific step usage policies, which are then used by the diffusion model for generation. AdaDiff is optimized using a policy gradient method to maximize a carefully designed reward function, balancing inference time and generation quality. We conduct experiments on three image generation and two video generation benchmarks and demonstrate that our approach achieves similar results in terms of visual quality compared to the baseline using a fixed 50 denoising steps while reducing inference time by at least 33%, going as high as 40%. Furthermore, our qualitative analysis shows that our method allocates more steps to more informative text conditions and fewer steps to simpler text conditions.

In this research, we developed a graph-based framework to represent various aspects of optimal thermal management system design, with the aim of rapidly and efficiently identifying optimal design candidates. Initially, the graph-based framework is utilized to generate diverse thermal management system architectures. The dynamics of these system architectures are modeled under various loading conditions, and an open-loop optimal controller is employed to determine each system's optimal performance. These modeled cases constitute the dataset, with the corresponding optimal performance values serving as the labels for the data. In the subsequent step, a Graph Neural Network (GNN) model is trained on 30% of the labeled data to predict the systems' performance, effectively addressing a regression problem. Utilizing this trained model, we estimate the performance values for the remaining 70% of the data, which serves as the test set. In the third step, the predicted performance values are employed to rank the test data, facilitating prioritized evaluation of the design scenarios. Specifically, a small subset of the test data with the highest estimated ranks undergoes evaluation via the open-loop optimal control solver. This targeted approach concentrates on evaluating higher-ranked designs identified by the GNN, replacing the exhaustive search (enumeration-based) of all design cases. The results demonstrate a significant average reduction of over 92% in the number of system dynamic modeling and optimal control analyses required to identify optimal design scenarios.

Conjugate heat transfer (CHT) models are vital for the design of many engineering systems. However, high-fidelity CHT models are computationally intensive, which limits their use in applications such as design optimization, where hundreds to thousands of model evaluations are required. In this work, we develop a modular deep convolutional encoder-decoder hierarchical (DeepEDH) neural network, a novel deep-learning-based surrogate modeling methodology for computationally intensive CHT models. Leveraging convective temperature dependencies, we propose a two-stage temperature prediction architecture that couples velocity and temperature models. The proposed DeepEDH methodology is demonstrated by modeling the pressure, velocity, and temperature fields for a liquid-cooled cold-plate-based battery thermal management system with variable channel geometry. A computational model of the cold plate is developed and solved using the finite element method (FEM), generating a dataset of 1,500 simulations. The FEM results are transformed and scaled from unstructured to structured, image-like meshes to create training and test datasets. The DeepEDH methodology's performance is examined in relation to data scaling, training dataset size, and network depth. Our performance analysis covers the impact of the novel architecture, separate field models, output geometry masks, multi-stage temperature models, and optimizations of the hyperparameters and architecture. Furthermore, we quantify the influence of the CHT thermal boundary condition on surrogate model performance, highlighting improved temperature model performance with higher heat fluxes. Compared to other deep learning neural network surrogate models, such as U-Net and DenseED, the proposed DeepEDH methodology for CHT models exhibits up to a 65% enhancement in the coefficient of determination ($R^{2}$).

Variational autoencoders (VAEs) are popular models for representation learning but their encoders are susceptible to overfitting (Cremer et al., 2018) because they are trained on a finite training set instead of the true (continuous) data distribution $p_{\mathrm{data}}(\mathbf{x})$. Diffusion models, on the other hand, avoid this issue by keeping the encoder fixed. This makes their representations less interpretable, but it simplifies training, enabling accurate and continuous approximations of $p_{\mathrm{data}}(\mathbf{x})$. In this paper, we show that overfitting encoders in VAEs can be effectively mitigated by training on samples from a pre-trained diffusion model. These results are somewhat unexpected as recent findings (Alemohammad et al., 2023; Shumailov et al., 2023) observe a decay in generative performance when models are trained on data generated by another generative model. We analyze generalization performance, amortization gap, and robustness of VAEs trained with our proposed method on three different data sets. We find improvements in all metrics compared to both normal training and conventional data augmentation methods, and we show that a modest amount of samples from the diffusion model suffices to obtain these gains.

We propose an approach to do learning in Gaussian factor graphs. We treat all relevant quantities (inputs, outputs, parameters, latents) as random variables in a graphical model, and view both training and prediction as inference problems with different observed nodes. Our experiments show that these problems can be efficiently solved with belief propagation (BP), whose updates are inherently local, presenting exciting opportunities for distributed and asynchronous training. Our approach can be scaled to deep networks and provides a natural means to do continual learning: use the BP-estimated parameter marginals of the current task as parameter priors for the next. On a video denoising task we demonstrate the benefit of learnable parameters over a classical factor graph approach and we show encouraging performance of deep factor graphs for continual image classification on MNIST.

A smart grid includes a broad range of sophisticated sensors that constantly assess the state of the grid and the electrical power demand and availability, with the aim of optimizing the energy supply. In the future, the power grid will evolve into a cyber-physical system where smart devices will allow advanced monitoring and control. In this context, along with the smart home, consumers play more active roles in the management of energy consumption, and Home Energy Management Systems (HEMSs) emerge as hardware and software technology to monitor and to provide feedback on energy consumption at home and, so, to support effective habits from the point of view of energy saving. HEMSs are a growing sector in the modern era of the smart grid and smart homes. Specifically, in Colombia, people have become increasingly dependent on energy, so that consumption is increasing year after year. Considering that the end user generates a notable amount of total energy consumption, and that the residential sector makes a considerable contribution, the DPN of the Colombian government (National Planning Department; by its acronym in Spanish) has included this sector in the energy efficiency goals in the country, for which reason HEMS technologies have been considered energy efficiency applications [1]. Those HEMSs have emerged as a solution that allows the residential sector to manage the energy consumption more efficiently. However, according to [2], energy management technologies for residential users have not yet been introduced in Colombia; [3] suggests that economic drawbacks are the main barrier to HEMS adoption.

In fields like energy storage materials or medicinal chemistry, substances are key to technological advancement and progress: the success of these applications hinges on the specific properties of the materials. However, the processes of discovery and development of new materials often face practical and/or principal obstacles, such as unavailability of compounds or precursors, high production costs, and the need for extensive trials on the practical side, or limited data and/or experience, as well as biased expectations of designers and developers on the other hand. Generative models, a powerful category in machine learning, have the potential to address both of these issues simultaneously, as they can help focus our efforts a priori only on the most likely candidates. Many architectures related to creation of novel data points were developed in recent years, most notably Recurrent Neural Networks (RNN) [1], Generative Adversarial Networks (GAN) [2], Variational Autoencoders (VAE) [3] and Transformers [4]. The transformer architecture, especially, has revolutionized the fields of Natural Language Processing (NLP) [5] and other domains like computer vision [6]. The introduction of the General Pretrained Transformer (GPT) architecture led to significant advancements in generative natural language applications. Generative models have also been applied in the fields of medicine and material science to create new molecules with predefined features, a process known as conditional generation [7, 8]. This application can significantly accelerate the discovery of new candidate molecules. Although current generative models may not provide the optimal solution, they can greatly reduce the size of the chemical space that needs to be evaluated.

Artificial Intelligence (AI) is one of the most transformative technologies of the 21st century. The extent and scope of future AI capabilities remain a key uncertainty, with widespread disagreement on timelines and potential impacts. As nations and technology companies race toward greater complexity and autonomy in AI systems, there are concerns over the extent of integration and oversight of opaque AI decision processes. This is especially true in the subfield of machine learning (ML), where systems learn to optimize objectives without human assistance. Objectives can be imperfectly specified or executed in an unexpected or potentially harmful way. This becomes more concerning as systems increase in power and autonomy, where an abrupt capability jump could result in unexpected shifts in power dynamics or even catastrophic failures. This study presents a hierarchical complex systems framework to model AI risk and provide a template for alternative futures analysis. Survey data were collected from domain experts in the public and private sectors to classify AI impact and likelihood. The results show increased uncertainty over the powerful AI agent scenario, confidence in multiagent environments, and increased concern over AI alignment failures and influence-seeking behavior.

Recent advancements in Large Vision-Language Models (VLMs) have shown great promise in natural image domains, allowing users to hold a dialogue about given visual content. However, such general-domain VLMs perform poorly for Remote Sensing (RS) scenarios, leading to inaccurate or fabricated information when presented with RS domain-specific queries. Such a behavior emerges due to the unique challenges introduced by RS imagery. For example, to handle high-resolution RS imagery with diverse scale changes across categories and many small objects, region-level reasoning is necessary alongside holistic scene interpretation. Furthermore, the lack of domain-specific multimodal instruction following data as well as strong backbone models for RS make it hard for the models to align their behavior with user queries. To address these limitations, we propose GeoChat - the first versatile remote sensing VLM that offers multitask conversational capabilities with high-resolution RS images. Specifically, GeoChat can not only answer image-level queries but also accepts region inputs to hold region-specific dialogue. Furthermore, it can visually ground objects in its responses by referring to their spatial coordinates. To address the lack of domain-specific datasets, we generate a novel RS multimodal instruction-following dataset by extending image-text pairs from existing diverse RS datasets. We establish a comprehensive benchmark for RS multitask conversations and compare with a number of baseline methods. GeoChat demonstrates robust zero-shot performance on various RS tasks, e.g., image and region captioning, visual question answering, scene classification, visually grounded conversations and referring detection. Our code is available at https://github.com/mbzuai-oryx/geochat.

This document describes an approach used in the Multi-Machine Disruption Prediction Challenge for Fusion Energy by ITU, a data science competition which ran from September to November 2023, on the online platform Zindi. The competition involved data from three fusion devices - C-Mod, HL-2A, and J-TEXT - with most of the training data coming from the last two, and the test data coming from the first one. Each device has multiple diagnostics and signals, and it turns out that a critical issue in this competition was to identify which signals, and especially which features from those signals, were most relevant to achieve accurate predictions. The approach described here is based on extracting features from signals, and then applying logistic regression on top of those features. Each signal is treated as a separate predictor and, in the end, a combination of such predictors achieved the first place on the leaderboard.