Multimodal foundation models serve numerous applications at the intersection of vision and language. Still, despite being pretrained on extensive data, they become outdated over time. To keep models updated, research into continual pretraining mainly explores scenarios with either (1) infrequent, indiscriminate updates on large-scale new data, or (2) frequent, sample-level updates. However, practical model deployment often operates in the gap between these two limit cases, as real-world applications often demand adaptation to specific subdomains, tasks or concepts -- spread over the entire, varying life cycle of a model. In this work, we complement current perspectives on continual pretraining through a research test bed as well as provide comprehensive guidance for effective continual model updates in such scenarios. We first introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements, constructed over 63 datasets with diverse visual and semantic coverage. Using FoMo-in-Flux, we explore the complex landscape of practical continual pretraining through multiple perspectives: (1) A data-centric investigation of data mixtures and stream orderings that emulate real-world deployment situations, (2) a method-centric investigation ranging from simple fine-tuning and traditional continual learning strategies to parameter-efficient updates and model merging, (3) meta learning rate schedules and mechanistic design choices, and (4) the influence of model and compute scaling. Together, our insights provide a practitioner's guide to continual multimodal pretraining for real-world deployment. Our benchmark and code is here: https://github.com/ExplainableML/fomo_in_flux.

Abundant, well-annotated multimodal data in remote sensing are pivotal for aligning complex visual remote sensing (RS) scenes with human language, enabling the development of specialized vision language models across diverse RS interpretation tasks. However, annotating RS images with rich linguistic semantics at scale demands expertise in RS and substantial human labor, making it costly and often impractical. In this study, we propose a workflow that leverages large language models (LLMs) to generate multimodal datasets with semantically rich captions at scale from plain OpenStreetMap (OSM) data for images sourced from the Google Earth Engine (GEE) platform. This approach facilitates the generation of paired remote sensing data and can be readily scaled up using openly available data. Within this framework, we present RSTeller, a multimodal dataset comprising over 1 million RS images, each accompanied by multiple descriptive captions. Extensive experiments demonstrate that RSTeller enhances the performance of multiple existing vision language models for RS scene understanding through continual pre-training. Our methodology significantly reduces the manual effort and expertise needed for annotating remote sensing imagery while democratizing access to high-quality annotated data. This advancement fosters progress in visual language modeling and encourages broader participation in remote sensing research and applications. The RSTeller dataset is available at https://github.com/SlytherinGe/RSTeller.

Diverse Wi-Fi-based wireless applications have been proposed, ranging from daily activity recognition to vital sign monitoring. Despite their remarkable sensing accuracy, the high energy consumption and the requirement for customized hardware modification hinder the wide deployment of the existing sensing solutions. In this paper, we propose REHSense, an energy-efficient wireless sensing solution based on Radio-Frequency (RF) energy harvesting. Instead of relying on a power-hungry Wi-Fi receiver, REHSense leverages an RF energy harvester as the sensor and utilizes the voltage signals harvested from the ambient Wi-Fi signals to enable simultaneous context sensing and energy harvesting. We design and implement REHSense using a commercial-off-the-shelf (COTS) RF energy harvester. Extensive evaluation of three fine-grained wireless sensing tasks (i.e., respiration monitoring, human activity, and hand gesture recognition) shows that REHSense can achieve comparable sensing accuracy with conventional Wi-Fi-based solutions while adapting to different sensing environments, reducing the power consumption by 98.7% and harvesting up to 4.5mW of power from RF energy.

Annotation of political discourse is resource-intensive, but recent developments in NLP promise to automate complex annotation tasks. Fine-tuned transformer-based models outperform human annotators in some annotation tasks, but they require large manually annotated training datasets. In our contribution, we explore to which degree a manually annotated dataset can be automatically replicated with today's NLP methods, using unsupervised machine learning and zero- and few-shot learning.

In quantitative finance, machine learning methods are essential for alpha generation. This study introduces a new approach that combines Hidden Markov Models (HMM) and neural networks, integrated with Black-Litterman portfolio optimization. During the COVID period (2019-2022), this dual-model approach achieved a 83% return with a Sharpe ratio of 0.77. It incorporates two risk models to enhance risk management, showing efficiency during volatile periods. The methodology was implemented on the QuantConnect platform, which was chosen for its robust framework and experimental reproducibility. The system, which predicts future price movements, includes a three-year warm-up to ensure proper algorithm function. It targets highly liquid, large-cap energy stocks to ensure stable and predictable performance while also considering broker payments. The dual-model alpha system utilizes log returns to select the optimal state based on the historical performance. It combines state predictions with neural network outputs, which are based on historical data, to generate trading signals. This study examined the architecture of the trading system, data pre-processing, training, and performance. The full code and backtesting data are available under the QuantConnect terms.

Designing synthetically accessible molecules and recommending analogs to unsynthesizable molecules are important problems for accelerating molecular discovery. We reconceptualize both problems using ideas from program synthesis. Drawing inspiration from syntax-guided synthesis approaches, we decouple the syntactic skeleton from the semantics of a synthetic tree to create a bilevel framework for reasoning about the combinatorial space of synthesis pathways. Given a molecule we aim to generate analogs for, we iteratively refine its skeletal characteristics via Markov Chain Monte Carlo simulations over the space of syntactic skeletons. Given a black-box oracle to optimize, we formulate a joint design space over syntactic templates and molecular descriptors and introduce evolutionary algorithms that optimize both syntactic and semantic dimensions synergistically. Our key insight is that once the syntactic skeleton is set, we can amortize over the search complexity of deriving the program's semantics by training policies to fully utilize the fixed horizon Markov Decision Process imposed by the syntactic template. We demonstrate performance advantages of our bilevel framework for synthesizable analog generation and synthesizable molecule design. Notably, our approach offers the user explicit control over the resources required to perform synthesis and biases the design space towards simpler solutions, making it particularly promising for autonomous synthesis platforms.

The deployment of Deep Neural Networks in energy-constrained environments, such as Energy Harvesting Wireless Sensor Networks, presents unique challenges, primarily due to the intermittent nature of power availability. To address these challenges, this study introduces and evaluates a novel training methodology tailored for DNNs operating within such contexts. In particular, we propose a dynamic dropout technique that adapts to both the architecture of the device and the variability in energy availability inherent in energy harvesting scenarios. Our proposed approach leverages a device model that incorporates specific parameters of the network architecture and the energy harvesting profile to optimize dropout rates dynamically during the training phase. By modulating the network's training process based on predicted energy availability, our method not only conserves energy but also ensures sustained learning and inference capabilities under power constraints. Our preliminary results demonstrate that this strategy provides 6 to 22 percent accuracy improvements compared to the state of the art with less than 5 percent additional compute. This paper details the development of the device model, describes the integration of energy profiles with intermittency aware dropout and quantization algorithms, and presents a comprehensive evaluation of the proposed approach using real-world energy harvesting data.

Characterizing materials using electron micrographs is crucial in areas such as semiconductors and quantum materials. Traditional classification methods falter due to the intricatestructures of these micrographs. This study introduces an innovative architecture that leverages the generative capabilities of zero-shot prompting in Large Language Models (LLMs) such as GPT-4(language only), the predictive ability of few-shot (in-context) learning in Large Multimodal Models (LMMs) such as GPT-4(V)ision, and fuses knowledge across image based and linguistic insights for accurate nanomaterial category prediction. This comprehensive approach aims to provide a robust solution for the automated nanomaterial identification task in semiconductor manufacturing, blending performance, efficiency, and interpretability. Our method surpasses conventional approaches, offering precise nanomaterial identification and facilitating high-throughput screening.

Characterizing materials with electron micrographs is a crucial task in fields such as semiconductors and quantum materials. The complex hierarchical structure of micrographs often poses challenges for traditional classification methods. In this study, we propose an innovative backbone architecture for analyzing electron micrographs. We create multi-modal representations of the micrographs by tokenizing them into patch sequences and, additionally, representing them as vision graphs, commonly referred to as patch attributed graphs. We introduce the Hierarchical Network Fusion (HNF), a multi-layered network structure architecture that facilitates information exchange between the multi-modal representations and knowledge integration across different patch resolutions. Furthermore, we leverage large language models (LLMs) to generate detailed technical descriptions of nanomaterials as auxiliary information to assist in the downstream task. We utilize a cross-modal attention mechanism for knowledge fusion across cross-domain representations(both image-based and linguistic insights) to predict the nanomaterial category. This multi-faceted approach promises a more comprehensive and accurate representation and classification of micrographs for nanomaterial identification. Our framework outperforms traditional methods, overcoming challenges posed by distributional shifts, and facilitating high-throughput screening.

Spatio-temporal time series forecasting plays a critical role in various real-world applications, such as transportation optimization, energy management, and climate analysis. The recent advancements in Pre-trained Language Models (PLMs) have inspired efforts to reprogram these models for time series forecasting tasks, by leveraging their superior reasoning and generalization capabilities. However, existing approaches fall short in handling complex spatial inter-series dependencies and intrinsic intra-series frequency components, limiting their spatio-temporal forecasting performance. Moreover, the linear mapping of continuous time series to a compressed subset vocabulary in reprogramming constrains the spatio-temporal semantic expressivity of PLMs and may lead to potential information bottleneck. To overcome the above limitations, we propose \textsc{RePST}, a tailored PLM reprogramming framework for spatio-temporal forecasting. The key insight of \textsc{RePST} is to decouple the spatio-temporal dynamics in the frequency domain, allowing better alignment with the PLM text space. Specifically, we first decouple spatio-temporal data in Fourier space and devise a structural diffusion operator to obtain temporal intrinsic and spatial diffusion signals, making the dynamics more comprehensible and predictable for PLMs. To avoid information bottleneck from a limited vocabulary, we further propose a discrete reprogramming strategy that selects relevant discrete textual information from an expanded vocabulary space in a differentiable manner. Extensive experiments on four real-world datasets show that our proposed approach significantly outperforms state-of-the-art spatio-temporal forecasting models, particularly in data-scarce scenarios.