Language is constantly changing and evolving, leaving language models to become quickly outdated. Consequently, we should continuously update our models with new data to expose them to new events and facts. However, that requires additional computing, which means new carbon emissions. Do any measurable benefits justify this cost? This paper looks for empirical evidence to support continuous training. We reproduce existing benchmarks and extend them to include additional time periods, models, and tasks. Our results show that the downstream task performance of temporally adapted English models for social media data do not improve over time. Pretrained models without temporal adaptation are actually significantly more effective and efficient. However, we also note a lack of suitable temporal benchmarks. Our findings invite a critical reflection on when and how to temporally adapt language models, accounting for sustainability.

Analysis and extraction of useful information from legal judgments using computational linguistics was one of the earliest problems posed in the domain of information retrieval. Presently, several commercial vendors exist who automate such tasks. However, a crucial bottleneck arises in the form of exorbitant pricing and lack of resources available in analysis of judgements mete out by Hong Kong's Legal System. This paper attempts to bridge this gap by providing several statistical, machine learning, deep learning and zero-shot learning based methods to effectively analyze legal judgments from Hong Kong's Court System. The methods proposed consists of: (1) Citation Network Graph Generation, (2) PageRank Algorithm, (3) Keyword Analysis and Summarization, (4) Sentiment Polarity, and (5) Paragrah Classification, in order to be able to extract key insights from individual as well a group of judgments together. This would make the overall analysis of judgments in Hong Kong less tedious and more automated in order to extract insights quickly using fast inferencing. We also provide an analysis of our results by benchmarking our results using Large Language Models making robust use of the HuggingFace ecosystem.

Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and then optimizing the model parameters to deconvolute various resistance, capacitive, inductive, or diffusion responses. For small data sets, this procedure can be conducted manually; however, it is not feasible to manually define a proper ECM for extensive data sets with a wide range of EIS responses. Automatic identification of an ECM would substantially accelerate the analysis of large sets of EIS data. We showcase machine learning methods to classify the ECMs of 9,300 impedance spectra provided by QuantumScape for the BatteryDEV hackathon. The best-performing approach is a gradient-boosted tree model utilizing a library to automatically generate features, followed by a random forest model using the raw spectral data. A convolutional neural network using boolean images of Nyquist representations is presented as an alternative, although it achieves a lower accuracy. We publish the data and open source the associated code. The approaches described in this article can serve as benchmarks for further studies. A key remaining challenge is the identifiability of the labels, underlined by the model performances and the comparison of misclassified spectra.

Traditional drug discovery programs are being transformed by the advent of machine learning methods. Among these, Generative AI methods (GM) have gained attention due to their ability to design new molecules and enhance specific properties of existing ones. However, current GM methods have limitations, such as low affinity towards the target, unknown ADME/PK properties, or the lack of synthetic tractability. To improve the applicability domain of GM methods, we have developed a workflow based on a variational autoencoder coupled with active learning steps. The designed GM workflow iteratively learns from molecular metrics, including drug likeliness, synthesizability, similarity, and docking scores. In addition, we also included a hierarchical set of criteria based on advanced molecular modeling simulations during a final selection step. We tested our GM workflow on two model systems, CDK2 and KRAS. In both cases, our model generated chemically viable molecules with a high predicted affinity toward the targets. Particularly, the proportion of high-affinity molecules inferred by our GM workflow was significantly greater than that in the training data. Notably, we also uncovered novel scaffolds significantly dissimilar to those known for each target. These results highlight the potential of our GM workflow to explore novel chemical space for specific targets, thereby opening up new possibilities for drug discovery endeavors.

Artificial Intelligence (AI) is poised to enable a new leap in the creation of scholarly content. New forms of engagement with AI systems, such as collaborations with large language models like GPT-3, offer affordances that will change the nature of both the scholarly process and the artifacts it produces. This article articulates ways in which those artifacts can be written, distributed, read, organized, and stored that are more dynamic, and potentially more effective, than current academic practices. Specifically, rather than the current "early-binding" process (that is, one in which ideas are fully reduced to a final written form before they leave an author's desk), we propose that there are substantial benefits to a "late-binding" process, in which ideas are written dynamically at the moment of reading. In fact, the paradigm of "binding" knowledge may transition to a new model in which scholarship remains ever "unbound" and evolving. An alternative form for a scholarly work could be encapsulated via several key components: a text abstract of the work's core arguments; hyperlinks to a bibliography of relevant related work; novel data that had been collected and metadata describing those data; algorithms or processes necessary for analyzing those data; a reference to a particular AI model that would serve as a "renderer" of the canonical version of the text; and specified parameters that would allow for a precise, word-for-word reconstruction of the canonical version. Such a form would enable both the rendering of the canonical version, and also the possibility of dynamic AI reimaginings of the text in light of future findings, scholarship unknown to the original authors, alternative theories, and precise tailoring to specific audiences (e.g., children, adults, professionals, amateurs).

Laplacian regularized stratified models (LRSM) are models that utilize the explicit or implicit network structure of the sub-problems as defined by the categorical features called strata (e.g., age, region, time, forecast horizon, etc.), and draw upon data from neighboring strata to enhance the parameter learning of each sub-problem. They have been widely applied in machine learning and signal processing problems, including but not limited to time series forecasting, representation learning, graph clustering, max-margin classification, and general few-shot learning. Nevertheless, existing works on LRSM have either assumed a known graph or are restricted to specific applications. In this paper, we start by showing the importance and sensitivity of graph weights in LRSM, and provably show that the sensitivity can be arbitrarily large when the parameter scales and sample sizes are heavily imbalanced across nodes. We then propose a generic approach to jointly learn the graph while fitting the model parameters by solving a single optimization problem. We interpret the proposed formulation from both a graph connectivity viewpoint and an end-to-end Bayesian perspective, and propose an efficient algorithm to solve the problem. Convergence guarantees of the proposed optimization algorithm is also provided despite the lack of global strongly smoothness of the Laplacian regularization term typically required in the existing literature, which may be of independent interest. Finally, we illustrate the efficiency of our approach compared to existing methods by various real-world numerical examples.

Multimodal abstractive summarization (MAS) aims to produce a concise summary given the multimodal data (text and vision). Existing studies mainly focus on how to effectively use the visual features from the perspective of an article, having achieved impressive success on the high-resource English dataset. However, less attention has been paid to the visual features from the perspective of the summary, which may limit the model performance, especially in the low- and zero-resource scenarios. In this paper, we propose to improve the summary quality through summary-oriented visual features. To this end, we devise two auxiliary tasks including vision to summary task and masked image modeling task. Together with the main summarization task, we optimize the MAS model via the training objectives of all these tasks. By these means, the MAS model can be enhanced by capturing the summary-oriented visual features, thereby yielding more accurate summaries. Experiments on 44 languages, covering mid-high-, low-, and zero-resource scenarios, verify the effectiveness and superiority of the proposed approach, which achieves state-of-the-art performance under all scenarios. Additionally, we will contribute a large-scale multilingual multimodal abstractive summarization (MM-Sum) dataset.

While transformer-based systems have enabled greater accuracies with fewer training examples, data acquisition obstacles still persist for rare-class tasks -- when the class label is very infrequent (e.g. < 5% of samples). Active learning has in general been proposed to alleviate such challenges, but choice of selection strategy, the criteria by which rare-class examples are chosen, has not been systematically evaluated. Further, transformers enable iterative transfer-learning approaches. We propose and investigate transfer- and active learning solutions to the rare class problem of dissonance detection through utilizing models trained on closely related tasks and the evaluation of acquisition strategies, including a proposed probability-of-rare-class (PRC) approach. We perform these experiments for a specific rare class problem: collecting language samples of cognitive dissonance from social media. We find that PRC is a simple and effective strategy to guide annotations and ultimately improve model accuracy while transfer-learning in a specific order can improve the cold-start performance of the learner but does not benefit iterations of active learning.

We study landmark-based SLAM with unknown data association: our robot navigates in a completely unknown environment and has to simultaneously reason over its own trajectory, the positions of an unknown number of landmarks in the environment, and potential data associations between measurements and landmarks. This setup is interesting since: (i) it arises when recovering from data association failures or from SLAM with information-poor sensors, (ii) it sheds light on fundamental limits (and hardness) of landmark-based SLAM problems irrespective of the front-end data association method, and (iii) it generalizes existing approaches where data association is assumed to be known or partially known. We approach the problem by splitting it into an inner problem of estimating the trajectory, landmark positions and data associations and an outer problem of estimating the number of landmarks. Our approach creates useful and novel connections with existing techniques from discrete-continuous optimization (e.g., k-means clustering), which has the potential to trigger novel research. We demonstrate the proposed approaches in extensive simulations and on real datasets and show that the proposed techniques outperform typical data association baselines and are even competitive against an "oracle" baseline which has access to the number of landmarks and an initial guess for each landmark.

Unsupervised discovery of stories with correlated news articles in real-time helps people digest massive news streams without expensive human annotations. A common approach of the existing studies for unsupervised online story discovery is to represent news articles with symbolic- or graph-based embedding and incrementally cluster them into stories. Recent large language models are expected to improve the embedding further, but a straightforward adoption of the models by indiscriminately encoding all information in articles is ineffective to deal with text-rich and evolving news streams. In this work, we propose a novel thematic embedding with an off-the-shelf pretrained sentence encoder to dynamically represent articles and stories by considering their shared temporal themes. To realize the idea for unsupervised online story discovery, a scalable framework USTORY is introduced with two main techniques, theme- and time-aware dynamic embedding and novelty-aware adaptive clustering, fueled by lightweight story summaries. A thorough evaluation with real news data sets demonstrates that USTORY achieves higher story discovery performances than baselines while being robust and scalable to various streaming settings.