This review summarizes popular unsupervised learning methods, and gives an overview of their past, current, and future uses in astronomy. Unsupervised learning aims to organise the information content of a dataset, in such a way that knowledge can be extracted. Traditionally this has been achieved through dimensionality reduction techniques that aid the ranking of a dataset, for example through principal component analysis or by using auto-encoders, or simpler visualisation of a high dimensional space, for example through the use of a self organising map. Other desirable properties of unsupervised learning include the identification of clusters, i.e. groups of similar objects, which has traditionally been achieved by the k-means algorithm and more recently through density-based clustering such as HDBSCAN. More recently, complex frameworks have emerged, that chain together dimensionality reduction and clustering methods. However, no dataset is fully unknown. Thus, nowadays a lot of research has been directed towards self-supervised and semi-supervised methods that stand to gain from both supervised and unsupervised learning.

Symbolic regression (SR) methods attempt to learn mathematical expressions that approximate the behavior of an observed system. However, when dealing with multivariate systems, they often fail to identify the functional form that explains the relationship between each variable and the system's response. To begin to address this, we propose an explainable neural SR method that generates univariate symbolic skeletons that aim to explain how each variable influences the system's response. By analyzing multiple sets of data generated artificially, where one input variable varies while others are fixed, relationships are modeled separately for each input variable. The response of such artificial data sets is estimated using a regression neural network (NN). Finally, the multiple sets of input-response pairs are processed by a pre-trained Multi-Set Transformer that solves a problem we termed Multi-Set Skeleton Prediction and outputs a univariate symbolic skeleton. Thus, such skeletons represent explanations of the function approximated by the regression NN. Experimental results demonstrate that this method learns skeleton expressions matching the underlying functions and outperforms two GP-based and two neural SR methods.

Imaging modalities like X-rays, computerized tomography scans, and magnetic resonance imaging provide detailed views of teeth, bones, and soft tissues (White and Pharoah, 2014). These tools enhance the precision of diagnoses and treatments, ensuring better patient outcomes. Among the current imaging exams, radiographs are the most common in dentistry (White and Pharoah, 2014; Langlais and Miller, 2016), being requested to identify various pathologies like cavities, periodontal disease, impacted teeth, and bone infections (Chang et al., 2020; Yüksel et al., 2021) and track the progress of dental treatments. One of the most commonly used radiographs in dentistry is the panoramic radiograph (White and Pharoah, 2014; Langlais and Miller, 2016; Silva et al., 2018), which is an extraoral imaging technique where the X-ray film or sensor remains outside the patient's mouth during acquisition. In a single image, the panoramic radiograph provides a comprehensive view of both upper and lower jaws, but with less detail of the mouth structures (Haring and Jansen, 2000; Silva et al., 2018; Jader et al., 2018; Pinheiro et al., 2021). Figure 1 depicts an example of a panoramic radiograph, revealing the structures and their overlaps, which can lead to cluttered readings.

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. However, their performance in tasks involving tabular data, especially those requiring symbolic reasoning, faces challenges due to the structural variance and inconsistency in table cell values often found in web tables. In this paper, we introduce NormTab, a novel framework aimed at enhancing the symbolic reasoning performance of LLMs by normalizing web tables. We study table normalization as a stand-alone, one-time preprocessing step using LLMs to support symbolic reasoning on tabular data. Our experimental evaluation, conducted on challenging web table datasets such as WikiTableQuestion and TabFact, demonstrates that leveraging NormTab significantly improves symbolic reasoning performance, showcasing the importance and effectiveness of web table normalization for enhancing LLM-based symbolic reasoning tasks.

The Off-Policy Evaluation (OPE) problem consists of evaluating the performance of counterfactual policies with data collected by another one. This problem is of utmost importance for various application domains, e.g., recommendation systems, medical treatments, and many others. To solve the OPE problem, we resort to estimators, which aim to estimate in the most accurate way possible the performance that the counterfactual policies would have had if they were deployed in place of the logging policy. In the literature, several estimators have been developed, all with different characteristics and theoretical guarantees. Therefore, there is no dominant estimator, and each estimator may be the best one for different OPE problems, depending on the characteristics of the dataset at hand. While the selection of the estimator is a crucial choice for an accurate OPE, this problem has been widely overlooked in the literature. We propose an automated data-driven OPE estimator selection method based on machine learning. In particular, the core idea we propose in this paper is to create several synthetic OPE tasks and use a machine learning model trained to predict the best estimator for those synthetic tasks. We empirically show how our method is able to generalize to unseen tasks and make a better estimator selection compared to a baseline method on several real-world datasets, with a computational cost significantly lower than the one of the baseline.

Translating advances in visual perception to robotic grasping and manipulation of objects remains challenging. For complex manipulation tasks such as peg insertion, pulling or twisting with resistance, and dynamic motions such as throwing and catching, fine-grained manipulation requires tactile perception. Tactile sensors have been paired with visual sensors for both classical control and machine learning approaches to these tasks [1], but issues of fragility and cost present barriers to heavy use or industrial integration, particularly for manipulation tasks that would place higher forces on sensors at the tactile edge. Previously, a GelSight [2] tactile sensor was used to train an agent on a USB insertion task [3], the first time this was achieved with imitation learning. GelSight is not designed for robustness to higher shear forces and was noted to break irrecoverably during data collection and inference for that task, requiring repeated replacement. This work also demonstrated an approach using tactile information only during pretraining, then ablating the tactile sensor at inference, achieving a more robust vision-only manipulation system. BeadSight [4] aimed to make a simpler, low cost calibration-free sensor that, like GelSight, still operated at an end effector's point of contact with objects. We constructed the BeadSight sensor, which does not rely on any calibration and instead relies entirely on neural networks to distill information about contacts and movements at the tactile edge. In this work, we repeated the visuo-tactile pretraining USB plugging experiment using the much lower fidelity BeadSight to produce a direct comparison with the GelSight sensor in the task of plugging in a USB cable.

Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible development practices, we introduce the Foundation Model Development Cheatsheet: a growing collection of 250+ tools and resources spanning text, vision, and speech modalities. We draw on a large body of prior work to survey resources (e.g. software, documentation, frameworks, guides, and practical tools) that support informed data selection, processing, and understanding, precise and limitation-aware artifact documentation, efficient model training, advance awareness of the environmental impact from training, careful model evaluation of capabilities, risks, and claims, as well as responsible model release, licensing and deployment practices. We hope this curated collection of resources helps guide more responsible development. The process of curating this list, enabled us to review the AI development ecosystem, revealing what tools are critically missing, misused, or over-used in existing practices. We find that (i) tools for data sourcing, model evaluation, and monitoring are critically under-serving ethical and real-world needs, (ii) evaluations for model safety, capabilities, and environmental impact all lack reproducibility and transparency, (iii) text and particularly English-centric analyses continue to dominate over multilingual and multi-modal analyses, and (iv) evaluation of systems, rather than just models, is needed so that capabilities and impact are assessed in context.

Existing methods for adapting large language models (LLMs) to new tasks are not suited to multi-task adaptation because they modify all the model weights -- causing destructive interference between tasks. The resulting effects, such as catastrophic forgetting of earlier tasks, make it challenging to obtain good performance on multiple tasks at the same time. To mitigate this, we propose Lottery Ticket Adaptation (LoTA), a sparse adaptation method that identifies and optimizes only a sparse subnetwork of the model. We evaluate LoTA on a wide range of challenging tasks such as instruction following, reasoning, math, and summarization. LoTA obtains better performance than full fine-tuning and low-rank adaptation (LoRA), and maintains good performance even after training on other tasks -- thus, avoiding catastrophic forgetting. By extracting and fine-tuning over lottery tickets (or sparse task vectors), LoTA also enables model merging over highly dissimilar tasks. Our code is made publicly available at https://github.com/kiddyboots216/lottery-ticket-adaptation.

As large language models gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms for high-end datacenter hardware. In this work, we ask the opposite question: how fast can we run LLMs on consumer machines? Consumer GPUs can no longer fit the largest available models (50B+ parameters) and must offload them to RAM or SSD. When running with offloaded parameters, the inference engine can process batches of hundreds or thousands of tokens at the same time as just one token, making it a natural fit for speculative decoding. We propose SpecExec (Speculative Execution), a simple parallel decoding method that can generate up to 20 tokens per target model iteration for popular LLM families. It utilizes the high spikiness of the token probabilities distribution in modern LLMs and a high degree of alignment between model output probabilities. SpecExec takes the most probable tokens continuation from the draft model to build a "cache" tree for the target model, which then gets validated in a single pass. Using SpecExec, we demonstrate inference of 50B+ parameter LLMs on consumer GPUs with RAM offloading at 4-6 tokens per second with 4-bit quantization or 2-3 tokens per second with 16-bit weights.

In-context learning (ICL) empowers large language models (LLMs) to perform diverse tasks in underrepresented languages using only short in-context information, offering a crucial avenue for narrowing the gap between high-resource and low-resource languages. Nonetheless, there is only a handful of works explored ICL for low-resource languages with most of them focusing on relatively high-resource languages, such as French and Spanish. In this work, we extensively study ICL and its cross-lingual variation (X-ICL) on 25 low-resource and 7 relatively higher-resource languages. Our study not only assesses the effectiveness of ICL with LLMs in low-resource languages but also identifies the shortcomings of in-context label alignment, and introduces a more effective alternative: query alignment. Moreover, we provide valuable insights into various facets of ICL for low-resource languages. Our study concludes the significance of few-shot in-context information on enhancing the low-resource understanding quality of LLMs through semantically relevant information by closing the language gap in the target language and aligning the semantics between the targeted low-resource and the high-resource language that the model is proficient in. Our work highlights the importance of advancing ICL research, particularly for low-resource languages. Our code is publicly released at https://github.com/SamuelCahyawijaya/in-context-alignment