Search

Cytology slides are essential tools in diagnosing and staging cancer, but their analysis is time-consuming and costly. Foundation models have shown great potential to assist in these tasks. In this paper, we explore how existing foundation models can be applied to cytological classification. More particularly, we focus on low-rank adaptation, a parameter-efficient fine-tuning method suited to few-shot learning. We evaluated five foundation models across four cytological classification datasets. Our results demonstrate that fine-tuning the pre-trained backbones with LoRA significantly improves model performance compared to fine-tuning only the classifier head, achieving state-of-the-art results on both simple and complex classification tasks while requiring fewer data samples., Comment: 5 pages, 2 figures

The shortage of doctors is creating a critical squeeze in access to medical expertise. While conversational Artificial Intelligence (AI) holds promise in addressing this problem, its safe deployment in patient-facing roles remains largely unexplored in real-world medical settings. We present the first large-scale evaluation of a physician-supervised LLM-based conversational agent in a real-world medical setting. Our agent, Mo, was integrated into an existing medical advice chat service. Over a three-week period, we conducted a randomized controlled experiment with 926 cases to evaluate patient experience and satisfaction. Among these, Mo handled 298 complete patient interactions, for which we report physician-assessed measures of safety and medical accuracy. Patients reported higher clarity of information (3.73 vs 3.62 out of 4, p < 0.05) and overall satisfaction (4.58 vs 4.42 out of 5, p < 0.05) with AI-assisted conversations compared to standard care, while showing equivalent levels of trust and perceived empathy. The high opt-in rate (81% among respondents) exceeded previous benchmarks for AI acceptance in healthcare. Physician oversight ensured safety, with 95% of conversations rated as "good" or "excellent" by general practitioners experienced in operating a medical advice chat service. Our findings demonstrate that carefully implemented AI medical assistants can enhance patient experience while maintaining safety standards through physician supervision. This work provides empirical evidence for the feasibility of AI deployment in healthcare communication and insights into the requirements for successful integration into existing healthcare services., Comment: 14 pages, 7 figures, 3 tables

Nuclear magnetic resonance instruments are becoming available to the do-it-yourself community. The challenges encountered in the endeavor to build a magnetic resonance imaging instrument from scratch were confronted in a four-day hackathon at Singapore University of Technology and Design in spring 2024. One day was devoted to educational lectures and three days to system construction and testing. Seventy young researchers from all parts of the world formed six teams focusing on magnet, gradient coil, RF coil, console, system integration, and design, which together produced a working MRI instrument in three days. The different steps, encountered challenges, and their solutions are reported., Comment: 49 pages, 23 figures, comments welcome (this paper is meant to be useful to people constructing their own MRI systems)

Sparse deep neural networks (DNNs) excel in real-world applications like robotics and computer vision, by reducing computational demands that hinder usability. However, recent studies aim to boost DNN efficiency by trimming redundant neurons or filters based on task relevance, but neglect their adaptability to distribution shifts. We aim to enhance these existing techniques by introducing a companion network, Ghost Connect-Net (GC-Net), to monitor the connections in the original network with distribution generalization advantage. GC-Net's weights represent connectivity measurements between consecutive layers of the original network. After pruning GC-Net, the pruned locations are mapped back to the original network as pruned connections, allowing for the combination of magnitude and connectivity-based pruning methods. Experimental results using common DNN benchmarks, such as CIFAR-10, Fashion MNIST, and Tiny ImageNet show promising results for hybridizing the method, and using GC-Net guidance for later layers of a network and direct pruning on earlier layers. We provide theoretical foundations for GC-Net's approach to improving generalization under distribution shifts., Comment: 21 pages, 4 figures, 3 subfigures, 42 tables

Within the context of the ALICE ITS3 collaboration, a set of MAPS small-scale test structures were developed using the 65 nm TPSCo CMOS imaging process with the upgrade of the ALICE inner tracking system as its primary focus. One such sensor, the Circuit Exploratoire 65 nm (CE-65), and its evolution the CE-65v2, were developed to explore charge collection properties for varying configurations including collection layer process (standard, blanket, modified with gap), pixel pitch (15, 18, \SI{22.5}{\micro\meter}), and pixel geometry (square vs hexagonal/staggered). In this work the characterisation of the CE-65v2 chip, based on $^{55}$Fe lab measurements and test beams at CERN SPS, is presented. Matrix gain uniformity up to the $\mathcal{O}$(5\%) level was demonstrated for all considered chip configurations. The CE-65v2 chip achieves a spatial resolution of under \SI{2}{\micro\meter} during beam tests. Process modifications allowing for faster charge collection and less charge sharing result in decreased spatial resolution, but a considerably wider range of operation, with both the \SI{15}{\micro\meter} and \SI{22.5}{\micro\meter} chips achieving over 99\% efficiency up to a $\sim$180 e$^{-}$ seed threshold. The results serve to validate the 65 nm TPSCo CMOS process, as well as to motivate design choices in future particle detection experiments., Comment: 7 pages, 12 figures; Proceedings for iWoRiD 2024 (Lisbon)

Hyperspectral imaging (HSI) holds significant potential for transforming the field of computational pathology. However, there is currently a shortage of pixel-wise annotated HSI data necessary for training deep learning (DL) models. Additionally, the number of HSI-based research studies remains limited, and in many cases, the advantages of HSI over traditional RGB imaging have not been conclusively demonstrated, particularly for specimens collected intraoperatively. To address these challenges we present a database consisted of 27 HSIs of hematoxylin-eosin stained frozen sections, collected from 14 patients with colon adenocarcinoma metastasized to the liver. It is aimed to validate pixel-wise classification for intraoperative tumor resection. The HSIs were acquired in the spectral range of 450 to 800 nm, with a resolution of 1 nm, resulting in images of 1384x1035 pixels. Pixel-wise annotations were performed by three pathologists. To overcome challenges such as experimental variability and the lack of annotated data, we combined label-propagation-based semi-supervised learning (SSL) with spectral-spatial features extracted by: the multiscale principle of relevant information (MPRI) method and tensor singular spectrum analysis method. Using only 1% of labeled pixels per class the SSL-MPRI method achieved a micro balanced accuracy (BACC) of 0.9313 and a micro F1-score of 0.9235 on the HSI dataset. The performance on corresponding RGB images was lower, with a micro BACC of 0.8809 and a micro F1-score of 0.8688. These improvements are statistically significant. The SSL-MPRI approach outperformed six DL architectures trained with 63% of labeled pixels. Data and code are available at: https://github.com/ikopriva/ColonCancerHSI., Comment: 12 pages, 5 figures, 5 tables

Large language models (LLMs) represent a promising, but controversial, tool in aiding scientific peer review. This study evaluates the usefulness of LLMs in a conference setting as a tool for vetting paper submissions against submission standards. We conduct an experiment at the 2024 Neural Information Processing Systems (NeurIPS) conference, where 234 papers were voluntarily submitted to an "LLM-based Checklist Assistant." This assistant validates whether papers adhere to the author checklist used by NeurIPS, which includes questions to ensure compliance with research and manuscript preparation standards. Evaluation of the assistant by NeurIPS paper authors suggests that the LLM-based assistant was generally helpful in verifying checklist completion. In post-usage surveys, over 70% of authors found the assistant useful, and 70% indicate that they would revise their papers or checklist responses based on its feedback. While causal attribution to the assistant is not definitive, qualitative evidence suggests that the LLM contributed to improving some submissions. Survey responses and analysis of re-submissions indicate that authors made substantive revisions to their submissions in response to specific feedback from the LLM. The experiment also highlights common issues with LLMs: inaccuracy (20/52) and excessive strictness (14/52) were the most frequent issues flagged by authors. We also conduct experiments to understand potential gaming of the system, which reveal that the assistant could be manipulated to enhance scores through fabricated justifications, highlighting potential vulnerabilities of automated review tools.

Classical Wolf-Rayet stars are descendants of massive OB-type stars that have lost their hydrogen-rich envelopes, and are in the final stages of stellar evolution, possibly exploding as type Ib/c supernovae. It is understood that the mechanisms driving this mass-loss are either strong stellar winds and or binary interactions, so intense studies of these binaries including their evolution can tell us about the importance of the two pathways in WR formation. WR 138 (HD 193077) has a period of just over 4 years and was previously reported to be resolved through interferometry. We report on new interferometric data combined with spectroscopic radial velocities in order to provide a three-dimensional orbit of the system. The precision on our parameters tend to be about an order of magnitude better than previous spectroscopic techniques. These measurements provide masses of the stars, namely $M_{\rm WR} = 13.93\pm1.49M_{\odot}$ and $M_{\rm O} = 26.28\pm1.71M_{\odot}$. The derived orbital parallax agrees with the parallax from \textit{Gaia}, namely with a distance of 2.13 kpc. We compare the system's orbit to models from BPASS, showing that the system likely may have been formed with little interaction but could have formed through some binary interactions either following or at the start of a red supergiant phase, but with the most likely scenario occurring as the red supergiant phase starts for a $\sim 40M_\odot$ star., Comment: accepted to ApJ

In the era of Industry 4.0, system reliability engineering faces both challenges and opportunities. On the one hand, the complexity of cyber-physical systems, the integration of novel numerical technologies, and the handling of large amounts of data pose new difficulties for ensuring system reliability. On the other hand, innovations such as AI-driven prognostics, digital twins, and IoT-enabled systems enable the implementation of new methodologies that are transforming reliability engineering. Condition-based monitoring and predictive maintenance are examples of key advancements, leveraging real-time sensor data collection and AI to predict and prevent equipment failures. These approaches reduce failures and downtime, lower costs, and extend equipment lifespan and sustainability. However, it also brings challenges such as data management, integrating complexity, and the need for fast and accurate models and algorithms. Overall, the convergence of advanced technologies in Industry 4.0 requires a rethinking of reliability tasks, emphasising adaptability and real-time data processing. In this chapter, we propose to review recent innovations in the field, related methods and applications, as well as challenges and barriers that remain to be explored. In the red lane, we focus on smart manufacturing and automotive engineering applications with sensor-based monitoring and driver assistance systems., Comment: 34 pages, 19 figures

Large-scale deployment of large language models (LLMs) in various applications, such as chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure inclusivity. Culture has been widely studied in psychology and anthropology, and there has been a recent surge in research on making LLMs more culturally inclusive in LLMs that goes beyond multilinguality and builds on findings from psychology and anthropology. In this paper, we survey efforts towards incorporating cultural awareness into text-based and multimodal LLMs. We start by defining cultural awareness in LLMs, taking the definitions of culture from anthropology and psychology as a point of departure. We then examine methodologies adopted for creating cross-cultural datasets, strategies for cultural inclusion in downstream tasks, and methodologies that have been used for benchmarking cultural awareness in LLMs. Further, we discuss the ethical implications of cultural alignment, the role of Human-Computer Interaction in driving cultural inclusion in LLMs, and the role of cultural alignment in driving social science research. We finally provide pointers to future research based on our findings about gaps in the literature.

Human image datasets used to develop and evaluate technology should represent the diversity of human phenotypes, including skin tone. Datasets that include skin tone information frequently rely on manual skin tone ratings based on the Fitzpatrick Skin Type (FST) or the Monk Skin Tone (MST) scales in lieu of the actual measured skin tone of the image dataset subjects. However, perceived skin tone is subject to known biases and skin tone appearance in digital images can vary substantially depending on the capture camera and environment, confounding manual ratings. Surprisingly, the relationship between skin-tone ratings and measured skin tone has not been explored. To close this research gap, we measured the relationship between skin tone ratings from existing scales (FST, MST) and skin tone values measured by a calibrated colorimeter. We also propose and assess a novel Colorimetric Skin Tone (CST) scale developed based on prior colorimetric measurements. Using experiments requiring humans to rate their own skin tone and the skin tone of subjects in images, we show that the new CST scale is more sensitive, consistent, and colorimetrically accurate. While skin tone ratings appeared to correct for some color variation across images, they introduced biases related to race and other factors. These biases must be considered before using manual skin-tone ratings in technology evaluations or for engineering decisions.

Regular remote sensing of the magnetic field embedded within the million-degree solar corona is severely lacking. This reality impedes fundamental investigations of the nature of coronal heating, the generation of solar and stellar winds, and the impulsive release of energy into the solar system via flares and other eruptive phenomena. Resulting from advancements in large aperture solar coronagraphy, we report unprecedented maps of polarized spectra emitted at 1074 nm by Fe+12 atoms in the active corona. We detect clear signatures of the Zeeman effect that are produced by the coronal magnetic field along the optically thin path length of its formation. Our comparisons with global magnetohydrodynamic models highlight the valuable constraints that these measurements provide for coronal modeling efforts, which are anticipated to yield subsequent benefits for space weather research and forecasting., Comment: 23 pages, 10 figures, published in Science Advances

While interpretability research has shed light on some internal algorithms utilized by transformer-based LLMs, reasoning in natural language, with its deep contextuality and ambiguity, defies easy categorization. As a result, formulating clear and motivating questions for circuit analysis that rely on well-defined in-domain and out-of-domain examples required for causal interventions is challenging. Although significant work has investigated circuits for specific tasks, such as indirect object identification (IOI), deciphering natural language reasoning through circuits remains difficult due to its inherent complexity. In this work, we take initial steps to characterize causal reasoning in LLMs by analyzing clear-cut cause-and-effect sentences like "I opened an umbrella because it started raining," where causal interventions may be possible through carefully crafted scenarios using GPT-2 small. Our findings indicate that causal syntax is localized within the first 2-3 layers, while certain heads in later layers exhibit heightened sensitivity to nonsensical variations of causal sentences. This suggests that models may infer reasoning by (1) detecting syntactic cues and (2) isolating distinct heads in the final layers that focus on semantic relationships., Comment: 12 pages

In this paper we study the embedding problem of an operator into a strongly continuous semigroup. We obtain characterizations for some classes of operators, namely composition operators and analytic Toeplitz operators on the Hardy space H^2. In particular, we focus on the isometric ones using the necessary and sufficient condition observed by T. Eisner.

Metalenses, advanced nanostructured alternatives to conventional lenses, significantly enhance the compactness and functionality of optical systems. Despite progress in monochromatic applications, scaling metalenses to centimeter-sized apertures for broadband or multiwavelength use remains challenging due to limitations in achieving the necessary group delay (GD) with current materials. In this study, we introduce a novel multiwavelength, polarization-insensitive metalens design operating in the near-infrared (NIR). Our approach employs multiple Huygens' metasurface layers, each optimized to modulate a specific wavelength while maintaining high transmittance and minimal phase disturbance at other wavelengths. We demonstrate a metalens operating at 2000 and 2340 nm with a numerical aperture (NA) of 0.11. In simulation, the metalens achieves a normalized modulation transfer function (MTF) that is nearly exactly diffraction-limited. The absolute focusing efficiencies are 65% and 56%, corresponding to relative efficiencies of 76% and 65% compared to an ideal lens of the same dimensions. The meta-atoms are designed using an inverse shape-optimization method that ensures polarization insensitivity and high tolerance to layer misalignment. The proposed design is compatible with large-area nanofabrication techniques, allowing metasurface layers to be fabricated individually and assembled into the final device. This innovative approach is also generalizable to any arbitrary multiwavelength phase profile beyond that of simple lensing., Comment: 9 pages, 5 figures

The tendency of repeating past choices more often than expected from the history of outcomes has been repeatedly empirically observed in reinforcement learning experiments. It can be explained by at least two computational processes: asymmetric update and (gradual) choice perseveration. A recent meta-analysis showed that both mechanisms are detectable in human reinforcement learning. However, while their descriptive value seems to be well established, they have not been compared regarding their possible adaptive value. In this study, we address this gap by simulating reinforcement learning agents in a variety of environments with a new variant of an evolutionary algorithm. Our results show that positivity bias (in the form of asymmetric update) is evolutionary stable in many situations, while the emergence of gradual perseveration is less systematic and robust. Overall, our results illustrate that biases can be adaptive and selected by evolution, in an environment-specific manner.

We present 850 {\mu}m thermal dust polarization observations with a resolution of 14.4"(~ 0.13 pc) towards an infrared dark cloud G16.96+0.27 using JCMT/POL-2. The average magnetic field orientation, which roughly agrees with the larger-scale magnetic field orientation traced by the Planck 353 GHz data, is approximately perpendicular to the filament structure. The estimated plane-of-sky magnetic field strength is ~ 96 {\mu}G and ~ 60 {\mu}G using two variants of the Davis-Chandrasekhar-Fermi methods. We calculate the virial and magnetic critical parameters to evaluate the relative importance of gravity, the magnetic field, and turbulence. The magnetic field and turbulence are both weaker than gravity, but magnetic fields and turbulence together are equal to gravity, suggesting that G16.96+0.27 is in a quasi-equilibrium state. The cloud-magnetic-field alignment is found to have a trend moving away from perpendicularity in the dense regions, which may serve as a tracer of potential fragmentation in such quiescent filaments., Comment: Accepted by ApJ. 13 pages, 5 figures

Modern Question Answering (QA) and Reasoning approaches based on Large Language Models (LLMs) commonly use prompting techniques, such as Chain-of-Thought (CoT), assuming the resulting generation will have a more granular exploration and reasoning over the question space and scope. However, such methods struggle with generating outputs that are faithful to the intermediate chain of reasoning produced by the model. On the other end of the spectrum, neuro-symbolic methods such as Faithful CoT (F-CoT) propose to combine LLMs with external symbolic solvers. While such approaches boast a high degree of faithfulness, they usually require a model trained for code generation and struggle with tasks that are ambiguous or hard to formalise strictly. We introduce $\textbf{F}$aithful $\textbf{L}$ogic-$\textbf{A}$ided $\textbf{R}$easoning and $\textbf{E}$xploration ($\textbf{FLARE}$), a novel interpretable approach for traversing the problem space using task decompositions. We use the LLM to plan a solution, soft-formalise the query into facts and predicates using a logic programming code and simulate that code execution using an exhaustive multi-hop search over the defined space. Our method allows us to compute the faithfulness of the reasoning process w.r.t. the generated code and analyse the steps of the multi-hop search without relying on external solvers. Our methods achieve SOTA results on $\mathbf{7}$ out of $\mathbf{9}$ diverse reasoning benchmarks. We also show that model faithfulness positively correlates with overall performance and further demonstrate that $\textbf{FLARE}$ allows pinpointing the decisive factors sufficient for and leading to the correct answer with optimal reasoning during the multi-hop search.

Interband Cascade Lasers (ICLs) are semiconductor lasers emitting in the mid-wave infrared (MWIR 3-6 {\mu}m) and can operate as frequency combs (FCs). These demonstrations are based on double section cavities that can reduce dispersion and/or are adapted for radio-frequency operation. Here we show that ICLs FCs at long wavelengths, where the refractive index dispersion reduces, can be realized in a single long section cavity. We show FC generation for ICLs operating at {\lambda} ~ 4.2 {\mu}m, demonstrating narrow electrical beatnotes over a large current range. We also reconstruct the ultrafast temporal response through a modified SWIFT spectroscopy setup with two fast MWIR detectors, which shows a frequency modulated response in free-running operation. Further, we show that, through active modelocking, the ICL can be forced to generate short pulses on the order of 3 ps. This temporal response is in agreement with Maxwell Bloch simulations, highlighting that these devices possess long dynamics (~100ps) and potentially makes them appropriate for the generation of large peak powers in the MWIR., Comment: 11 pages, 6 figures

Classical Wolf-Rayet stars are the descendants of massive OB stars that have lost their hydrogen envelopes and are burning helium in their cores prior to exploding as type Ib/c supernovae. The mechanisms for losing their hydrogen envelopes are either through binary interactions or through strong stellar winds potentially coupled with episodic mass-loss. Amongst the bright classical WR stars, the binary system WR\,137 (HD\,192641; WC7d + O9e) is the subject of this paper. This binary is known to have a 13-year period and produces dust near periastron. Here we report on interferometry with the CHARA Array collected over a decade of time and providing the first visual orbit for the system. We combine these astrometric measurements with archival radial velocities to measure masses of the stars of $M_{\rm WR} = 9.5\pm3.4 M_\odot$ and $M_{\rm O} = 17.3\pm 1.9 M_\odot$ when we use the most recent \textit{Gaia} distance. These results are then compared to predicted dust distribution using these orbital elements, which match the observed imaging from \textit{JWST} as discussed recently by Lau et al. Furthermore, we compare the system to the BPASS models, finding that the WR star likely formed through stellar winds and not through binary interactions. However, the companion O star did likely accrete some material from the WR's mass-loss to provide the rotation seen today that drives its status as an Oe star., Comment: Accepted to ApJ

In this paper, we address the identification and estimation of insurance models where insurees have private information about their risk and risk aversion. The model includes random damages and allows for several claims, while insurers choose from a finite number of coverages. We show that the joint distribution of risk and risk aversion is nonparametrically identified despite bunching due to multidimensional types and a finite number of coverages. Our identification strategy exploits the observed number of claims as well as an exclusion restriction, and a full support assumption. Furthermore, our results apply to any form of competition. We propose a novel estimation procedure combining nonparametric estimators and GMM estimation that we illustrate in a Monte Carlo study.

In this study, we propose a novel approach to uncover subgroup-specific and subgroup-common latent factors addressing the challenges posed by the heterogeneity of neurological and mental disorders, which hinder disease understanding, treatment development, and outcome prediction. The proposed approach, sparse Group Factor Analysis (GFA) with regularised horseshoe priors, was implemented with probabilistic programming and can uncover associations (or latent factors) among multiple data modalities differentially expressed in sample subgroups. Synthetic data experiments showed the robustness of our sparse GFA by correctly inferring latent factors and model parameters. When applied to the Genetic Frontotemporal Dementia Initiative (GENFI) dataset, which comprises patients with frontotemporal dementia (FTD) with genetically defined subgroups, the sparse GFA identified latent disease factors differentially expressed across the subgroups, distinguishing between "subgroup-specific" latent factors within homogeneous groups and "subgroup common" latent factors shared across subgroups. The latent disease factors captured associations between brain structure and non-imaging variables (i.e., questionnaires assessing behaviour and disease severity) across the different genetic subgroups, offering insights into disease profiles. Importantly, two latent factors were more pronounced in the two more homogeneous FTD patient subgroups (progranulin (GRN) and microtubule-associated protein tau (MAPT) mutation), showcasing the method's ability to reveal subgroup-specific characteristics. These findings underscore the potential of sparse GFA for integrating multiple data modalities and identifying interpretable latent disease factors that can improve the characterization and stratification of patients with neurological and mental health disorders., Comment: 38 pages, 14 figures

Training a large set of machine learning algorithms to convergence in order to select the best-performing algorithm for a dataset is computationally wasteful. Moreover, in a budget-limited scenario, it is crucial to carefully select an algorithm candidate and allocate a budget for training it, ensuring that the limited budget is optimally distributed to favor the most promising candidates. Casting this problem as a Markov Decision Process, we propose a novel framework in which an agent must select in the process of learning the most promising algorithm without waiting until it is fully trained. At each time step, given an observation of partial learning curves of algorithms, the agent must decide whether to allocate resources to further train the most promising algorithm (exploitation), to wake up another algorithm previously put to sleep, or to start training a new algorithm (exploration). In addition, our framework allows the agent to meta-learn from learning curves on past datasets along with dataset meta-features and algorithm hyperparameters. By incorporating meta-learning, we aim to avoid myopic decisions based solely on premature learning curves on the dataset at hand. We introduce two benchmarks of learning curves that served in international competitions at WCCI'22 and AutoML-conf'22, of which we analyze the results. Our findings show that both meta-learning and the progression of learning curves enhance the algorithm selection process, as evidenced by methods of winning teams and our DDQN baseline, compared to heuristic baselines or a random search. Interestingly, our cost-effective baseline, which selects the best-performing algorithm w.r.t. a small budget, can perform decently when learning curves do not intersect frequently.

This study introduces a novel frequency-based data-driven controller for adaptive optics, using power spectral density for optimization while ensuring stability criteria. It addresses disturbance rejection, command amplitude constraints and system transfer functions through convex optimization to obtain an optimal control in an infinite input response filter form. Evaluated within the SAXO+ project, it demonstrates efficacy under diverse atmospheric conditions and operational scenarios. The proposed controller is tested in both standard and disentangled adaptive optics schemes, showcasing its adaptability and performance. Experimental validation is conducted using the COMPASS simulation tool, affirming the controller's promise for enhancing adaptive optics systems in real-world applications.

Much theoretical work has described the ability of transformers to represent formal languages. However, linking theoretical results to empirical performance is not straightforward due to the complex interplay between the architecture, the learning algorithm, and training data. To test whether theoretical lower bounds imply \emph{learnability} of formal languages, we turn to recent work relating transformers to $n$-gram language models (LMs). We study transformers' ability to learn random $n$-gram LMs of two kinds: ones with arbitrary next-symbol probabilities and ones where those are defined with shared parameters. We find that classic estimation techniques for $n$-gram LMs such as add-$\lambda$ smoothing outperform transformers on the former, while transformers perform better on the latter, outperforming methods specifically designed to learn $n$-gram LMs.

The FAIR Universe -- HiggsML Uncertainty Challenge focuses on measuring the physics properties of elementary particles with imperfect simulators due to differences in modelling systematic errors. Additionally, the challenge is leveraging a large-compute-scale AI platform for sharing datasets, training models, and hosting machine learning competitions. Our challenge brings together the physics and machine learning communities to advance our understanding and methodologies in handling systematic (epistemic) uncertainties within AI techniques., Comment: Whitepaper for the FAIR Universe HiggsML Uncertainty Challenge Competition, available : https://fair-universe.lbl.gov