Related papers: Framework for Model Independent Analyses of Multip…
We propose a novel centrality definition-independent method for analyzing higher-order cumulants, specifically addressing the challenge of volume fluctuations that dominate in low-energy heavy-ion collisions. This method reconstructs…
To extend the limited scope of autonomy used in prior missions for operation in distant and complex environments, there is a need to further develop and mature autonomy that jointly reasons over multiple subsystems, which we term…
In a well-calibrated risk prediction model, the average predicted probability is close to the true event rate for any given subgroup. Such models are reliable across heterogeneous populations and satisfy strong notions of algorithmic…
An overview of recent searches with top quarks in the final state using up to 36 fb$^{-1}$ of pp collision data at $\sqrt{s}$ = 13 TeV collected with the ATLAS and CMS experiments at the LHC is presented. In particular, searches for heavy…
Confounding is a significant obstacle to unbiased estimation of causal effects from observational data. For settings with high-dimensional covariates -- such as text data, genomics, or the behavioral social sciences -- researchers have…
For many particle collider searches for physics beyond the Standard Model in final states with jets and missing transverse momentum, events from QCD multi-jet processes are an important and challenging background contribution. The CMS and…
A vast amount of ecological knowledge generated recently has hinged upon the ability of model selection methods to discriminate among various ecological hypotheses. The last decade has seen the rise of Bayesian hierarchical models in…
Machine learning systems have been extensively used as auxiliary tools in domains that require critical decision-making, such as healthcare and criminal justice. The explainability of decisions is crucial for users to develop trust on these…
Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…
Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplishes anomaly detection for multiple classes with a unified…
This study aims to comprehensively investigate the deep ensemble approach, an approximate Bayesian inference, in the multi-output regression task for predicting the aerodynamic performance of a missile configuration. To this end, the effect…
Most of the existing classification methods are aimed at minimization of empirical risk (through some simple point-based error measured with loss function) with added regularization. We propose to approach this problem in a more information…
Deep research agents have emerged as LLM-based systems designed to perform multi-step information seeking and reasoning over large, open-domain sources to answer complex questions by synthesizing information from multiple information…
Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in assessing uncertainty, leading to overconfident predictions. To…
Several different uncertain inference systems (UISs) have been developed for representing uncertainty in rule-based expert systems. Some of these, such as Mycin's Certainty Factors, Prospector, and Bayes' Networks were designed as…
In this paper we build a comprehensive analysis framework to perform direct extraction of all possible effective Higgs couplings to neutral electroweak gauge bosons in the decay to electrons and muons, the so called `golden channel'. Our…
Cancer survival analysis commonly integrates information across diverse medical modalities to make survival-time predictions. Existing methods primarily focus on extracting different decoupled features of modalities and performing fusion…
Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective…
The Beyond the Standard Model Working Group discussed a variety of topics relating to exotic searches at current and future colliders, and the phenomenology of current models beyond the Standard Model. For example, various supersymmetric…
Since the advent of various pre-trained large language models, extracting structured knowledge from scientific text has experienced a revolutionary change compared with traditional machine learning or natural language processing techniques.…