Related papers: Reconstructing hadronically decaying tau leptons w…
Hadronic decays rates of the $\tau$ lepton into multi meson final states are presented. The structure of the hadronic matrix elements for various decay modes is discussed. The formalism of structure functions allows for a detailed test of…
Artificial neural networks are trained by a standard backpropagation learning algorithm with regularization to model and predict the systematics of -decay of heavy and superheavy nuclei. This approach to regression is implemented in two…
Vision foundation models exhibit impressive power, benefiting from the extremely large model capacity and broad training data. However, in practice, downstream scenarios may only support a small model due to the limited computational…
The knowledge of $\tau$ lepton kinematic and kinematic of the $\tau$ pair in the decay $Z/H \rightarrow \tau\tau$ is essential for various analysis at LHC. However, the reconstruction of the whole kinematic of the $\tau$ decay is a…
Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks. Despite their success, training and fine-tuning these models is still far too computationally and memory intensive. In this…
This paper describes the implementation and performance of a particle flow algorithm applied to 20.2 fb$^{-1}$ of ATLAS data from 8 TeV proton-proton collisions in Run 1 of the LHC. The algorithm removes calorimeter energy deposits due to…
Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…
Experimental studies of beauty hadron decays face significant challenges due to a wide range of backgrounds arising from the numerous possible decay channels with similar final states. For a particular signal decay, the process for…
Artificial intelligence and machine learning have shown great promise in their ability to accelerate novel materials discovery. As researchers and domain scientists seek to unify and consolidate chemical knowledge, the case for models with…
Anomalies from the LHCb lepton flavour universality and Fermilab muon anomalous magnetic momentum, show tantalizing hints of possible new physics from the lepton sectors. Due to its large mass and shorter lifetime than muon, the tau lepton…
Model-based material decomposition is a statisticaliterative reconstruction framework where basis material densityimages are estimated directly from spectral CT data. This methoduses a physical model for polyenergetic x-ray transmission…
The development of machine learning models has led to an abundance of datasets containing quantum mechanical (QM) calculations for molecular and material systems. However, traditional training methods for machine learning models are unable…
Foundation models can be disruptive for future AI development by scaling up deep learning in terms of model size and training data's breadth and size. These models achieve state-of-the-art performance (often through further adaptation) on a…
This paper presents a novel application of the Tabular Prior-Data Fitted Network (TabPFN) - a transformer-based foundation model for tabular data - to geotechnical site characterization problems defined in the GEOAI benchmark…
We present a technique for reconstructing the kinematics of pair-produced top quarks that decay to a charged lepton, a neutrino and four final state quarks in the subset of events where only three jets are reconstructed. We present a figure…
A jet algorithm based on the k-means clustering procedure is proposed which can be used for the invariant-mass reconstruction of heavy states decaying to hadronic jets. The proposed algorithm was tested by reconstructing E+ E- to ttbar to 6…
We introduce Poseidon, a foundation model for learning the solution operators of PDEs. It is based on a multiscale operator transformer, with time-conditioned layer norms that enable continuous-in-time evaluations. A novel training strategy…
Accurate machine-learning models for aerodynamic prediction are essential for accelerating shape optimization, yet remain challenging to develop for complex three-dimensional configurations due to the high cost of generating training data.…
Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks -- text and code generation, question answering, summarization, image classification, and…
Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…