Related papers: Identifying L-H transition in HL-2A through deep l…
The success of reinforcement learning (RL)-based control in tokamaks, an emerging technique for controlled nuclear fusion with improved flexibility, typically requires substantial interaction with a simulator capable of accurately evolving…
Recent advances in the integrated modeling of ELMy H-mode plasmas are presented. A model for the H-mode pedestal and for the triggering of ELMs predicts the height, width, and shape of the H-mode pedestal and the frequency and width of…
Current LLM structured pruning methods typically involve two steps: (1) compression with calibration data and (2) costly continued pretraining on billions of tokens to recover lost performance. This second step is necessary as the first…
The extreme learning machine (ELM) method can yield highly accurate solutions to linear/nonlinear partial differential equations (PDEs), but requires the last hidden layer of the neural network to be wide to achieve a high accuracy. If the…
Fuel efficient Homogeneous Charge Compression Ignition (HCCI) engine combustion timing predictions must contend with non-linear chemistry, non-linear physics, period doubling bifurcation(s), turbulent mixing, model parameters that can drift…
Recent advancements in machine learning, particularly through deep learning architectures like PointNet, have transformed the processing of three-dimensional (3D) point clouds, significantly improving 3D object classification and…
Automatic detection of leukemic B-lymphoblast cancer in microscopic images is very challenging due to the complicated nature of histopathological structures. To tackle this issue, an automatic and robust diagnostic system is required for…
The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on…
Multivariate techniques based on engineered features have found wide adoption in the identification of jets resulting from hadronic top decays at the Large Hadron Collider (LHC). Recent Deep Learning developments in this area include the…
The popular use of histopathology images, such as hematoxylin and eosin (H&E), has proven to be useful in detecting tumors. However, moving such cancer cases forward for treatment requires accurate on the amount of the human epidermal…
Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing need for more efficient finetuning and inference without sacrificing performance. This is…
Circular cross-section plasma is the most basic form of tokamak plasma and the fundamental configuration for magnetic confinement fusion experiments. Based on the HL-2A limiter discharge experiments, the magnetohydrodynamic (MHD)…
Automated emotion detection in speech is a challenging task due to the complex interdependence between words and the manner in which they are spoken. It is made more difficult by the available datasets; their small size and incompatible…
Improving reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this by performing multiple latent iterations to refine each token…
The ATLAS experiment at CERN measures energy of proton-proton (p-p) collisions with a repetition frequency of 40 MHz at the Large Hadron Collider (LHC). The readout electronics of liquid-argon (LAr) calorimeters are being prepared for high…
The results of flux-driven, two-fluid simulations in single-null configurations are used to investigate the processes determining the turbulent transport in the tokamak edge. Three turbulent transport regimes are identified: (i) a developed…
Knowledge distillation is a form of model compression that allows artificial neural networks of different sizes to learn from one another. Its main application is the compactification of large deep neural networks to free up computational…
We deploy an advanced Machine Learning (ML) environment, leveraging a multi-scale cross-attention encoder for event classification, towards the identification of the $gg\to H\to hh\to b\bar b b\bar b$ process at the High Luminosity Large…
Prompt injection attacks are a critical security vulnerability in large language models (LLMs), allowing attackers to hijack model behavior by injecting malicious instructions within the input context. Recent defense mechanisms have…
Fine-tuned large language models (LLMs) often exhibit overconfidence, particularly when trained on small datasets, resulting in poor calibration and inaccurate uncertainty estimates. Evidential Deep Learning (EDL), an uncertainty-aware…