Related papers: Active learning BSM parameter spaces
Ultralight axion-like particles (ALPs) are well-motivated dark matter candidates introduced by theories beyond the standard model. However, the constraints on the existence of ALPs through existing laboratory experiments are hindered by…
We perform an investigation of the MSSM parameter space at the Fermi scale taking into account available accelerator, non-accelerator and cosmological constraints. Extra assumptions about upper bounds for some of the SUSY particles are also…
We investigate the use of active-learning (AL) strategies to generate the input excitation signal at runtime for system identification of linear and nonlinear autoregressive and state-space models. We adapt various existing AL approaches…
Several Active Learning (AL) policies require retraining a target model several times in order to identify the most informative samples and rarely offer the option to focus on the acquisition of samples from underrepresented classes. Here…
Recent works have shown a surprising result: a small fraction of Large Language Model (LLM) parameter outliers are disproportionately important to the quality of the model. LLMs contain billions of parameters, so these small fractions, such…
We study architectural and optimization techniques for sample-efficient language modeling under the constraints of the BabyLM 2025 shared task. Our model, BLaLM, replaces self-attention with a linear-time mLSTM token mixer and explores…
The development of accurate and transferable machine learning (ML) potentials for predicting molecular energetics is a challenging task. The process of data generation to train such ML potentials is a task neither well understood nor…
Recently, the CMS Collaboration observed the hint of a resonance decaying to two photons at about 96 GeV with a local significance of $2.8\sigma$. While it is too early to say whether this will stand the test of time, such a resonance can…
Electroweak precision measurements can provide indirect information about the possible scale of supersymmetry already at the present level of accuracy. We update the present-day sensitivities of precision data using the new experimental…
Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most…
We determine the allowed parameter space and the particle spectra of the minimal SUSY standard model (MSSM) and nonminimal SUSY standard model (NMSSM) imposing correct electroweak gauge-symmetry breaking and recent experimental constraints.…
Active learning optimizes the exploration of large parameter spaces by strategically selecting which experiments or simulations to conduct, thus reducing resource consumption and potentially accelerating scientific discovery. A key…
Active learning frameworks offer efficient data annotation without remarkable accuracy degradation. In other words, active learning starts training the model with a small size of labeled data while exploring the space of unlabeled data in…
We use the framework of dark matter effective field theories to study the complementarity of bounds for a dark matter particle with mass in the MeV range. Taking properly into account the mixing between operators induced by the…
Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL one iteratively selects training examples for annotation, often those for which the current model is…
We propose Cartography Active Learning (CAL), a novel Active Learning (AL) algorithm that exploits the behavior of the model on individual instances during training as a proxy to find the most informative instances for labeling. CAL is…
Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…
The B-L extension of the Standard Model requires the existence of right-handed neutrinos and naturally realizes the seesaw mechanism of neutrino mass generation. We study the possibility of explaining the dark matter in this model with an…
Do we need active learning? The rise of strong deep semi-supervised methods raises doubt about the usability of active learning in limited labeled data settings. This is caused by results showing that combining semi-supervised learning…
Hyperspectral imagery collected from airborne or satellite sources inevitably suffers from spectral variability, making it difficult for spectral unmixing to accurately estimate abundance maps. The classical unmixing model, the linear…