Shedding Light on Dark Matter at the LHC with Machine Learning

We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the $Z_3$-symmetric Next-to-Minimal Supersymmetric Standard Model. This framework gives rise to regions of parameter space where DM is obtained via co-annihilation with nearby higgsino-like electroweakinos and DM direct detection~signals are suppressed, the so-called ``blind spots". On the other hand, collider signatures remain promising due to enhanced radiative decay modes of higgsinos into the singlino-dominated LSP and a photon, rather than into leptons or hadrons. This motivates searches for radiatively decaying neutralinos, however, these signals face substantial background challenges, as the decay products are typically soft due to the small mass-splits ($\Delta m$) between the LSP and the higgsino-like coannihilation partners. We apply a data-driven Machine Learning (ML) analysis that improves sensitivity to these subtle signals, offering a powerful complement to traditional search strategies to discover a new physics scenario. Using an LHC integrated luminosity of $100~\mathrm{fb}^{-1}$ at $14~\mathrm{TeV}$, the method achieves a $5\sigma$ discovery reach for higgsino masses up to $225~\mathrm{GeV}$ with $\Delta m\!\lesssim\!12~\mathrm{GeV}$, and a $2\sigma$ exclusion up to $285~\mathrm{GeV}$ with $\Delta m\!\lesssim\!20~\mathrm{GeV}$. These results highlight the power of collider searches to probe DM candidates that remain hidden from current direct detection experiments, and provide a motivation for a search by the LHC collaborations using ML methods.

Rotary Masked Autoencoders are Versatile Learners

Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional computational overhead and increased method complexity. We present the Rotary Masked Autoencoder (RoMAE), which utilizes the popular Rotary Positional Embedding (RoPE) method for continuous positions. RoMAE is an extension to the Masked Autoencoder (MAE) that enables representation learning with multidimensional continuous positional information while avoiding any time-series-specific architectural specializations. We showcase RoMAE's performance on a variety of modalities including irregular and multivariate time-series, images, and audio, demonstrating that RoMAE surpasses specialized time-series architectures on difficult datasets such as the DESC ELAsTiCC Challenge while maintaining MAE's usual performance across other modalities. In addition, we investigate RoMAE's ability to reconstruct the embedded continuous positions, demonstrating that including learned embeddings in the input sequence breaks RoPE's relative position property.

Machine-Learning Analysis of Radiative Decays to Dark Matter at the LHC

The search for weakly interacting matter particles (WIMPs) is one of the main objectives of the High Luminosity Large Hadron Collider (HL-LHC). In this work we use Machine Learning (ML) techniques to explore WIMP radiative decays into a Dark Matter (DM) candidate in a supersymmetric framework. The minimal supersymmetric WIMP sector includes the lightest neutralino that can provide the observed DM relic density through its co-annihilation with the second lightest neutralino and lightest chargino. Moreover, the direct DM detection cross section rates fulfill current experimental bounds and provide discovery targets for the same region of model parameters in which the radiative decay of the second lightest neutralino into a photon and the lightest neutralino is enhanced. This strongly motivates the search for radiatively decaying neutralinos which, however, suffers from strong backgrounds. We investigate the LHC reach in the search for these radiatively decaying particles by means of cut-based and ML methods and estimate its discovery potential in this well-motivated, new physics scenario.