Nikita Kazeev

Siddharth Betala, Samuel P. Gleason, Ali Ramlaoui et al.

Generative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented exploration of chemical space. Yet, the lack of standardized evaluation frameworks makes it challenging to evaluate, compare, and further develop these ML models meaningfully. In this work, we introduce LeMat-GenBench, a unified benchmark for generative models of crystalline materials, supported by a set of evaluation metrics designed to better inform model development and downstream applications. We release both an open-source evaluation suite and a public leaderboard on Hugging Face, and benchmark 12 recent generative models. Results reveal that an increase in stability leads to a decrease in novelty and diversity on average, with no model excelling across all dimensions. Altogether, LeMat-GenBench establishes a reproducible and extensible foundation for fair model comparison and aims to guide the development of more reliable, discovery-oriented generative models for crystalline materials.

Lucio Anderlini, Matteo Barbetti, Simone Capelli et al.

Detailed detector simulation is the major consumer of CPU resources at LHCb, having used more than 90% of the total computing budget during Run 2 of the Large Hadron Collider at CERN. As data is collected by the upgraded LHCb detector during Run 3 of the LHC, larger requests for simulated data samples are necessary, and will far exceed the pledged resources of the experiment, even with existing fast simulation options. An evolution of technologies and techniques to produce simulated samples is mandatory to meet the upcoming needs of analysis to interpret signal versus background and measure efficiencies. In this context, we propose Lamarr, a Gaudi-based framework designed to offer the fastest solution for the simulation of the LHCb detector. Lamarr consists of a pipeline of modules parameterizing both the detector response and the reconstruction algorithms of the LHCb experiment. Most of the parameterizations are made of Deep Generative Models and Gradient Boosted Decision Trees trained on simulated samples or alternatively, where possible, on real data. Embedding Lamarr in the general LHCb Gauss Simulation framework allows combining its execution with any of the available generators in a seamless way. Lamarr has been validated by comparing key reconstructed quantities with Detailed Simulation. Good agreement of the simulated distributions is obtained with two-order-of-magnitude speed-up of the simulation phase.

Lucio Anderlini, Matteo Barbetti, Denis Derkach et al.

The increasing luminosities of future data taking at Large Hadron Collider and next generation collider experiments require an unprecedented amount of simulated events to be produced. Such large scale productions demand a significant amount of valuable computing resources. This brings a demand to use new approaches to event generation and simulation of detector responses. In this paper, we discuss the application of generative adversarial networks (GANs) to the simulation of the LHCb experiment events. We emphasize main pitfalls in the application of GANs and study the systematic effects in detail. The presented results are based on the Geant4 simulation of the LHCb Cherenkov detector.

Stephen G. Dale, Nikita Kazeev, Alastair J. A. Price et al.

Artificial intelligence and machine learning are reshaping how we approach scientific discovery, not by replacing established methods but by extending what researchers can probe, predict, and design. In this roadmap we provide a forward-looking view of AI-enabled science across biology, chemistry, climate science, mathematics, materials science, physics, self-driving laboratories and unconventional computing. Several shared themes emerge: the need for diverse and trustworthy data, transferable electronic-structure and interatomic models, AI systems integrated into end-to-end scientific workflows that connect simulations to experiments and generative systems grounded in synthesisability rather than purely idealised phases. Across domains, we highlight how large foundation models, active learning and self-driving laboratories can close loops between prediction and validation while maintaining reproducibility and physical interpretability. Taken together, these perspectives outline where AI-enabled science stands today, identify bottlenecks in data, methods and infrastructure, and chart concrete directions for building AI systems that are not only more powerful but also more transparent and capable of accelerating discovery in complex real-world environments.

Lucio Anderlini, Constantine Chimpoesh, Nikita Kazeev et al.

In recent years fully-parametric fast simulation methods based on generative models have been proposed for a variety of high-energy physics detectors. By their nature, the quality of data-driven models degrades in the regions of the phase space where the data are sparse. Since machine-learning models are hard to analyse from the physical principles, the commonly used testing procedures are performed in a data-driven way and can't be reliably used in such regions. In our work we propose three methods to estimate the uncertainty of generative models inside and outside of the training phase space region, along with data-driven calibration techniques. A test of the proposed methods on the LHCb RICH fast simulation is also presented.

Nian Liu, Nikita Kazeev, Stephen Gregory Dale et al.

De novo crystal generation seeks to discover materials that are not merely realistic, but also stable and novel. However, most existing generative models are trained to maximize the likelihood of observed crystals, which encourages samples to stay close to known materials yet not necessarily align with the criteria that matter in discovery. Through an empirical investigation, we show that current crystal generative models are caught in a pronounced stability--novelty trade-off: moving toward the observed distribution preserves stability but limits novelty, whereas moving away from it quickly destroys stability. This suggests that the useful region for discovering crystals that are both stable and novel is extremely narrow. To escape the trade-off, we introduce Crys-JEPA, a joint embedding predictive architecture for crystals that learns an energy-aware latent space preserving formation-energy differences. In this space, stability assessment can be reformulated as an embedding-based comparison against accessible training crystals, reducing the reliance on expensive energy evaluation and task-specific external references. Building on Crys-JEPA, we further develop a screening-and-refinement pipeline that identifies promising generated crystals and reintroduces them to refine the generative model. On MP-20 and Alex-MP-20 datasets, we achieve improvements over baselines up to 81.4% and 82.6% on V.S.U.N metric, respectively.

Nian Liu, Yuwei Zeng, Ryoji Kubo et al.

De novo crystal generation, a central task in materials discovery, aims to generate crystals that are simultaneously valid, stable, unique, and novel. Existing methods mainly rely on black-box stochastic sampling, providing limited control over how generated structures move beyond the observed distribution. In this paper, we introduce a concept-based compositional framework for crystal generation. We train a vector-quantized variational autoencoder to automatically discover a shared set of reusable crystal concepts, which serve as building blocks for guided generation. These learned concepts naturally exhibit interpretability from both local atomic environments and global symmetry patterns, and generalize to crystals from different distributions. By recombining such concepts, our framework enables controllable exploration of novel crystals beyond the training distribution, rather than relying solely on unconstrained random sampling. To further improve composition efficiency, we introduce a composition generator and iteratively refine it using high-quality samples generated by the model itself. The resulting concept compositions are then used to condition downstream crystal generation. Numerical experiments on MP-20 and Alex-MP-20 show that compositing concepts separately increase base model up to 53.2% and 51.7% on V.S.U.N metric, with particular gains in novelty.

Andrey Okhotin, Maksim Nakhodnov, Nikita Kazeev et al.

In recent years, diffusion-based models have demonstrated exceptional performance in searching for simultaneously stable, unique, and novel (S.U.N.) crystalline materials. However, most of these models don't have the ability to change the number of atoms in the crystal during the generation process, which limits the variability of model sampling trajectories. In this paper, we demonstrate the severity of this restriction and introduce a simple yet powerful technique, mirage infusion, which enables diffusion models to change the state of the atoms that make up the crystal from existent to non-existent (mirage) and vice versa. We show that this technique improves model quality by up to $\times2.5$ compared to the same model without this modification. The resulting model, Mirage Atom Diffusion (MiAD), is an equivariant joint diffusion model for de novo crystal generation that is capable of altering the number of atoms during the generation process. MiAD achieves an $8.2\%$ S.U.N. rate on the MP-20 dataset, which substantially exceeds existing state-of-the-art approaches. The source code can be found at \href{https://github.com/andrey-okhotin/miad.git}{\texttt{github.com/andrey-okhotin/miad}}.

Nikita Kazeev, Wei Nong, Ignat Romanov et al.

Crystal symmetry plays a fundamental role in determining its physical, chemical, and electronic properties such as electrical and thermal conductivity, optical and polarization behavior, and mechanical strength. Almost all known crystalline materials have internal symmetry. However, this is often inadequately addressed by existing generative models, making the consistent generation of stable and symmetrically valid crystal structures a significant challenge. We introduce WyFormer, a generative model that directly tackles this by formally conditioning on space group symmetry. It achieves this by using Wyckoff positions as the basis for an elegant, compressed, and discrete structure representation. To model the distribution, we develop a permutation-invariant autoregressive model based on the Transformer encoder and an absence of positional encoding. Extensive experimentation demonstrates WyFormer's compelling combination of attributes: it achieves best-in-class symmetry-conditioned generation, incorporates a physics-motivated inductive bias, produces structures with competitive stability, predicts material properties with competitive accuracy even without atomic coordinates, and exhibits unparalleled inference speed.

Maxim Borisyak, Nikita Kazeev

Data analysis in high energy physics has to deal with data samples produced from different sources. One of the most widely used ways to unfold their contributions is the sPlot technique. It uses the results of a maximum likelihood fit to assign weights to events. Some weights produced by sPlot are by design negative. Negative weights make it difficult to apply machine learning methods. The loss function becomes unbounded. This leads to divergent neural network training. In this paper we propose a mathematically rigorous way to transform the weights obtained by sPlot into class probabilities conditioned on observables, thus enabling to apply any machine learning algorithm out-of-the-box.

Artem Maevskiy, Denis Derkach, Nikita Kazeev et al.

The increasing luminosities of future Large Hadron Collider runs and next generation of collider experiments will require an unprecedented amount of simulated events to be produced. Such large scale productions are extremely demanding in terms of computing resources. Thus new approaches to event generation and simulation of detector responses are needed. In LHCb, the accurate simulation of Cherenkov detectors takes a sizeable fraction of CPU time. An alternative approach is described here, when one generates high-level reconstructed observables using a generative neural network to bypass low level details. This network is trained to reproduce the particle species likelihood function values based on the track kinematic parameters and detector occupancy. The fast simulation is trained using real data samples collected by LHCb during run 2. We demonstrate that this approach provides high-fidelity results.

Maxim Borisyak, Nikita Kazeev

Data analysis in high energy physics often deals with data samples consisting of a mixture of signal and background events. The sPlot technique is a common method to subtract the contribution of the background by assigning weights to events. Part of the weights are by design negative. Negative weights lead to the divergence of some machine learning algorithms training due to absence of the lower bound in the loss function. In this paper we propose a mathematically rigorous way to train machine learning algorithms on data samples with background described by sPlot to obtain signal probabilities conditioned on observables, without encountering negative event weight at all. This allows usage of any out-of-the-box machine learning methods on such data.

Denis Derkach, Nikita Kazeev, Fedor Ratnikov et al.

We propose a way to simulate Cherenkov detector response using a generative adversarial neural network to bypass low-level details. This network is trained to reproduce high level features of the simulated detector events based on input observables of incident particles. This allows the dramatic increase of simulation speed. We demonstrate that this approach provides simulation precision which is consistent with the baseline and discuss possible implications of these results.

Leonid Gremyachikh, Dmitrii Dubov, Nikita Kazeev et al.

The number of space objects will grow several times in a few years due to the planned launches of constellations of thousands microsatellites. It leads to a significant increase in the threat of satellite collisions. Spacecraft must undertake collision avoidance maneuvers to mitigate the risk. According to publicly available information, conjunction events are now manually handled by operators on the Earth. The manual maneuver planning requires qualified personnel and will be impractical for constellations of thousands satellites. In this paper we propose a new modular autonomous collision avoidance system called "Space Navigator". It is based on a novel maneuver optimization approach that combines domain knowledge with Reinforcement Learning methods.