115 citations · 383 across the 27 of their papers we have counts for
29 papers
EvoMem: Memory-Augmented Evolution for Code Optimization
Viktor Volkov, Valentin Khrulkov, Andrey V. Galichin +8
Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related tasks an…
LLM-Guided Evolutionary Search for Algebraic T-Count Optimization
Daniil Fisher, Valentin Khrulkov, Mikhail Saygin +2
T-count minimization is an NP-hard problem that arises in fault-tolerant quantum compilation. In the parity-matrix representation, which captures the non-Clifford part of a quantum…
CADEvolve: Creating Realistic CAD via Program Evolution
Maksim Elistratov, Marina Barannikov, Gregory Ivanov +4
Computer-Aided Design (CAD) delivers rapid, editable modeling for engineering and manufacturing. Recent AI progress now makes full automation feasible for various CAD tasks. Howeve…
ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search
Alexey Kravatskiy, Valentin Khrulkov, Ivan Oseledets
LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization pr…
CoMa: Contextual Massing Generation with Vision-Language Models
Evgenii Maslov, Valentin Khrulkov, Alexandra Vabnits +6
Context-aware building massing is an important early-stage design task: given a site for buildings, a generated massing should not only fit the target parcel, but also relate to th…
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms
Valentin Khrulkov, Andrey Galichin, Denis Bashkirov +5
Recent advances in LLM-guided evolutionary computation, particularly AlphaEvolve (Novikov et al., 2025; Georgiev et al., 2025), have demonstrated remarkable success in discovering…
Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs
Anton Gusarov, Anastasia Volkova, Valentin Khrulkov +3
While Retrieval-Augmented Generation (RAG) methods commonly draw information from unstructured documents, the emerging paradigm of GraphRAG aims to leverage structured data such as…
Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis
Anton Voronov, Denis Kuznedelev, Mikhail Khoroshikh +2
This work presents Switti, a scale-wise transformer for text-to-image generation. We start by adapting an existing next-scale prediction autoregressive (AR) architecture to T2I gen…
YaART: Yet Another ART Rendering Technology
Sergey Kastryulin, Artem Konev, Alexander Shishenya +20
In the rapidly progressing field of generative models, the development of efficient and high-fidelity text-to-image diffusion systems represents a significant frontier. This study…
Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Models
Nikita Starodubcev, Dmitry Baranchuk, Valentin Khrulkov +1
Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of…
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov +2
Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. Th…
Understanding DDPM Latent Codes Through Optimal Transport
Valentin Khrulkov, Gleb Ryzhakov, Andrei Chertkov +1
Diffusion models have recently outperformed alternative approaches to model the distribution of natural images, such as GANs. Such diffusion models allow for deterministic sampling…
Label-Efficient Semantic Segmentation with Diffusion Models
Dmitry Baranchuk, Ivan Rubachev, Andrey Voynov +2
Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-t…
Latent Transformations via NeuralODEs for GAN-based Image Editing
Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets +1
Recent advances in high-fidelity semantic image editing heavily rely on the presumably disentangled latent spaces of the state-of-the-art generative models, such as StyleGAN. Speci…
Revisiting Deep Learning Models for Tabular Data
Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov +1
The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports competitive results on various datasets. However, the proposed mo…
Disentangled Representations from Non-Disentangled Models
Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets +1
Constructing disentangled representations is known to be a difficult task, especially in the unsupervised scenario. The dominating paradigm of unsupervised disentanglement is curre…
Functional Space Analysis of Local GAN Convergence
Valentin Khrulkov, Artem Babenko, Ivan Oseledets
Recent work demonstrated the benefits of studying continuous-time dynamics governing the GAN training. However, this dynamics is analyzed in the model parameter space, which result…
Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks
Leyla Mirvakhabova, Evgeny Frolov, Valentin Khrulkov +2
We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem. In contrast to many modern deep learning techniques, we build o…
Sample Efficient Ensemble Learning with Catalyst.RL
Sergey Kolesnikov, Valentin Khrulkov
We present Catalyst.RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research. Main features of Catalyst.RL include large-scal…
Universality Theorems for Generative Models
Valentin Khrulkov, Ivan Oseledets
Despite the fact that generative models are extremely successful in practice, the theory underlying this phenomenon is only starting to catch up with practice. In this work we addr…
Hyperbolic Image Embeddings
Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova +2
Computer vision tasks such as image classification, image retrieval and few-shot learning are currently dominated by Euclidean and spherical embeddings, so that the final decisions…
Generalized Tensor Models for Recurrent Neural Networks
Valentin Khrulkov, Oleksii Hrinchuk, Ivan Oseledets
Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory…
Tensorized Embedding Layers for Efficient Model Compression
Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova +2
The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is…
Geometry Score: A Method For Comparing Generative Adversarial Networks
Valentin Khrulkov, Ivan Oseledets
One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse.…