Maria Kovaleva

Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko et al.

This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core line-up of models: Kandinsky 5.0 Image Lite - a line-up of 6B parameter image generation models, Kandinsky 5.0 Video Lite - a fast and lightweight 2B parameter text-to-video and image-to-video models, and Kandinsky 5.0 Video Pro - 19B parameter models that achieves superior video generation quality. We provide a comprehensive review of the data curation lifecycle - including collection, processing, filtering and clustering - for the multi-stage training pipeline that involves extensive pre-training and incorporates quality-enhancement techniques such as self-supervised fine-tuning (SFT) and reinforcement learning (RL)-based post-training. We also present novel architectural, training, and inference optimizations that enable Kandinsky 5.0 to achieve high generation speeds and state-of-the-art performance across various tasks, as demonstrated by human evaluation. As a large-scale, publicly available generative framework, Kandinsky 5.0 leverages the full potential of its pre-training and subsequent stages to be adapted for a wide range of generative applications. We hope that this report, together with the release of our open-source code and training checkpoints, will substantially advance the development and accessibility of high-quality generative models for the research community.

Dmitrii Mikhailov, Aleksey Letunovskiy, Maria Kovaleva et al.

Recent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution and long-duration video sequences. In this paper, we propose NABLA, a novel Neighborhood Adaptive Block-Level Attention mechanism that dynamically adapts to sparsity patterns in video diffusion transformers (DiTs). By leveraging block-wise attention with adaptive sparsity-driven threshold, NABLA reduces computational overhead while preserving generative quality. Our method does not require custom low-level operator design and can be seamlessly integrated with PyTorch's Flex Attention operator. Experiments demonstrate that NABLA achieves up to 2.7x faster training and inference compared to baseline almost without compromising quantitative metrics (CLIP score, VBench score, human evaluation score) and visual quality drop. The code and model weights are available here: https://github.com/gen-ai-team/Wan2.1-NABLA

Alexey Zaytsev, Maria Kovaleva, Alex Natekin et al.

Banks routinely use neural networks to make decisions. While these models offer higher accuracy, they are susceptible to adversarial attacks, a risk often overlooked in the context of event sequences, particularly sequences of financial transactions, as most works consider computer vision and NLP modalities. We propose a thorough approach to studying these risks: a novel type of competition that allows a realistic and detailed investigation of problems in financial transaction data. The participants directly oppose each other, proposing attacks and defenses -- so they are examined in close-to-real-life conditions. The paper outlines our unique competition structure with direct opposition of participants, presents results for several different top submissions, and analyzes the competition results. We also introduce a new open dataset featuring financial transactions with credit default labels, enhancing the scope for practical research and development.

Alexandra Bazarova, Maria Kovaleva, Ilya Kuleshov et al.

In today's world, banks use artificial intelligence to optimize diverse business processes, aiming to improve customer experience. Most of the customer-related tasks can be categorized into two groups: 1) local ones, which focus on a client's current state, such as transaction forecasting, and 2) global ones, which consider the general customer behaviour, e.g., predicting successful loan repayment. Unfortunately, maintaining separate models for each task is costly. Therefore, to better facilitate information management, we compared eight state-of-the-art unsupervised methods on 11 tasks in search for a one-size-fits-all solution. Contrastive self-supervised learning methods were demonstrated to excel at global problems, while generative techniques were superior at local tasks. We also introduced a novel approach, which enriches the client's representation by incorporating external information gathered from other clients. Our method outperforms classical models, boosting accuracy by up to 20\%.

Lev Novitskiy, Viacheslav Vasilev, Maria Kovaleva et al.

Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation quality. This paper introduces VIVAT, a systematic approach to mitigating common artifacts in KL-VAE training without requiring radical architectural changes. We present a detailed taxonomy of five prevalent artifacts - color shift, grid patterns, blur, corner and droplet artifacts - and analyze their root causes. Through straightforward modifications, including adjustments to loss weights, padding strategies, and the integration of Spatially Conditional Normalization, we demonstrate significant improvements in VAE performance. Our method achieves state-of-the-art results in image reconstruction metrics (PSNR and SSIM) across multiple benchmarks and enhances text-to-image generation quality, as evidenced by superior CLIP scores. By preserving the simplicity of the KL-VAE framework while addressing its practical challenges, VIVAT offers actionable insights for researchers and practitioners aiming to optimize VAE training.

Viacheslav Vasilev, Arseny Ivanov, Nikita Gushchin et al.

Diffusion models excel in noise-to-data generation tasks, providing a mapping from a Gaussian distribution to a more complex data distribution. However they struggle to model translations between complex distributions, limiting their effectiveness in data-to-data tasks. While Bridge Matching (BM) models address this by finding the translation between data distributions, their application to time-correlated data sequences remains unexplored. This is a critical limitation for video generation and manipulation tasks, where maintaining temporal coherence is particularly important. To address this gap, we propose Time-Correlated Video Bridge Matching (TCVBM), a framework that extends BM to time-correlated data sequences in the video domain. TCVBM explicitly models inter-sequence dependencies within the diffusion bridge, directly incorporating temporal correlations into the sampling process. We compare our approach to classical methods based on bridge matching and diffusion models for three video-related tasks: frame interpolation, image-to-video generation, and video super-resolution. TCVBM achieves superior performance across multiple quantitative metrics, demonstrating enhanced generation quality and reconstruction fidelity.

Maria Kovaleva, Petr Sokerin, Pavel Tikhomirov et al.

Representation learning produces models in different domains, such as store purchases, client transactions, and general people's behaviour. However, such models for event sequences usually process each sequence in isolation, ignoring context from ones that co-occur in time. This limitation is particularly problematic in domains with fast-evolving conditions, like finance and e-commerce, or when certain sequences lack recent events. We develop a method that aggregates information from multiple user representations, augmenting a specific user for a scenario of multiple co-occurring event sequences, achieving better quality than processing each sequence independently. Our study considers diverse aggregation approaches, ranging from simple pooling techniques to trainable attention-based Kernel attention aggregation, that can highlight more complex information flow from other users. The proposed methods operate on top of an existing encoder and support its efficient fine-tuning. Across six diverse event sequence datasets (finance, e-commerce, education, etc.) and downstream tasks, Kernel attention improves ROC-AUC scores, both with and without fine-tuning, while mean pooling yields a smaller but still significant gain.