arXiv subjects

Maria Kovaleva

Publications and source records attributed to Maria Kovaleva.

8 recordsLinked to original sources

arXiv2025

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

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.

cs.CV↗

arXiv2025

Time-Correlated Video Bridge Matching

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 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 Bridge Matching 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, benchmark datasets and human evaluation.

cs.LG↗

arXiv2025

NABLA: Neighborhood Adaptive Block-Level Attention

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

cs.CV↗

arXiv2025

VIVAT: Virtuous Improving VAE Training through Artifact Mitigation

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.

cs.CV↗

arXiv2025

Looking around you: external information enhances representations for event sequences

Representation learning produces models in different domains, such as store purchases, client transactions, and general people's behavior. However, such models for event sequences usually process each sequence in isolation, ignoring context from those 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's representation in a setting with 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 Learnable attention aggregation, that can highlight more complex information flow among other users. The proposed methods operate on top of an existing encoder and support its efficient fine-tuning. Across nine diverse event sequence datasets (finance, e-commerce, entertainment, etc.) and downstream tasks, Learnable attention improves metric scores, both with and without fine-tuning, while mean pooling yields a smaller but still significant gain.

cs.LG↗

arXiv2024

Investigating mutual coupling in the MWA Phase II compact array

Measurement of the power spectrum of high redshift 21 cm emission from neutral hydrogen probes the formation of the first luminous objects and the ionization of intergalactic medium by the first stars. However, the 21 cm signal at these redshifts is orders of magnitude fainter than astrophysical foregrounds, making it challenging to measure. Power spectrum techniques may be able to avoid these foregrounds by extracting foreground-free Fourier modes, but this is exacerbated by instrumental systematics that can add spectral structure to the data, leaking foreground power to the foreground-free Fourier modes. It is therefore imperative that any instrumental systematic effects are properly understood and mitigated. One such systematic occurs when neighboring antennas have undesired coupling. A systematic in Phase II data from the MWA was identified which manifests as excess correlation in the visibilities. One possible explanation for such an effect is mutual coupling between antennas. A numerical electromagnetic software simulation of the antenna beam using FEKO has been built to estimate the amplitude of this effect for multiple antennas in the MWA. The numerical model predicts an amplitude which exceeds the requirement to avoid spreading the foreground. More work is necessary to better validate the required level of coupling and to verify that approximations did not under estimate the level of coupling.

astro-ph.IM↗

arXiv2024

Learning Transactions Representations for Information Management in Banks: Mastering Local, Global, and External Knowledge

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\%.

cs.LG↗

arXiv2023

Designing an attack-defense game: how to increase robustness of financial transaction models via a competition

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.

cs.LG↗