Related papers: HOFAR: High-Order Augmentation of Flow Autoregress…
Flow-based text-to-image (T2I) models excel at prompt-driven image generation, but falter on Image Restoration (IR), often "drifting away" from being faithful to the measurement. Prior work mitigate this drift with data-specific flows or…
The multi-step denoising process in diffusion and Flow Matching models causes major efficiency issues, which motivates research on few-step generation. We present Solution Flow Models (SoFlow), a framework for one-step generation from…
Recent advances have reformulated diffusion models as deterministic ordinary differential equations (ODEs) through the framework of flow matching, providing a unified formulation for the noise-to-data generative process. Various…
Most end-to-end Multi-Object Tracking (MOT) methods face the problems of low accuracy and poor generalization ability. Although traditional filter-based methods can achieve better results, they are difficult to be endowed with optimal…
Diffusion and flow-matching have emerged as powerful methodologies for generative modeling, with remarkable success in capturing complex data distributions and enabling flexible guidance at inference time. Many downstream applications,…
Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing…
Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on…
Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…
Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap,…
Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient…
Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where generation under energy guidance (abbreviated as guidance in the following) is pivotal. However, the…
We present a high-order method for flow simulation on unstructured curved nonconforming sliding meshes. This method utilizes dynamic transfinite mortar elements to exchange flow information between the two sides of a sliding interface. The…
Flow-based models have proven successful for time-series generation, particularly when defined in lower-dimensional latent spaces that enable efficient sampling. However, how to design latent representations with desirable equivariance…
Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency. However, a systemic challenge remains unresolved, as inherent latency…
Deep learning-based image enhancement methods face a fundamental trade-off between computational efficiency and representational capacity. For example, although a conventional three-dimensional Look-Up Table (3D LUT) can process a degraded…
Flow matching as a paradigm of generative model achieves notable success across various domains. However, existing methods use either multi-round training or knowledge within minibatches, posing challenges in finding a favorable coupling…
This paper investigates the accuracy of bootstrap-based inference in the case of long memory fractionally integrated processes. The re-sampling method is based on the semi-parametric sieve approach, whereby the dynamics in the process used…
Recent advances in generative modeling have led to promising results in robot motion planning, particularly through diffusion and flow matching (FM)-based models that capture complex, multimodal trajectory distributions. However, these…
We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architecture, NextFlow…
Research in efficient vision backbones is evolving into models that are a mixture of convolutions and transformer blocks. A smart combination of both, architecture-wise and component-wise is mandatory to excel in the speedaccuracy…