Related papers: Segment-Wise Flow Matching for Vision-Aided mmWave…

Millimeter Wave (mmWave) communications with full-duplex (FD) have the potential of increasing the spectral efficiency, relative to those with half-duplex. However, the residual self-interference (SI) from FD and high pathloss inherent to…

In the advent of next-generation wireless communication, millimeter-wave (mmWave) and terahertz (THz) technologies are pivotal for their high data rate capabilities. However, their reliance on large antenna arrays and narrow directive beams…

We present Functional Mean Flow (FMF) as a one-step generative model defined in infinite-dimensional Hilbert space. FMF extends the one-step Mean Flow framework to functional domains by providing a theoretical formulation for Functional…

This paper investigates a novel research direction that leverages vision to help overcome the critical wireless communication challenges. In particular, this paper considers millimeter wave (mmWave) communication systems, which are…

Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice…

Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising steps limits their potential use in real-time or interactive…

Recent work has shown that leveraging learned predictions can improve the running time of algorithms for bipartite matching and similar combinatorial problems. In this work, we build on this idea to improve the performance of the widely…

Millimeter-wave (mmWave) frequencies promise multi-gigabit connectivity for vehicle-to-everything (V2X) networks, but face challenges in terms of severe path loss and mobility-related beam misalignment. Reliable V2X connectivity requires…

Allocating extra computation at inference time has recently improved sample quality in large language models and diffusion-based image generation. In parallel, Flow Matching (FM) has gained traction in language, vision, and scientific…

The integration of Fourier transform and deep learning opens new avenues for time series forecasting. We reconsider the Fourier transform from a basis functions perspective. Specifically, the real and imaginary parts of the frequency…

Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete…

Modeling complex systems that evolve toward equilibrium distributions is important in various physical applications, including molecular dynamics and robotic control. These systems often follow the stochastic gradient descent of an…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

Millimeter wave (mmWave) communication represents one of the main innovations of the next generation of wireless technologies, allowing users to reach unprecedented data rates. To overcome the high path loss at mmWave frequencies, these…

Diffusion models have achieved remarkable quality in multi-modal MRI synthesis, but their computational cost (hundreds of sampling steps and separate models per modality) limits clinical deployment. We observe that this inefficiency stems…

Predictive millimeter-wave (mmWave) beamforming is a promising technique to enable low-latency and high-rate ground-air communications for cellular-connected unmanned aerial vehicles (UAVs). However, the high vulnerability of mmWave to…

Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods…

We consider the problem of designing constraint-aware flow matching (FM) models that address the issue of constraint violations commonly observed in vanilla generative models. We consider two scenarios, viz.: (a) when a differentiable…

This paper presents an inertial sensor aided technique for beam alignment and tracking in massive multiple-input multiple-output (MIMO) vehicle-to-vehicle (V2V) communications based on millimeter waves (mmWave). Since directional…

Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of…