Related papers: DiffLoc: Diffusion Model-Based High-Precision Posi…
Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields from coarse-scale numerical model simulations, saving the…
Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection and image segmentation) and are increasingly gaining…
Pervasive localization is essential for continuous tracking applications, yet existing solutions face challenges in balancing power consumption and accuracy. GPS, while precise, is impractical for continuous tracking of micro-assets due to…
Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio. A practical bottleneck of diffusion models is their sampling speed, due to the repeated evaluation of…
Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time consumption of sampling. Existing caching methods accelerate…
This paper proposes a new transmission strategy for the multiuser massive multiple-input multiple-output (MIMO) systems, including uplink/downlink channel estimation and user scheduling for data transmission. A discrete Fourier transform…
Strong generative models can accurately learn channel distributions. This could save recurring costs for physical measurements of the channel. Moreover, the resulting differentiable channel model supports training neural encoders by…
Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment:…
Diffusion models have demonstrated remarkable synthesis quality and diversity in generating co-speech gestures. However, the computationally intensive sampling steps associated with diffusion models hinder their practicality in real-world…
Climate change is intensifying rainfall extremes, making high-resolution precipitation projections crucial for society to better prepare for impacts such as flooding. However, current Global Climate Models (GCMs) operate at spatial…
3D human pose estimation from 2D images is a challenging problem due to depth ambiguity and occlusion. Because of these challenges the task is underdetermined, where there exists multiple -- possibly infinite -- poses that are plausible…
The advent of ultra-massive multiple-input-multiple output systems holds great promise for next-generation communications, yet their channels exhibit hybrid far- and near- field beam-squint (HFBS) effect. In this paper, we not only overcome…
Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds. Meanwhile, diffusion models have shown appealing performance in generating…
In the context of continuously rising global air traffic, efficient and safe Conflict Detection and Resolution (CD&R) is paramount for air traffic management. Although Deep Reinforcement Learning (DRL) offers a promising pathway for CD&R…
In recent years, UWB has garnered widespread attention in academia and industry due to its low power consumption, wide bandwidth, and high time resolution characteristics. This paper introduces the design of an asynchronous IR-UWB…
Diffusion models are rising as a powerful solution for high-fidelity image generation, which exceeds GANs in quality in many circumstances. However, their slow training and inference speed is a huge bottleneck, blocking them from being used…
In this paper, we propose a novel coarse-to-fine continuous pose diffusion method to enhance the precision of pick-and-place operations within robotic manipulation tasks. Leveraging the capabilities of diffusion networks, we facilitate the…
Recently, the advent of generative AI technologies has made transformational impacts on our daily lives, yet its application in scientific applications remains in its early stages. Data scarcity is a major, well-known barrier in data-driven…
In this work, we present FRIGID, a framework with a novel diffusion language model that generates molecular structures conditioned on mass spectra via intermediate fingerprint representations and determined chemical formulae, training at…
Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…