Alessandro Figà-Talamanca (1938-2023) was an influential Italian mathematician, scientific leader of the Italian group of harmonic analysis for many years. Since the late 1970ies, his interest focussed on harmonic analysis on free groups and trees....
[NeurIPS 2024] Official code for DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut (⭐ 50)
RNA inverse folding, designing sequences to form specific 3D structures, is critical for therapeutics, gene regulation, and synthetic biology. Current methods, focused on sequence recovery, struggle to address structural objectives like secondary str...
Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to maintain tempora...
Recent progress in large-scale zero-shot speech synthesis has been significantly advanced by language models and diffusion models. However, the generation process of both methods is slow and computationally intensive. Efficient speech synthesis using...
Kotlin is a novel language that represents an alternative to Java, and has been recently adopted as a first-class programming language for Android applications. Kotlin is achieving a significant diffusion among developers, and several studies have hi...
Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial control. However, existing methods either train separate models for each c...
There is an overwhelming number of news articles published every day around the globe. Following the evolution of a news-story is a difficult task given that there is no such mechanism available to track back in time to study the diffusion of the rel...
Personalization is central to human-AI interaction, yet current diffusion-based image generation systems remain largely insensitive to user diversity. Existing attempts to address this often rely on costly paired preference data or introduce latency...
Using molecular beam epitaxy (MBE) to grow multi-elemental oxides (MEO) is generally challenging, partly due to difficulty in stoichiometry control. Occasionally, if one of the elements is volatile at the growth temperature, stoichiometry control can...
linked list tldraw + LCM model (realtime stable diffusion) (⭐ 70)
3D image reconstruction from a limited number of 2D images has been a long-standing challenge in computer vision and image analysis. While deep learning-based approaches have achieved impressive performance in this area, existing deep networks often...
In the recent paper \cite{DESZ}, the notion of $\mathscr{Y}^{g,ξ}$-submartingale processes has been introduced. Within a jump-diffusion model, we prove here that a process $X$ which satisfies the simultaneous $\mathscr{Y}^{\mathbb{Q},g,ξ}$ -submart...
We quantify the spin Hall angle θSH and spin diffusion length lsd of Nb from inverse spin-Hall effect (iSHE) measurements in Nb/Ni80Fe20 bilayers under ferromagnetic resonance. By varying the Nb thickness tNb and comparing to a Ni80Fe20/Pt reference...
Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech synthesis. Yet...
This paper has been withdrawn by the author because it is superseded by a new preprint: Tran Doan Huan & Nguyen Phuc Hai: arXiv:1010.5162....
Current diffusion-based video editing primarily focuses on local editing (\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondences. However, these methods often fail to accurately edit the foregroun...
The diffusion of minimally invasive, endovascular interventions motivates the development of visualization methods for complex vascular networks. We propose a planar representation of blood vessel trees which preserves the properties that are most re...
Diffusion mechanism design, which investigate how to incentivise agents to invite as many colleagues to a multi-agent decision making as possible, is a new research paradigm at the intersection between microeconomics and computer science. In this pap...
We study continuous time quantum random walk on a comb with infinite teeth and show that the return probability to the starting point decays with time $t$ as $t^{-1}$. We analyse the diffusion along the spine and into the teeth and show that the walk...