Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges when handling complex prompt, particularly those involving multiple subjects with distinct attributes. In...
Diffusion models have emerged as a powerful class of generative models, capable of producing high-quality images by mapping noise to a data distribution. However, recent findings suggest that image likelihood does not align with perceptual quality: h...
Contemporary social media networks can be viewed as a break to the early two-step flow model in which influential individuals act as intermediaries between the media and the public for information diffusion. Today's social media platforms enable user...
We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. Howe...
Recent innovations on text-to-3D generation have featured Score Distillation Sampling (SDS), which enables the zero-shot learning of implicit 3D models (NeRF) by directly distilling prior knowledge from 2D diffusion models. However, current SDS-based...
Consider a finite system of competing Brownian particles on the real line. Each particle moves as a Brownian motion, with drift and diffusion coefficients depending only on its current rank relative to the other particles. A triple collision occurs i...
Consider a finite system of competing Brownian particles on the real line. Each particle moves as a Brownian motion, with drift and diffusion coefficients depending only on its current rank relative to the other particles. We find a sufficient condit...
We discuss some stochastic spatial generalizations of the Lotka--Volterra model for competing species. The generalizations take the forms of spin systems on general discrete sets and interacting diffusions on integer lattices. Methods for proving coe...
Consider a finite system of rank-based competing Brownian particles, where the drift and diffusion of each particle depend only on its current rank relative to other particles. We present a simple sufficient condition for absence of multiple collisio...
Friction is the force resisting relative motion of objects. The force depends on material properties, loading conditions and external factors such as temperature and humidity, but also contact aging has been identified as a primary factor. Several ag...
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (⭐ 3091)
A graph based matching is used to construct aggregation for algebraic multigrid. Effects of inexact coarse grid solve is analyzed numerically for a highly discontinuous convection diffusion coefficient matrix and problems from Florida matrix market c...
Diffusion Transformers have demonstrated remarkable capabilities in visual synthesis, yet they often struggle with high-level semantic reasoning and long-horizon planning. This limitation frequently leads to visual hallucinations and mis-alignments w...
Slate generation is a common task in streaming and e-commerce platforms, where multiple items are presented together as a list or ``slate''. Traditional systems focus mostly on item-level ranking and often fail to capture the coherence of the slate a...
Home Made Diffusion Models (⭐ 193)
PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech) (⭐ 247)
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code (⭐ 4744)
We make a further step in the open problem of unisolvence for unsymmetric Kansa collocation, proving that the MultiQuadric Kansa method with fixed collocation points and random fictitious centers is almost surely unisolvent, for stationary convection...
Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe generation...
We consider Hermitian and symmetric random band matrices $H$ in $d \geq 1$ dimensions. The matrix elements $H_{xy}$, indexed by $x,y \in Λ\subset \Z^d$, are independent, uniformly distributed random variables if $\abs{x-y}$ is less than the band wid...