An early adopter or lighthouse customer is an early customer of a given company, product, or technology. The term originates from Everett M. Rogers' Diffusion
Recently, machine learning has made a significant impact on de novo drug design. However, current approaches to creating novel molecules conditioned on a target protein typically rely on generating molecules directly in the 3D conformational space, w...
Video generation has witnessed remarkable progress with the advent of deep generative models, particularly diffusion models. While existing methods excel in generating high-quality videos from text prompts or single images, personalized multi-subject...
Robotic food scooping is a critical manipulation skill for food preparation and service robots. However, existing robot learning algorithms, especially learn-from-demonstration methods, still struggle to handle diverse and dynamic food states, which...
Remote sensing change detection is crucial for understanding the dynamics of our planet's surface, facilitating the monitoring of environmental changes, evaluating human impact, predicting future trends, and supporting decision-making. In this work,...
Perturbations in a non-normal system can grow transiently even if the system is linearly stable. If this transient growth is sufficiently large, it can trigger self-sustained oscillations from small initial disturbances. This has important practical...
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior (⭐ 3003)
[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors (⭐ 2994)
[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior (⭐ 4032)
[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution (⭐ 2638)
In bistable systems, the stability of front structures often influences the dynamics of extended patterns. We show how the combined effect of an instability to curvature modulations and proximity to a pitchfork front bifurcation leads to spontaneou...
Predictive manipulation has recently gained considerable attention in the Embodied AI community due to its potential to improve robot policy performance by leveraging predicted states. However, generating accurate future visual states of robot-object...
I consider ageing behaviour in two exactly solvable reaction-diffusion systems. Ageing exponents and scaling functions are determined. I discuss in particular a case in which the equality of two critical exponents, known from systems with detailed...
Recent advances in large models have significantly advanced image-to-3D reconstruction. However, the generated models are often fused into a single piece, limiting their applicability in downstream tasks. This paper focuses on 3D garment generation,...
New Target-Ion Source Systems combining a target and a catcher material are developed in the radioactive beam community, in particular at GANIL, in order to maximise the yield of very short lived atoms by minimizing the atom-to-ion transformation tim...
In this work, we explain the underlying interaction mechanisms which govern students' influence on each other in Massive Open Online Courses (MOOCs). Specifically, we outline different ways in which students can be negatively exposed to their peers o...
Tropical cyclone (TC) forecasting is crucial for disaster preparedness and mitigation. While recent deep learning approaches have shown promise, existing methods often treat TC evolution as a series of independent frame-to-frame predictions, limiting...
We study the problem of precisely swapping objects in videos, with a focus on those interacted with by hands, given one user-provided reference object image. Despite the great advancements that diffusion models have made in video editing recently, th...
We develop a Schumpeterian quality-ladder spatial model in which innovation arrivals depend on regional knowledge spillovers. A parsimonious reduced-form diffusion mechanism induces the convergence of regions' average distance to the global frontier...
We prove that for a general diffusion process, certain assumptions on its behavior \emph{only within a fixed open subset} of the state space imply the existence and sub-Gaussian type off-diagonal upper bounds of the \emph{global} heat kernel on the f...