Archives AI News

Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games

arXiv:2506.02849v2 Announce Type: replace-cross Abstract: We address the problem of agile 1v1 quadrotor pursuit-evasion, where a pursuer and an evader learn to outmaneuver each other through reinforcement learning (RL). Such settings face two major challenges: non-stationarity, since each agent’s evolving…

Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion

arXiv:2412.13389v2 Announce Type: replace-cross Abstract: Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image. Existing methods for this highly ill-posed task operate in tightly constrained settings and tend to struggle when applied to images…

A Particle-Flow Algorithm for Free-Support Wasserstein Barycenters

arXiv:2509.11435v1 Announce Type: cross Abstract: The Wasserstein barycenter extends the Euclidean mean to the space of probability measures by minimizing the weighted sum of squared 2-Wasserstein distances. We develop a free-support algorithm for computing Wasserstein barycenters that avoids entropic regularization…

Maximum diversity, weighting and invariants of time series

arXiv:2509.11146v1 Announce Type: cross Abstract: Magnitude, obtained as a special case of Euler characteristic of enriched category, represents a sense of the size of metric spaces and is related to classical notions such as cardinality, dimension, and volume. While the…

A Controllable 3D Deepfake Generation Framework with Gaussian Splatting

arXiv:2509.11624v1 Announce Type: cross Abstract: We propose a novel 3D deepfake generation framework based on 3D Gaussian Splatting that enables realistic, identity-preserving face swapping and reenactment in a fully controllable 3D space. Compared to conventional 2D deepfake approaches that suffer…

Can AI be Auditable?

arXiv:2509.00575v3 Announce Type: replace-cross Abstract: Auditability is defined as the capacity of AI systems to be independently assessed for compliance with ethical, legal, and technical standards throughout their lifecycle. The chapter explores how auditability is being formalized through emerging regulatory…

MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization

arXiv:2509.11361v1 Announce Type: new Abstract: Prompt engineering is crucial for leveraging large language models (LLMs), but existing methods often rely on a single optimization trajectory, limiting adaptability and efficiency while suffering from narrow perspectives, gradient conflicts, and high computational cost.…