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…
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…
arXiv:2505.03595v3 Announce Type: replace Abstract: High-dimensional partial differential equations (PDEs) arise in diverse scientific and engineering applications but remain computationally intractable due to the curse of dimensionality. Traditional numerical methods struggle with the exponential growth in computational complexity, particularly on…
arXiv:2509.08180v3 Announce Type: replace Abstract: The Domain Mixed Unit (DMU) is a new neural arithmetic unit that learns a single parameter gate that mixes between log-space and linear-space representations while performing either addition (DMU add) or subtraction (DMU sub). Two…
arXiv:2509.10506v1 Announce Type: new Abstract: Forecasting product demand in retail supply chains presents a complex challenge due to noisy, heterogeneous features and rapidly shifting consumer behavior. While traditional gradient boosting decision trees (GBDT) offer strong predictive performance on structured data,…
arXiv:2509.10509v1 Announce Type: new Abstract: The stability of recursively trained large language models (LLMs) is a foundational problem for AI safety. Prevailing theory predicts model collapse, a progressive degradation when models are trained on their own output. We challenge this…
arXiv:2509.10503v1 Announce Type: new Abstract: Federated Object Detection (FOD) enables clients to collaboratively train a global object detection model without accessing their local data from diverse domains. However, significant variations in environment, weather, and other domain specific factors hinder performance,…
arXiv:2509.10504v1 Announce Type: new Abstract: Retrosynthesis planning aims to decompose target molecules into available building blocks, forming a synthesis tree where each internal node represents an intermediate compound and each leaf ideally corresponds to a purchasable reactant. However, this tree…
arXiv:2509.10501v1 Announce Type: new Abstract: Zero-inflated data pose significant challenges in precipitation forecasting due to the predominance of zeros with sparse non-zero events. To address this, we propose the Zero Inflation Diffusion Framework (ZIDF), which integrates Gaussian perturbation for smoothing…
arXiv:2509.10500v1 Announce Type: new Abstract: Describing the world behavior through mathematical functions help scientists to achieve a better understanding of the inner mechanisms of different phenomena. Traditionally, this is done by deriving new equations from first principles and careful observations.…
