Prépublication
· 2026 arXiv
EN
Effectively preparing for changes in extreme flooding requires understanding present and future rainfall extremes with return periods up to $\sim$100-1000 years, including changes in intensity, spatial structure at km-scale and sub-daily temporal variability....
Henry Addison, Elizabeth J. Kendon et al.
#physics.ao-ph
Prépublication
· 2026 arXiv
EN
Accurate real-time forecasting of atmospheric pollutants is essential for reducing exposure risks and improving public health. Traditional numerical forecasting systems suffer from incomplete parameterizations, uncertain inputs, and high computational cost. Ex...
Yiheng Wang, Kai Zheng et al.
#physics.ao-ph
Prépublication
· 2026 arXiv
EN
Meteorological downscaling is crucial for high-resolution regional climate forecasting and disaster early warning. While neural operators have emerged as a promising paradigm for modeling complex spatiotemporal mappings, existing frameworks often struggle with...
Yiqiang Ye, Yichi Wang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
A mechanistic interpretation for baroclinic normal mode instability with exponential growth is the interaction arising from Counter-propagating Rossby Waves (CRWs), where pairs of CRWs phase-lock and interfere constructively. On the other hand, an arbitrary in...
J. Yin, N. Harnik et al.
#physics.flu-dyn
Prépublication
· 2026 arXiv
EN
Radiance-based retrievals and data assimilation require radiative transfer models (RTMs) to simulate radiances and quantify their sensitivities to atmospheric and surface conditions. Conventional RTMs often rely on separately maintained forward, tangent-linear...
Zeting Li, Wei Han et al.
#physics.ao-ph
Prépublication
· 2026 arXiv
EN
AI weather prediction models are often regarded as black boxes. Despite their impressive skill, there is little understanding of how the input data is processed during inference to produce the forecast. This limitation arises from the use of high-dimensional l...
Matthias Beylich, Kirsten I. Tempest et al.
#physics.ao-ph
Prépublication
· 2026 arXiv
EN
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks shows that simply increasing the inferenc...
Yu Zhou, Cheng-Fu Yang et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
While LLM agents can generate visually plausible CAD assemblies, these designs often fail to fulfill their intended physical functions. We study functional CAD design, a setting where agents interpret underspecified requests to construct and iteratively revise...
Wenqian Zhang, Yangyi Huang et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
Multimodal reinforcement learning with verifiable rewards (RLVR) provides reliable task-level supervision, yet offers limited guidance for localizing errors in visual reasoning. On-policy self-distillation (OPSD) complements this supervision with dense token-l...
Shiao Xie, Siyu Chen et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
Reinforcement learning enables mobile robots to make fast and scalable navigation decisions in constrained human-shared environments. However, directly extending single-robot approaches to multi-robot settings often fails to ensure safety and efficiency, espec...
Zehao Wang, Jianpeng Yao et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a five-axis metric: First-Attempt Performance, Efficiency, Succ...
Zekai Li, Jiayi Yu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As a trajectory unfolds, different stages...
Rui Shi, Xunjian Yin et al.
#cs.LG