output
20062026
most citedDistance-IoU Loss: Faster and Better Learning for Bounding Box Regression

961 citations

Showing 2026Show all

13 papers · 1 filter

physics.atm-clus2026

Reflections on future problems in cluster science

K. Hansen, V. V. Kresin, R. Alhyder +22

This article is a collection of contributions from speakers at the 2025 DEAMN [Dynamics of Electrons in Atomic and Molecular Nanoclusters] workshop at the Majorana Centre in Erice.…

cs.RO2026

Unleashing the Agility of Wheeled-Legged Robots for High-Dynamic Reflexive Obstacle Evasion

Yongen Zhao, Zihao Xu, Wenzhi Lu +2

Wheeled-legged robots combine the energy efficiency of wheeled locomotion with the terrain adaptability of legged systems, making them promising platforms for agile mobility in com…

physics.flu-dyn202618 cited

Effects of gas diffusion layer thickness on PEM fuel cells with composite foam-rib flow fields

Wei Gao, Qifeng Li, Kai Sun +3

Gas diffusion layers (GDLs) play a crucial role for the performance of proton exchange membrane fuel cells (PEMFCs). The utilization of composite foam-rib flow fields (CFRFFs) can…

cs.CL2026

Data Mixing for Large Language Models Pretraining: A Survey and Outlook

Zhuo Chen, Yuxuan Miao, Supryadi +1

Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream g…

cs.CE202628 cited

FFV-PINN: A Fast Physics-Informed Neural Network with Simplified Finite Volume Discretization and Residual Correction

Chang Wei, Yuchen Fan, Jian Cheng Wong +3

Physics-informed neural networks (PINNs) have emerged as a major research focus. However, today's PINNs encounter several limitations. Firstly, during the construction of the loss…

cs.CV202621 cited

Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classification

Zhong Ji, Liyuan Hou, Xuan Wang +2

Few-shot remote sensing image scene classification (FS-RSISC) aims at classifying remote sensing images with only a few labeled samples. The main challenges lie in small inter-clas…