Introduced a passage-aware structural mapping method for RGB-D Visual SLAM to effectively detect doors and traversable openings.

Ali Tourani, Miguel Fernandez-Cortizas, Saad Ejaz et al.

Energy-Arena is a dynamic benchmarking platform enhancing transparency and comparability in energy forecasting.

Max Kleinebrahm, Jonathan Berrisch, Philipp Eiser et al.

SciCrafter evaluates AI's discovery-to-application ability in Minecraft; current models achieve only 26% success.

Zhou Ziheng, Huacong Tang, Jinyuan Zhang et al.

MoT-HRA framework learns human-intention priors from large-scale demonstrations, enhancing motion plausibility and control robustness in robotic manipulation.

Yifan Xie, YuAn Wang, Guangyu Chen et al.

Radar-KISSICP and Radar-IMU improve trajectory estimation in off-road environments.

Shaunak Kolhe, Peng Jiang, Maggie Wigness et al.

ACO-MoE recovers 95.3% performance under dynamic perturbations, enhancing visual RL robustness.

Zhengru Fang, Yu Guo, Fei Liu et al.

Integrating data-driven computational design with feedback-driven co-robotic fabrication for material reuse in architecture.

Arash Adel, Daniel Ruan, Ruxin Xie

DenSNet enhances molecular dynamics by predicting electronic structures using equivariant neural networks and a $Δ$-learning strategy.

Mihail Bogojeski, Muhammad R. Hasyim, Leslie Vogt-Maranto et al.

Efficient learning by implicit exploration in bandit problems with side observations, achieving near-optimal regret guarantees.

Tomas Kocak, Gergely Neu, Michal Valko et al.

Deployment-aligned low-precision NAS enhances spaceborne edge AI performance, achieving 0.826 mIoU.

Parampuneet Kaur Thind, Vaibhav Katturu, Giacomo Zema et al.

Generate complex path vector fields using Score-Induced Guiding Vector Field (SGVF) to enhance robotic navigation.

Zirui Chen, Shiliang Guo, Shiyu Zhao

SeaEvo enhances algorithm discovery via strategy space evolution, achieving 21% improvement in system optimization tasks.

Sichun Luo, Yi Huang, Haochen Luo et al.

OS-SPEAR toolkit systematically analyzes OS agents' safety, performance, efficiency, and robustness, revealing trade-offs between efficiency and safety.

Zheng Wu, Yi Hua, Zhaoyuan Huang et al.

A divergence-based method outperforms traditional weighting in small sample scenarios.

Olav Benjamin Vassend

Improving tabular retrieval robustness via representational stability using centroid averaging to reduce format-specific variance.

Kushal Raj Bhandari, Adarsh Singh, Jianxi Gao et al.

DeepTaxon: An interpretable retrieval-augmented multimodal framework significantly improves species identification and discovery accuracy.

Jiawei Wang, Ming Lei, Yaning Yang et al.

Introduces SSL, a three-layer structured skill representation, improving skill retrieval and risk assessment with 15-20% performance gains.

Qiliang Liang, Hansi Wang, Zhong Liang et al.

TCOD employs a progressive trajectory length schedule to stabilize on-policy distillation in multi-turn autonomous agents, boosting success rate by up to 18 points.

Jiaqi Wang, Wenhao Zhang, Weijie Shi et al.

Proposes Sliced-Regularized OT (SROT), leveraging smoothened SOT plans to improve OT approximation with a Sinkhorn-style algorithm.

Khai Nguyen

ZenBrain is a 7-layer neuroscience-inspired memory architecture integrating 15 mechanisms, significantly improving QA and cross-session reasoning with 91.3% oracle accuracy at 1/106 query cost.

Alexander Bering