ESPRESSO framework implements scalable keyword search with granular visibility constraints and privacy guarantees in Solid-based environments.

Mohamed Ragab, Faria Ferooz, Mohammad Bahrani et al.

LTBs-KAN enhances KAN efficiency with linear-time B-spline computation.

Eduardo Said Merin-Martinez, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello

DM³-Nav: Fully decentralized multi-agent semantic navigation with multimodal goals, using intent broadcasting and neighbor frontier selection.

Amin Kashiri, Atharva Jamsandekar, Yasin Yazıcıoğlu

An LLM-assisted analysis of 30 multilingual YouTube videos shows that cultural health misinformation defeats prompt-only detection.

Anamta Khan, Ratna Kandala, Deepti et al.

Lsys encoding excels in neural network evolution, achieving a food count of 3802, surpassing Matrix encoding.

Alexander Stuy, Nodin Weddington

EVENT5Ws: A large dataset for open-domain event extraction, manually annotated and statistically verified.

Praval Sharma, Ashok Samal, Leen-Kiat Soh et al.

Introduces WorldMark benchmark using model adapters and control-system metrics to evaluate interactive video world models' response dynamics.

Xiaojie Xu, Zhengyuan Lin, Kang He et al.

VLAA-GUI integrates completeness verification, loop breaking, and online search, boosting GUI automation success to 77.5%.

Qijun Han, Haoqin Tu, Zijun Wang et al.

Behavior Forest method improves travel planning efficiency by 6.67% and 11.82%.

Duanyang Yuan, Sihang Zhou, Yanning Hou et al.

Proposes a biologically-inspired weightlessness mechanism integrating imitation and reinforcement learning for humanoid non-self-stabilizing motions, achieving robust environmental interaction.

Yucheng Xin, Jiacheng Bao, Haoran Yang et al.

Proposed multi-layered hardware-software co-design reduces multimodal model size by 40%, accelerates inference 3.8×, and cuts energy use, enabling edge deployment.

Muhammad Shafique, Abdul Basit, Muhammad Abdullah Hanif et al.

Hyperloop Transformer uses looped architecture and hyper-connections to halve parameters while outperforming depth-matched models.

Abbas Zeitoun, Lucas Torroba-Hennigen, Yoon Kim

Introduces Preconditioned DeltaNet to enhance linear recurrence sequence modeling by considering curvature.

Neehal Tumma, Noel Loo, Daniela Rus

Proposes Near-Future Policy Optimization (NPO), leveraging subsequent checkpoints to improve RLVR, boosting average performance by 4.96%.

Chuanyu Qin, Chenxu Yang, Qingyi Si et al.

ProactAgent combines EXPONEVO and PROACTRL for proactive memory retrieval, achieving 32% higher success rate and 33% fewer rounds on SciWorld.

Yuxuan Cai, Wei Li, Jie Zhou et al.

Proposed an animator-centric skeleton generation framework handling complex inputs with control mechanisms, dataset includes 82,633 models.

Mingze Sun, Cheng Zeng, Jiansong Pei et al.

DNA-CRAFT combines conditional discrete diffusion and Monte Carlo tree search to design cell-type-specific and biologically faithful regulatory DNA.

Animesh Awasthi, Raphael Bednarsky, Moritz Schaefer et al.

SCG-MEM uses schema-constrained generation to significantly improve LoCoMo benchmark performance.

Lei Zheng, Weinan Song, Daili Li et al.

SkillLearnBench evaluates continual skill learning with a three-level framework, showing limited gains across tasks and models.

Shanshan Zhong, Yi Lu, Jingjie Ning et al.

Memora benchmark and FAMA metric evaluate long-term memory in personalized agents, revealing models' struggles with memory consolidation and forgetting over months.

Md Nayem Uddin, Kumar Shubham, Eduardo Blanco et al.