Comparative analysis of AV-human and AI agent-human interactions, proposing relational archetype taxonomy.

Antoni Lorente, Amin Oueslati, Robin Staes-Polet

Introduced TAWin method using WPAUC to optimize RL-based recommenders, enhancing Top-K performance.

Wentao Shi, Qifan Wang, Chen Chen et al.

Decoding high-dimensional finger motion using Riemannian features and RNNs, TRR achieves 9.79° error on EMG-FK dataset.

Martin Colot, Cédric Simar, Guy Cheron et al.

FedSPDnet outperforms traditional methods on EEG datasets using ProjAvg and RLAvg strategies, enhancing F1 score and robustness.

Thibault Pautrel, Florent Bouchard, Ammar Mian et al.

Point&Grasp enables flexible selection of out-of-reach objects through probabilistic cue integration, improving accuracy and speed.

Xuejing Luo, Hee-Seung Moon, Christian Holz et al.

HubRouter replaces O(n^2) attention with O(nM) routing for efficiency gains.

Abhinaba Basu

AgentSearchBench improves agent search ranking quality using execution signals, bridging the gap between semantics and performance.

Bin Wu, Arastun Mammadli, Xiaoyu Zhang et al.

SQUEAK algorithm achieves low space complexity for kernel ridge regression using unnormalized ridge leverage scores.

Daniele Calandriello, Alessandro Lazaric, Michal Valko

Pliable Rejection Sampling (PRS) learns the proposal distribution using kernel estimation, ensuring high-probability i.i.d. sampling.

Akram Erraqabi, Michal Valko, Alexandra Carpentier et al.

Proposed Structural Entropy-Guided Decoupled (SEGD) framework effectively separates multiple degradations, improving infrared image quality with fewer parameters.

Pu Li, Huafeng Li, Yafei Zhang et al.

LeHome simulation environment achieves high-fidelity manipulation of deformable objects in household scenarios using PBD and FEM.

Zeyi Li, Yushi Yang, Shawn Xie et al.

MuDABench uses a multi-agent workflow for analytical QA across documents, significantly improving accuracy.

Zhanli Li, Yixuan Cao, Lvzhou Luo et al.

Proposes a co-evolutionary theory of human-AI coexistence with a dynamic system model emphasizing mutualism and governance.

Somyajit Chakraborty

UniSonate model generates speech, music, and sound effects via text instructions with a TTS WER of 1.47%.

Chunyu Qiang, Xiaopeng Wang, Kang Yin et al.

Proposes a complementarity fusion method for semantic and collaborative views, avoiding global alignment limitations to enhance recommender systems.

Maolin Wang, Dongze Wu, Jianing Zhou et al.

ResRank enhances retrieval efficiency and effectiveness via residual passage compression and end-to-end joint training.

Xiaojie Ke, Shuai Zhang, Liansheng Sun et al.

SharpAP significantly enhances the transferability of poisoning attacks on recommender systems, showing improved performance across multiple datasets.

Junsong Xie, Yonghui Yang, Pengyang Shao et al.

ReCast framework improves Pass@1 by 36.6% in generative recommendation, optimizing sparse-hit signals.

Peiyan Zhang, Hanmo Liu, Chengxuan Tong et al.

dWorldEval uses a discrete diffusion world model for scalable robotic policy evaluation, outperforming WorldEval and others.

Yaxuan Li, Zhongyi Zhou, Yefei Chen et al.

Concave statistical utility maximization bandits using influence-function gradients.

Matías Carrasco, Alejandro Cholaquidis