Budget-efficient scaling law fitting via active experiment selection achieves full dataset performance using only 10% of the budget.

Sijie Li, Shanda Li, Haowei Lin et al.

Using BantuMorph v7, a neural model recovers historical lexical structures in Bantu languages from modern data, confirming 90.9% noun candidates align with Proto-Bantu forms.

Hillary Mutisya, John Mugane

Zero-shot morphological discovery in low-resource Bantu languages via cross-lingual transfer and unsupervised clustering.

Hillary Mutisya, John Mugane

WG-SRC provides operational feature fingerprints for graph datasets using a white-box signal-subspace probe, enhancing node classification accuracy.

Yuchen Xiong, Swee Keong Yeap, Zhen Hong Ban

Evaluates eight Shapley variants' human utility in high-risk settings, revealing misalignment between current metrics and human perception.

Inês Oliveira e Silva, Sérgio Jesus, Iker Perez 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.

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

Abhinaba Basu

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.

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

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

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

Duanyang Yuan, Sihang Zhou, Yanning Hou 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.

Introduces 'sharpness dimension' to explain improved generalization at the edge of stability.

Mario Tuci, Caner Korkmaz, Umut Şimşekli et al.

Proposes Safe EWC and CF-EWC algorithms for safe continual reinforcement learning in non-stationary environments.

Austin Coursey, Abel Diaz-Gonzalez, Marcos Quinones-Grueiro et al.

FASTER method reduces computational cost by early action sample filtering during denoising while maintaining RL performance.

Perry Dong, Alexander Swerdlow, Dorsa Sadigh et al.

Adversarial training enables Vision Transformers to achieve near-zero robust training loss and robust generalization error under moderate perturbation budgets.

Jiaming Zhang, Meng Ding, Shaopeng Fu et al.

Utilizing determinantal point processes for Monte Carlo integration to enhance estimator variance convergence speed.

Guillaume Gautier, Rémi Bardenet, Michal Valko