Introduces free-probability kernels for zero-rollout hyperparameter selection in reservoir computing, reducing simulation costs while maintaining accuracy.

Sara Malacarne, Andrea Ceni, Claudio Gallicchio

Classical time series methods reveal linear models outperform GNNs on benchmarks, questioning dataset discriminative power.

Kenneth Martin, Simon Heilig, Asja Fischer et al.

GBC introduces class-conditional Gaussian feature bridges, improving long-tailed SSL by enforcing geometric consistency and feature interpolation, boosting tail-class accuracy.

Hongyang He, Xinyuan Song, Yan Zhong et al.

Proposes physical-support confidence sets for highly coherent dictionaries, quantifying uncertainty and achieving optimal physical resolution with AEB algorithm.

Guan-Ju Peng

Using PCMCI+ on 105 HSAT datasets, this study uncovers dynamic causal structures of sleep-disordered breathing, highlighting sex and age differences.

Ranveer Singh, Saurabh Mathur, Pranuthi Tenali et al.

Proposes a deterministic algorithm for exact RLCT computation of 2D polynomial models, improving model selection accuracy.

Grégoire Sergeant-Perthuis, Elias Tsigaridas, Jules Tsukahara

SAE-Xplainers combines geographic modulation and rule-based models to enhance interpretability of extreme weather event predictions, improving reconstruction and understanding.

Hugo Porta, Emanuele Dalsasso, Chang Xu et al.

Proposes a finite-horizon input–state–output model for AdamW, revealing delayed gradient effects with high accuracy.

Kang Liu, Suyan Li

This paper reveals fundamental limits of time-uniform self-normalized bounds in discounted least squares, providing counterexamples and correction strategies.

Yi-Shan Wu

MeanFlow-Transfer and CAMF achieve fast domain adaptation with limited data, improving FID by 29%.

Yara Bahram, Zahra Dehghani, Mélodie Desbos et al.

GC-OPD introduces group-normalized verifier rewards and relative advantage credit assignment, boosting long-context reasoning scores from 29.08 to 40.47 on five benchmarks.

Zhu Zhang, Jixun Wang, Xiaoang Xu et al.

MDTIM model discretizes time series for imputation, achieving 30% accuracy improvement.

Dongbin Kim, Seungyun Lee, Geonwoo Shin et al.

Introduces Penrose tensor notation mapped to PyTorch einsum, enhancing interpretability and reproducibility of neural architectures.

Pietro Barbiero

Introducing data co-observation as a third key factor in continual learning, quantifying its impact on model generalization beyond forgetting.

Timm Hess, Abhishek Jha, Gido M. van de Ven et al.

RP1 learns multi-step plan improvement rules via reinforcement, achieving near-perfect success with 1/1000 model rollouts and 67× faster inference in robotic tasks.

Armin Sommer, Jannik Schilling

DAEI combines residual denoising autoencoder with generative inversion, achieving 154% BLEU improvement in noisy text embedding inversion.

Yubo Wang, Shujie Cui, James Bailey et al.

Proposes Bayesian Optimization-based sampling schedule (OYS) that reduces steps to 5 while retaining 89%-94% of quality, greatly lowering inference costs.

Travis Zhang, Christian Belardi, Justin Lovelace et al.

Proposes the Effectiveness–Losslessness Framework for tokenization, emphasizing coordinate systems in symbolic music for improved predictive compression.

Yi Wang

TSFT optimizes budget allocation via performance prediction and ILP, boosting task coverage by 2-3× in CRL under limited resources.

Jianan Zhou, Jung-Hoon Cho, Tianyue Zhou et al.

LACE leverages cheap auxiliary signals within a local control variate framework to efficiently estimate conditional language model performance with limited gold labels.

Zhi Zhang, Lingfeng Lyu, Yue Kang et al.