First performance guarantee for score-mismatched diffusion models with explicit dimension dependence; analyzes zero-shot conditional sampling bias and convergence.

Yuchen Liang, Peizhong Ju, Yingbin Liang et al.

SimBa injects simplicity bias to scale deep RL networks, improving sample efficiency and surpassing SOTA with fewer resources.

Hojoon Lee, Dongyoon Hwang, Donghu Kim et al.

nach0-pc integrates point cloud encoder with T5, enabling multi-task 3D molecular generation with high efficiency.

Maksim Kuznetsov, Airat Valiev, Alex Aliper et al.

HyperPG outperforms Euclidean prototypes on CUB-200-2011 with simplified training.

Maximilian Xiling Li, Korbinian Franz Rudolf, Paul Mattes et al.

This paper systematically reviews the roles of large language models in algorithm design, including optimizer, predictor, extractor, and designer, across three stages.

Fei Liu, Yiming Yao, Ping Guo et al.

Mycroft combines feature distance and gradient matching to efficiently select informative data subsets from private sources, boosting model performance with minimal data sharing.

Zain Sarwar, Van Tran, Arjun Nitin Bhagoji et al.

Using irreducible representations and Schur’s lemma, this paper systematically characterizes permutation-equivariant layers, simplifying derivations for DeepSets, graph networks, and weight spaces.

Yonatan Sverdlov, Ido Springer, Nadav Dym

This study systematically evaluates LLMs' ability in time series anomaly detection, revealing they mainly rely on visual understanding with limited reasoning capacity.

Zihao Zhou, Rose Yu

TidalDecode enhances LLM decoding speed by 2.1× using position persistent sparse attention, maintaining near full-attention performance.

Lijie Yang, Zhihao Zhang, Zhuofu Chen et al.

Unsupervised framework using persistent entropy and topological preservation to detect topological changes in MNIST data streams.

Sebastian Basterrech

Introduces Lévy stochastic integrals to analyze discrete diffusion errors, providing the first KL divergence error bound for τ-leaping schemes.

Yinuo Ren, Haoxuan Chen, Grant M. Rotskoff et al.

Proposes EBiEOT framework combining semi-supervised data via inverse entropic OT for conditional distribution maximization.

Mikhail Persiianov, Arip Asadulaev, Nikita Andreev et al.

Introduces Girsanov-based convergence bounds for discrete diffusion models in CTMC framework; KL divergence nearly linear in dimension d.

Zikun Zhang, Zixiang Chen, Quanquan Gu

Gradient-free cutting plane method for deep ReLU networks, providing convergence guarantees and improving sample efficiency in active learning.

Erica Zhang, Fangzhao Zhang, Mert Pilanci

GRAPHEDX: neural set divergence-based estimator for general-cost graph edit distance.

Eeshaan Jain, Indradyumna Roy, Saswat Meher et al.

Introduces human-defined correctness and ICE metrics for data filtering, improving tool-using LLMs performance with high-quality synthetic data.

Shadi Iskander, Nachshon Cohen, Zohar Karnin et al.

This paper establishes theoretical guarantees for in-context learning of linear systems using linear transformers, introducing task diversity as a key condition for out-of-domain generalization.

Frank Cole, Yulong Lu, Wuzhe Xu et al.

Evaluated six Transformer models' music understanding using triplets generated from Audioset ontology.

Yannis Vasilakis, Rachel Bittner, Johan Pauwels

BNEM employs bootstrapped energy matching with diffusion models, reducing variance and improving robustness in high-dimensional sampling.

RuiKang OuYang, Bo Qiang, José Miguel Hernández-Lobato

DEAHES-O combines dynamic weighting, EASGD, and AdaHessian, nearly matching oracle fault-aware training on MNIST while beating fixed-weight baselines.

Yuesheng Xu, Arielle Carr