Data Analysis

Debajyoti Sengupta, Matthew Leigh, John Andrew Raine et al.

This addresses the challenge of detecting rare signals in high-energy physics experiments, offering a novel method for background estimation that could impact particle physics research.

Ziyu Ye, Rishabh Agarwal, Tianqi Liu et al.

This addresses scalability bottlenecks in RL post-training for LLMs, representing a paradigm shift rather than an incremental improvement.

Koen Minartz, Fleur Hendriks, Simon Martinus Koop et al.

This work addresses the problem of designing efficient urban infrastructure and ensuring safe crowd management, offering a novel paradigm for data-driven scientific discovery in crowd dynamics.

Apivich Hemachandra, Gregory Kang Ruey Lau, See-Kiong Ng et al.

This work addresses the problem of costly and sequential experimental design in science and engineering by providing a more efficient and effective method for optimizing design parameters prior to data collection.

Daniel Maître, Vishal S. Ngairangbam, Michael Spannowsky

This work addresses the need for more efficient and powerful tools in high-energy physics analysis, offering a novel synergy between physics-informed methods and deep learning for probing beyond the Standard Model.

Roger Guimera, Marta Sales-Pardo

This work addresses the need for more rigorous and theoretically grounded methods in symbolic regression, offering a solution for physicists and researchers seeking automated equation discovery with improved reliability over heuristic approaches.

Lorenzo Livi

This provides theoretical foundations for understanding temporal learning limits in RNNs, which is important for researchers working on sequence modeling.

Zhuo Chen, Oriol Mayné i Comas, Zhuotao Jin et al.

This provides a principled foundation for designing more efficient architectures with stronger long-context capabilities, potentially benefiting natural language processing and beyond.

Aaron J. Gutknecht, Fernando E. Rosas, David A. Ehrlich et al.

This work addresses fundamental limitations in analyzing complex interactions in systems like neural networks, offering broad opportunities for theoretical and empirical advancements.

Wei Liu, Kiran Bacsa, Loon Ching Tang et al.

This work addresses the problem of creating accurate and interpretable models for complex nonlinear dynamics in science and engineering, offering a novel method for symbolic discovery.

X. San Liang, Dake Chen, Renhe Zhang

This work addresses the problem of making causality analysis quantitative and efficient for researchers in AI and various scientific disciplines, representing a foundational advancement rather than an incremental step.

Selim Romero, Shreyan Gupta, Robert S. Chapkin et al.

This work addresses the challenge of modeling intercellular communication in complex biological systems, shifting from static database reliance to data-driven learning, with potential applications in single-cell biology.

Wassim Tenachi, Rodrigo Ibata, Foivos I. Diakogiannis

This addresses the challenge of robust symbolic regression in physics and engineering applications where units are known, offering improved noise resilience.

Zhuo-Yang Song, Qing-Hong Cao, Ming-xing Luo et al.

This work attempts to establish a foundational macroscopic dynamics theory for complex AI systems, potentially elevating AI agent studies from engineering practices to a predictable science, though it is incremental in providing initial evidence for such a framework.

Marios Andreou, Nan Chen, Erik Bollt

This addresses a bottleneck in causal inference for complex systems like those with intermittency and extreme events, offering a novel framework with broad applications.

Eric Volkmann, Alena Brändle, Daniel Durstewitz et al.

This solves a key bottleneck for applying state space models to neuroscience data, allowing automated inference of brain dynamics without handcrafted models.

Hyungjoon Soh, Junghyo Jo

This addresses the need for better alignment models in sequence-to-sequence tasks like text-to-speech, offering a drop-in replacement that enhances performance for frame-synchronous targets.

Hao Xu, Yuntian Chen, Dongxiao Zhang

This work addresses the need for generalizable and interpretable constitutive models in solid mechanics and materials science, offering a novel approach to replace traditional empirical methods.

Jack Y. Araz, Anja Beck, Méril Reboud et al.

This work addresses the problem of likelihood communication for high-energy physicists, providing an incremental solution.

Amir Jahangiri, Tatiana Agback, Ulrika Brath et al.

This addresses the challenge of distinguishing overlapping peaks and noise in NMR spectroscopy for researchers in structural biology and chemistry, representing a novel method rather than an incremental improvement.