NeurIPS - arXivDaily 期刊&会议

2510.19887 2025-10-24 q-bio.QM cs.LG

Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discovery

Télio Cropsal, Rocío Mercado

机构 * Chalmers University of Technology and University of Gothenburg（查尔姆斯理工大学和哥德堡大学）

Comments Accepted to the 3rd Workshop on Imageomics: Discovering Biological Knowledge from Images Using AI at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

2510.19854 2025-10-24 eess.IV cs.LG

Multi-Resolution Analysis of the Convective Structure of Tropical Cyclones for Short-Term Intensity Guidance

Elizabeth Cucuzzella, Tria McNeely, Kimberly Wood, Ann B. Lee

机构 * Department of Statistics and Data Science（统计与数据科学系）； Carnegie Mellon University（卡内基梅隆大学）； Department of Atmospheric Sciences and Hydrology（大气科学与水文学系）； University of Arizona（亚利桑那大学）

Comments For Tackling Climate Change with Machine Learning workshop at NeurIPS 2025

2510.11851 2025-10-24 cs.CR cs.CL

Deep Research Brings Deeper Harm

Shuo Chen, Zonggen Li, Zhen Han, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu

机构 * LMU Munich（慕尼黑大学）； Siemens（西门子）； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）； Technical University of Munich (TUM)（慕尼黑技术大学）； AWS AI（亚马逊AI）； Konrad Zuse School of Excellence in Reliable AI (relAI)（Konrad Zuse卓越可靠AI学校）； University of Hong Kong (HKU)（香港大学）； University of Oxford（牛津大学）

Comments Accepted to Reliable ML from Unreliable Data Workshop @ NeurIPS 2025

2506.13688 2025-10-24 cs.LG stat.ML

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

Pulkit Gopalani, Wei Hu

机构 * University of Michigan（密歇根大学）

Comments NeurIPS 2025

2505.20612 2025-10-24 cs.CV cs.CL cs.LG

Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models

Peter Robicheaux, Matvei Popov, Anish Madan, Isaac Robinson, Joseph Nelson, Deva Ramanan, Neehar Peri

机构 * Roboflow ； Carnegie Mellon University（卡内基梅隆大学）

Comments The first two authors contributed equally. This work has been accepted to the Neural Information Processing Systems (NeurIPS) 2025 Datasets & Benchmark Track. Project Page: https://rf100-vl.org/

2502.10297 2025-10-24 cs.LG cs.CL cs.FL

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

Julien Siems, Timur Carstensen, Arber Zela, Frank Hutter, Massimiliano Pontil, Riccardo Grazzi

机构 * University of Freiburg（弗赖堡大学）； ELLIS Institute Tübingen（图宾根ELLIS研究所）； Microsoft Research（微软研究院）； Prior Labs（先驱实验室）； CSML, Istituto Italiano di Tecnologia（CSML，意大利技术研究所）； AI Centre, University College London（伦敦大学学院人工智能中心）

Comments v5: Characterization of DeltaProduct's state-tracking ability. Analysis of hidden state's effective rank. Improved scaling analysis. v6: Added analysis for products of RWKV-7 matrices, v6: Accepted at NeurIPS 2025

2502.05094 2025-10-24 quant-ph cs.LG cs.NA math.NA stat.CO stat.ML

Quantum speedup of non-linear Monte Carlo problems

Jose Blanchet, Yassine Hamoudi, Mario Szegedy, Guanyang Wang

Comments 18 pages; v2: improved writing, changed title, and added lower bound

Journal ref Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025

2410.06300 2025-10-24 cs.LG

SHAP values via sparse Fourier representation

Ali Gorji, Andisheh Amrollahi, Andreas Krause

机构 * ETH Zürich（苏黎世联邦理工学院）

Comments Published in 39th Conference on Neural Information Processing Systems (NeurIPS 2025)