arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Learning Representations · 会议 · Machine Learning

2026-06-01 至 2026-06-01 共收录 10
2605.31562 2026-06-01 cs.LG

Effective Biological Representation Learning by Masking Gene Expression

通过掩码基因表达实现有效的生物表示学习

Kian Kenyon-Dean, Alina Selega, Ihab Bendidi, Jordan M. Sorokin, Luca Bertinetto, David Errington, Hayley Donnella, Oren Kraus

机构 * Recursion Valence Labs École Normale Supérieure PSL

AI总结 提出自监督模型TxFM,采用掩码自编码方法处理RNA-seq数据,通过消融研究确定关键架构,并在精心策划的DiverseRNA-1.4M数据集上训练,获得优于大规模基础模型的基因表示。

Comments 31 pages, 11 figures. Preprint; presented at ICLR 2026 2nd Workshop on Foundation Models for Science: Real-World Impact and Science-First Design

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.30553 2026-06-01 cs.LG cs.IT math.IT

Destruction is a General Strategy to Learn Generation; Diffusion's Strength is to Take it Seriously; Exploration is the Future

破坏是学习生成的一般策略;扩散的优势在于认真对待它;探索是未来

Pierre-André Noël

机构 * ServiceNow AI Research(ServiceNow AI研究院)

AI总结 本文提出扩散模型作为信息隐藏与猜测框架的一部分,论证其破坏式信息隐藏比手工设计更灵活,尤其在数据稀缺场景有优势,并探讨强化学习技术移植到扩散上下文时的微妙问题及原生探索方向。

Comments Published April 27th, 2026 as an ICLR blogpost https://iclr-blogposts.github.io/2026/blog/2026/destruction/

Journal ref Noël, Piere-André. "Destruction is a General Strategy to Learn Generation; Diffusion's Strength is to Take it Seriously; Exploration is the Future", ICLR Blogposts, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.30387 2026-06-01 cs.LG cs.AI cs.CV eess.SP

Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification

基于小波图像变换和频谱流匹配的功能磁共振时间序列生成用于脑疾病识别

Hwa Hui Tew, Junn Yong Loo, Fang Yu Leong, Julia K. Lau, Ding Fan, Hernando Ombao, Raphaël C. -W. Phan, Chee Pin Tan, Chee-Ming Ting

机构 * School of Information Technology, Monash University Malaysia(墨尔本大学马来西亚分校信息科技学院) School of Engineering, Monash University Malaysia(墨尔本大学马来西亚分校工程学院) Statistics Program, King Abdullah University of Science and Technology(国王阿卜杜勒·阿齐兹大学科学与技术学院统计学项目)

AI总结 提出双频谱流匹配(DSFM)框架,通过离散小波变换和离散余弦变换对BOLD信号进行双频表示,结合频谱流匹配生成类条件余弦频率表示,再经逆变换重建生理上合理的时域BOLD信号,以改善下游脑网络分类。

Comments Accepted at the Fourteenth International Conference on Learning Representations (ICLR 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.06074 2026-06-01 cs.LG cs.NA math.NA

Scalable Mechanistic Neural Networks for Differential Equations and Machine Learning

可扩展的机械神经网络用于微分方程和机器学习

Jiale Chen, Dingling Yao, Adeel Pervez, Dan Alistarh, Francesco Locatello

机构 * Institute of Science and Technology Austria (ISTA)(奥地利科学技术研究所)

AI总结 提出可扩展机械神经网络(S-MNN),通过线性化序列长度的计算和空间复杂度,实现高效建模长期动力学,保持精度和可解释性。

Comments Published as a conference paper at the Thirteenth International Conference on Learning Representations (ICLR 2025): https://openreview.net/forum?id=Oazgf8A24z

Journal ref International Conference on Learning Representations, 2025, pp. 10018-10039

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21558 2026-06-01 cs.AI

Reliable Self-Improvement Training by Verifying Reasoning, Not Just Answers

可靠的自改进训练:验证推理过程,而不仅仅是答案

Xinyu Zhang

机构 * Anyscale

AI总结 针对自改进训练中因依赖最终答案正确性导致推理错误累积的问题,提出VSI框架,通过步骤级结构验证(如符号计算检查算术步骤)筛选训练数据,在GSM8K上实现持续准确率提升(80.5%→91.0%)。

Comments Accepted at ICLR 2026 Workshop LLM Reasoning. 10 pages, 3 figures, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.01186 2026-06-01 cs.LG cs.AI

The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics

高斯头OFL系列:基于客户端全局统计的一次性联邦学习

Fabio Turazza, Marco Picone, Marco Mamei

机构 * Department of Sciences and Methods for Engineering(工程科学与方法系) Artificial Intelligence Research and Innovation Center(人工智能研究与创新中心) University of Modena and Reggio Emilia(摩德纳和雷吉奥艾米利亚大学)

AI总结 提出高斯头OFL系列方法,通过客户端仅传输每类计数和一二阶矩,服务器利用闭式高斯头、FisherMix和Proto-Hyper三种组件构建模型,实现严格无数据的一次性联邦学习,在强非独立同分布下达到最先进鲁棒性和准确性。

Comments Accepted at the International Conference on Learning Representations (ICLR) 2026 - Final Version

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20853 2026-06-01 eess.AS cs.CL cs.SD

Beyond Hearing: Learning Task-Agnostic ExG Representations from Earphones via Physiology-Informed Tokenization

超越听觉:通过生理学启发的标记化从耳机学习任务无关的ExG表示

Hyungjun Yoon, Seungjoo Lee, Yu Yvonne Wu, Xiaomeng Chen, Taiting Lu, Freddy Yifei Liu, Taeckyung Lee, Hyeongheon Cha, Haochen Zhao, Gaoteng Zhao, Dongyao Chen, Cecilia Mascolo, Sung-Ju Lee, Lili Qiu

机构 * KAIST(韩国科学技术院) Carnegie Mellon University(卡内基梅隆大学) University of Cambridge(剑桥大学) Shanghai Jiao Tong University(上海交通大学) Pennsylvania State University(宾夕法尼亚州立大学) UCLA(加州大学洛杉矶分校) Northwest University(北华大学) University of Texas at Austin(德克萨斯大学奥斯汀分校) Microsoft Research(微软研究院)

AI总结 提出一种基于耳机的生理学启发的多频带标记化方法(PiMT),通过无干扰的日常ExG数据采集和重建任务学习鲁棒表示,实现跨多种任务(包括五种人类感官)的通用ExG监测。

Comments Accepted to ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16138 2026-06-01 cs.LG stat.ML

Expert Merging in Sparse Mixture of Experts with Nash Bargaining

基于纳什谈判的稀疏混合专家模型专家合并

Dung V. Nguyen, Anh T. Nguyen, Minh H. Nguyen, Luc Q. Nguyen, Shiqi Jiang, Ethan Fetaya, Linh Duy Tran, Gal Chechik, Tan M. Nguyen

机构 * Department of Mathematics, National University of Singapore(新加坡国立大学数学系) Viettel AI, Viettel Group(越南电信AI部门) Faculty of Mathematics and Informatics, Hanoi University of Science and Technology(河内科学技术大学数学与信息学系) Bar Ilan University, Israel(以色列巴伊兰大学) AI Imaging Team, Data Solution Department, FPT Software Japan(日本FPT软件数据解决方案部门AI成像团队)

AI总结 针对稀疏混合专家模型缺乏原则性加权机制的专家合并问题,提出基于纳什谈判的NAMEx框架,实现专家间更平衡高效的协作,在多项任务中优于现有方法。

Comments 10 pages in the main text. ICLR 2026 Poster

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.02060 2026-06-01 cs.AI cs.LG

ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection

ReTabAD: 恢复表格异常检测中语义上下文的基准

Sanghyu Yoon, Dongmin Kim, Suhee Yoon, Ye Seul Sim, Seungdong Yoa, Hye-Seung Cho, Soonyoung Lee, Hankook Lee, Woohyung Lim

机构 * LG AI Research, Seoul, South Korea(LG人工智能研究实验室,首尔,韩国) Sungkyunkwan University, Suwon, South Korea(成均馆大学,水原,韩国)

AI总结 针对现有表格异常检测基准缺乏语义上下文的问题,提出ReTabAD基准,通过丰富结构化文本元数据并集成零样本LLM框架,验证了语义上下文能提升检测性能和可解释性。

Comments Accepted to ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
1709.08894 2026-06-01 stat.ML cs.LG

On the regularization of Wasserstein GANs

关于Wasserstein GANs的正则化

Henning Petzka, Asja Fischer, Denis Lukovnikov

机构 * Fraunhofer Institute IAIS(弗劳恩霍夫研究所IAIS) Department of Computer Science, University of Bonn(波恩大学计算机科学系)

AI总结 本文研究Wasserstein GANs中Lipschitz约束的正则化方法,通过理论分析和实验证明使用较弱的正则化项优于权重裁剪。

Comments Published as a conference paper at ICLR 2018. * Henning Petzka and Asja Fischer contributed equally to this work (11 pages +13 pages appendix)

详情

展开后加载摘要…

URL PDF HTML 收藏