Missing value imputation is a fundamental task in machine learning, with most existing methods assuming that all missing entries correspond to unobserved regular values. In many real-world datasets, however, missingness may arise from two distinct sources: some entries are meaningfully missing (intrinsically absent and semantically valid), while others are missing due to the observation process and should be imputed.
arXiv:2606. 05073v1 Announce Type: new Abstract: Missing value imputation is a fundamental task in machine learning, with most existing methods assuming that all missing entries correspond to unobserved regular values.
By Lixing Zhang, Yidong Ouyang, Weifu Li, Shixiang Zhu, Guang Cheng, Liyan Xie
arXiv:2602. 07875v3 Announce Type: replace Abstract: Generating tabular data under conditions is critical to applications requiring precise control over the generative process.
By Aditya Shankar, Yuandou Wang, Rihan Hai, Lydia Y. Chen
arXiv:2607. 28698v1 Announce Type: new Abstract: Flow matching assumes fully observed training data, which many real-world applications rarely provide.
By Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
arXiv:2512. 20963v3 Announce Type: replace Abstract: Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective.
By Zekai Zhang, Xiao Li, Xiang Li, Lianghe Shi, Meng Wu, Molei Tao, Qing Qu
arXiv:2607. 16685v1 Announce Type: cross Abstract: Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data.
By Jin Su, Yuan Gao, Yong Zhou, Jian Huang
arXiv:2510. 02625v5 Announce Type: replace Abstract: Missing data in tabular datasets forces practitioners into a hard choice: deploy a general-purpose imputer that may perform poorly for the problem at hand, or wait for someone to design a specialized algorithm.
By Jacob Feitelberg, Dwaipayan Saha, Kyuseong Choi, Zaid Ahmad, Anish Agarwal, Raaz Dwivedi
arXiv:2509. 09960v2 Announce Type: replace-cross Abstract: Synthetic tabular data generation is increasingly essential in machine learning, supporting downstream applications when real-world, high-quality tabular data is insufficient.
By Mingxuan Jiang, Keyang Chen, Yongxin Wang, Yongsheng Zhao, Ziyue Dai, Yicun Liu, Zeping Li, Qiuyang Zhang, Hongyi Nie, Hongbin Zhu, Sen Liu, Guangnan Ye, Hongfeng Chai
arXiv:2606. 03212v1 Announce Type: new Abstract: Low-rank tensor decomposition (TD) is usually effective on clean, fully observed data, but it often degrades under severe missingness or noise.
By Zerui Tao, Qibin Zhao
arXiv:2606. 31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points.
By Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Marco Grangetto, Stephan Alaniz
arXiv:2506. 01544v2 Announce Type: replace Abstract: We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient and accurate individualized imputation and forecasting.
By Batuhan Koyuncu, Rachael DeVries, Ole Winther, Isabel Valera