paper-with-me

홈 › Papers

CaDrift: A Time-dependent Causal Generator of Drifting Data Streams

2026-02-23 · Eduardo V. L. Barboza, Jean Paul Barddal, Robert Sabourin, Rafael M. O. Cruz arxiv

This work presents Causal Drift Generator (CaDrift), a time-dependent synthetic data generator framework based on Structural Causal Models (SCMs). The framework produces a virtually infinite combination of data streams with controlled shift events and time-dependent data, making it a tool to evaluate methods under evolving data. CaDrift synthesizes various distributional and covariate shifts by drifting mapping functions of the SCM, which change underlying cause-and-effect relationships between features and the target. In addition, CaDrift models occasional perturbations by leveraging interventions in causal modeling. Experimental results show that, after distributional shift events, the accuracy of classifiers tends to drop, followed by a gradual retrieval, confirming the generator's effectiveness in simulating shifts. The framework has been made available on GitHub.

📄 PDF Abstract BibTeX arXiv:2602.20329

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Receding-Horizon Control via Drifting Models

2026-04-06 · Daniele Foffano, Alessio Russo, Alexandre Proutiere arxiv

We study the problem of trajectory optimization in settings where the system dynamics are unknown and it is not possible to simulate trajectories through a surrogate model. When an offline dataset of trajectories is avai…

DriftXpress: Faster Drifting Models via Projected RKHS Fields

2026-05-12 · Ali Falahati, Elliot Creager, Gautam Kamath, Shubhankar Mohapatra arxiv

Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative denoising process in diffusion models w…

Drifting Objectives for Refining Discrete Diffusion Language Models

2026-05-19 · Daisuke Oba, Hiroki Furuta, Naoaki Okazaki arxiv

Discrete diffusion language models (DDLMs) generate text by iteratively denoising categorical token sequences, while recent drifting methods for continuous generators suggest that part of this sampling-time correction ca…

Generative Modeling via Drifting

2026-02-04 · Mingyang Deng, He Li, Tianhong Li, Yilun Du 외 arxiv

Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example i…

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry

2026-05-31 · Zemin Yang, Yaoyu He, Yiming Zhong, Yuhao Zhang 외 arxiv

Generative action policies based on diffusion or flow matching excel in behavior cloning, yet their iterative sampling is prohibitive for high-frequency robot control. While recent one-step formulations alleviate this la…