ProtoFlow is a new multivariate time series forecasting framework that combines vector‑quantized autoencoding with prototype‑guided flow matching. It maps sequences into a discrete latent space, constructs a structured prior from the learned VQ codebook, and trains a DiT‑based rectified flow to transport samples from this prior to future latent representations conditioned on past observations. By replacing generic Gaussian noise with a learned prototype prior, ProtoFlow eliminates autoregressive rollout mismatch and achieves faster training convergence while delivering superior forecasting performance on benchmark datasets.
By Shibo Feng, Wanjin Feng, Yang Qiu, Deheng Ye, Peilin Zhao, Chunyan Miao
arXiv:2605. 08398v2 Announce Type: replace Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage.
By Rania Briq, Michael Kamp, Ohad Fried, Sarel Cohen, Stefan Kesselheim
arXiv:2608.23551v1 Announce Type: cross
Abstract: Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existi...
By Na Li, Yuchen Jiao, Changxiao Cai, Gen Li
arXiv:2602. 03564v2 Announce Type: replace Abstract: Time series forecasting can be viewed as a generative problem that requires both semantic understanding over contextual conditions and stochastic modeling of continuous temporal dynamics.
By Mingyue Cheng, Yaguo Liu, Daoyu Wang, Xiaoyu Tao, Qi Liu
arXiv:2607. 21427v1 Announce Type: new Abstract: Discrete flow matching provides a flexible framework for generative modeling on discrete structures.
By Daniil Cherniavskii, Daniel Severo, Karen Ullrich
The paper introduces DV-Flow, a flow‑matching framework that treats deterministic prediction as a parallel velocity component instead of embedding it within the generative process. This design stabilizes end‑to‑end training and unifies several existing methods as special cases, enabling direct comparison. Experiments on six real‑world datasets show that DV‑Flow consistently outperforms strong baselines in probabilistic time‑series forecasting.
HALO introduces a hyperspherical VAE to constrain continuous latent representations to a fixed‑radius shell, stabilizing numerical fluctuations. It then employs a masked autoregressive model that balances parallel decoding with temporal correlation learning, reducing inference steps and improving stability. Experiments show HALO achieves state‑of‑the‑art generation performance with significantly better inference efficiency compared to existing baselines.
By Chunyi Hou, Xiangfei Qiu, Hanyin Cheng, Yutong Li, Bin Yang
arXiv:2503. 07154v3 Announce Type: replace-cross Abstract: Generative pre-training is often framed through a false dichotomy between autoregressive models for discrete signals and diffusion models for continuous signals.
By Jiaming Song, Linqi Zhou
arXiv:2609.15643v1 Announce Type: new
Abstract: Flow-matching diffusion models have recently emerged as a strong paradigm for high-fidelity visual generation. However, their prohibitively high fine-t...
By Jiayang Gu, Zheng Fang, Lichaun Xiang, Fanghui Liu, Xu Cai, Hongkai Wen
arXiv:2607. 12616v1 Announce Type: new Abstract: Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields.
By Shuchan Wang
arXiv:2410. 10137v5 Announce Type: replace Abstract: We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds.
By Andrew Gracyk
The paper introduces a spectrally-aligned latent-flow model for time‑series generation that trains the latent space to preserve dynamical properties relevant to synthetic data quality. By incorporating fine‑tuning losses based on Fourier, wavelet, and signature transforms, the method mitigates spectral mismatches caused by latent compression and ensures alignment with true signals in terms of smoothness and targeted spectral content. Experiments on real‑world long‑range univariate and multivariate benchmarks show that the aligned model outperforms a base latent‑flow model and state‑of‑the‑art approaches in signal realism, computational efficiency, and local structure alignment.
By Camilo Carvajal Reyes, Felipe Tobar