The paper introduces RQ-Reg, a residual‑quantization framework for predicting continuous values in recommender systems. It decomposes target values into a sequence of quantization codes, autoregressively refining predictions from coarse to fine granularity, and incorporates an ordinal‑aware objective to align embeddings with target order. Experiments on watch‑time, LTV, and a large‑scale online A/B test for GMV demonstrate competitive performance and strong generalization across diverse prediction tasks.
By Runpeng Cui, Zhipeng Sun, Chi Lu, Peng Jiang
The paper introduces an adaptive Mixture-of-Experts (MoE) framework for time series forecasting that incorporates expert-specific losses to give each expert a direct learning signal independent of gating weights. The overall objective combines base forecasting loss with these expert losses, encouraging experts to specialize on different temporal segments. A partial online learning strategy is added for efficient incremental updates, and experiments on economic, tourism, and energy datasets show the method outperforms state‑of‑the‑art neural models and foundation models, with ablation studies confirming the benefit of expert loss integration.
By Btissame El Mahtout, Florian Ziel
arXiv:2606. 18367v1 Announce Type: new Abstract: Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes.
By Yingshuo Wang, Xian Sun, Lingdong Kong, Wei Gao, Yanhang Li, Zhichao Fan, Zexin Zhuang
arXiv:2606. 01352v1 Announce Type: new Abstract: Watch time has emerged as a pivotal metric for optimizing deep user engagement in short-video recommender systems.
By Hongxu Ma, Han Zhou, Chenghou Jin, Jie Zhang, Xiaoyu Yang, Chunjie Chen, Jihong Guan, Shuigeng Zhou
arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.
By Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang
Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.
By Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang
arXiv:2609.37533v1 Announce Type: new
Abstract: Masked diffusion models (MDMs) generate sequences by progressively unmasking several tokens per denoising step, but their reverse process is typically...
By Arseny Ivanov, Alexander Kolesov, Alexander Korotin, Ivan Oseledets, Mikhail Goncharov
arXiv:2607. 06607v1 Announce Type: cross Abstract: Accurate long-term forecasting in complex systems is frequently compromised by dataset-level distribution shifts, where diverse underlying behavioral modes and evolving system states drive the dynamic multivariate time-series.
By Lanhao Li, Bingshu Xie, Lijun Sun, Xin Xue, Haoyi Zhou, Jianxin Li
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
The paper introduces an adaptive fitting procedure for mixtures of product distributions in Gaussian regression with a spike‑and‑slab prior, directly minimizing reverse Kullback‑Leibler divergence on inclusion indicators and active coefficients. This method jointly refines component parameters and weights as the mixture grows, avoiding extra divergence penalties on unused latent coefficients. Empirical results on 250 simulated datasets show that mixtures reduce errors in inclusion probabilities, grouped support probabilities, and coefficient covariance compared to multistart mean‑field approaches, and that direct joint refinement outperforms augmented or restricted refinement at fixed mixture size.
By Hanqing Li, Yaroslav Golub, Xuewen Lu
The paper introduces TiMi, a framework that enhances time series transformers with a Multimodal Mixture-of-Experts (MMoE) module to incorporate multimodal data, especially textual information, into forecasting. TiMi leverages large language models to generate future inferences that guide predictions, eliminating the need for explicit representation alignment. Experiments show TiMi achieves state‑of‑the‑art performance on sixteen real‑world multimodal forecasting benchmarks, outperforming advanced baselines while maintaining adaptability and interpretability.
By Jiafeng Lin, Yuxuan Wang, Huakun Luo, Jianmin Wang, Zhongyi Pei
arXiv:2604. 25834v2 Announce Type: replace Abstract: With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms.
By Wenhao Li, Zihan Lin, Zhengxiao Guo, Jie Zhou, Shukai Liu, Yongqi Liu, Chuan Luo, Chaoyi Ma, Ruiming Tang, Han Li