Author

Malik Tiomoko

h-index 7 View on Semantic Scholar

We have 6 of 35 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

On the Generalization Gap of Streaming Federated Learning with Markovian Data

Streaming federated learning (SFL) allows clients to train a shared model from continuously arriving data without retaining large local datasets. Such streams often exhibit temporal dependence, yet its effect on generalization remains poorly understood. In this paper we study the expected generalization gap of the aggr...

Masoud Kavian, Milad Sefidgaran, Youssef Attia El Hili et al. · 0 citations

#machine learning Sep 2026

Instance-Adaptive Prompts as Context for Time-Series Foundation Models

PaCTS is introduced, which generates a small set of instance-adaptive latent prompts in the form of continuous embedding tokens conditioned on the visible context, which serve as compact context surrogates for frozen TSFMs.

Ze-Hao Xiao, Shi-Feng Xie, Lei Zan et al. · arXiv.org · 0 citations

#artificial intelligence Preprint Sep 2026

LLM-Generated Feature Pools for Time Series Anomaly Detection

A pool per domain is generated by prompting a multimodal LLM with in-context example windows from that domain by prompting a multimodal LLM with in-context example windows from that domain, and the generated pools match the hand-crafted one under matched selection, and the two cover different domains.

Youssef Attia El Hili, Malik Tiomoko, Corinne Ancourt · 0 citations

#artificial intelligence Jul 2026

Post-Training in Time Series Foundation Models: A Unifying Framework

This work analyzes TSFM post-training methods based on their locus of intervention in the prediction pipeline, yielding five categories: parameter adaptation, context augmentation, model composition, output processing and uncertainty control, and compression and specialization.

Shi-Feng Xie, Ambroise Odonnat, Ze-Hao Xiao et al. · arXiv.org · 3 citations

#machine learning Preprint Sep 2026

Tabby: An Open Pretraining Recipe for Time Series Foundation Models

Tabby, a long context probabilistic time series foundation model, is released together with a complete and open recipe of how it was built, which achieves competitive zero-shot forecasting performance on GIFT-Eval and the out-of-distribution TIME benchmark.

Shi-Feng Xie, Bahaeddine Abdessalem, Ze-Hao Xiao et al. · 1 citation

#machine learning Preprint Sep 2026

FlowTSFM: Turning Encoder Depth into Quantile Transport

FlowTSFM is introduced, an encoder architecture that interprets depth as a recurrent transport process: a single Transformer block is iteratively applied with shared parameters, while a quantile-flow objective supervises intermediate states along a prescribed trajectory from a prior distribution toward the final foreca...

Bahaeddine Abdessalem, Shi-Feng Xie, Ze-Hao Xiao et al. · 0 citations