ChorusTIC is a training‑free foundation model for multivariate time‑series classification that works across heterogeneous channel configurations without updating task‑specific parameters. It uses Random Subchannel Slot Concatenation and a shared dual‑axis encoder to capture temporal and cross‑channel interactions, mapping variable channel counts into a fixed‑width representation. The model is pretrained on synthetic episodes and achieves strong performance on the UEA‑30 and UCR‑128 archives, handling both full‑context and low‑label scenarios without fitting a target‑specific classifier.
arXiv:2607. 19234v1 Announce Type: new Abstract: Time series classification is central to domains like medical signal analysis, industrial monitoring, and sensor-based activity recognition, where class information manifests as localized shapes, specific frequencies, temporal shifts, or complex cross-channel interactions.
arXiv:2608.31013v1 Announce Type: new Abstract: Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for p...
arXiv:2606. 09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open.
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.
arXiv:2606. 10466v1 Announce Type: cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains.
arXiv:2607. 07500v1 Announce Type: cross Abstract: Time series classification (TSC) is dominated by a two-stage paradigm: train a feature encoder -- either from scratch on the target dataset or via pretraining on large corpora -- and then fit a task-specific classifier on top.
Timer‑M1 is a pretrained multivariate time‑series foundation model that learns with primitives for zero‑shot forecasting. It uses a primitive‑based data synthesis and pretraining pipeline to generate series with shared temporal and relational patterns, assembling them into multivariate samples with distinct channel roles. The model employs gated two‑dimensional Transformer blocks that dynamically allocate cross‑variate attention, achieving top performance on several large‑scale forecasting benchmarks.
The paper introduces the Recursive Time-Series Model (RTSM), a deep-learning architecture that uses a learned convolutional temporal tokenizer, a single-state weight‑tied refinement module, and a pooled classification readout to classify multivariate time‑series data. On the 30 UEA datasets, RTSM achieves a mean accuracy of 72.81% under validation‑based configuration, surpassing all 17 evaluated deep‑learning models and outperforming MambaSL by 1.60 percentage points. Ablation studies show that the proposed tokenizer and single‑state design outperform simpler convolutional embeddings and two‑state variants, and the full classifier reaches 86.10% mean accuracy compared to 84.79% for a tokenizer‑only classifier.
arXiv:2602. 00620v2 Announce Type: replace-cross Abstract: The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier.
arXiv:2607. 08234v1 Announce Type: cross Abstract: Real-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal cycles, long-term trends, and irregular abrupt changes.
TimeBraid is a family of unified models that combine pretrained language models with pretrained time‑series foundation models using interleaved global residual attention layers. The models inherit instruction following, reasoning, and continuous‑signal perception, fusing both modalities into a shared representation space for understanding and generation. The design focuses on aligning representation spaces, grounding language in temporal structure, balancing understanding with generation, and maintaining stable joint optimization, supported by 2.2 M curated series‑text pairs and 4.9 M instruction‑tuning samples. Across diverse benchmarks, TimeBraid competes with larger general‑purpose and task‑specific models.
The paper introduces iAmTime, a time‑series foundation model that uses instruction‑conditioned in‑context learning to adapt to tasks at inference time. iAmTime represents each episode as a structured prompt with semantic tokens that focus on specific time‑series regions, enabling the model to infer task structure from input‑output demonstrations. Trained on large real and synthetic corpora across forecasting, imputation, reconstruction, classification, anomaly detection, and source de‑mixing, iAmTime outperforms strong baselines on zero‑shot probabilistic and point forecasting while matching or exceeding performance on several non‑forecasting tasks.