Multivariate time-series forecasting is essential to many real-world applications. Recent large vision models (LVMs) offer a promising paradigm by transferring cross-domain visual priors to time-serie...
arXiv:2510. 03244v2 Announce Type: replace-cross Abstract: Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies.
The paper introduces ICI-Time, a framework that casts time series forecasting as a visual inpainting problem. By converting series into area‑chart images, it enables pre‑trained vision transformers to perform forecasting through in‑context learning without fine‑tuning or new temporal architectures. Experiments on epidemiology, meteorology, and power systems show competitive performance and strong adaptability in low‑data scenarios.
We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting task, leveraging the generalisation power of large vision models (LVMs). Unlike methods that require...
arXiv:2506.08641v3 Announce Type: replace Abstract: Adapting vision models for time series analysis is compelling, yet all existing approaches are falling short of dedicated time series foundation mo...
SAGE is an end‑to‑end CLIP‑based framework that augments vision‑language time‑series forecasting by jointly modeling temporal, cross‑variable, textual, and visual information. It processes frequency‑enhanced patches and variable tokens through a CLIP text encoder, while gated residual paths inject variable‑specific descriptions and statistical descriptors. A frozen CLIP vision encoder aligns rendered series with temporal representations via a training‑only contrastive objective, enabling multimodal alignment and variable‑level knowledge without using an LLM during inference.
SAGE is a CLIP-based framework that augments vision‑language time series forecasting by incorporating variable‑specific semantic and statistical information. It processes frequency‑enhanced patches and variable tokens through a CLIP text encoder, while a frozen CLIP vision encoder aligns rendered series with temporal representations via a contrastive objective. The approach achieves state‑of‑the‑art accuracy on eight long‑term benchmarks and M4, with ablations showing complementary gains from multimodal alignment and variable‑level knowledge.
WinoTS introduces a wavelet‑based self‑distillation framework for time‑series models that uses time‑frequency augmentations to create multi‑scale structural views, avoiding distortion of signal dynamics. The method outperforms state‑of‑the‑art baselines in long‑term forecasting, cross‑domain zero‑shot transfer, and unsupervised anomaly detection, and linear probing on frozen representations often beats fully supervised training from scratch. Ablation studies show WinoTS is architecture‑agnostic and demonstrates that time‑frequency transformations offer a principled alternative to vision‑style spatial augmentations.
arXiv:2603. 05997v2 Announce Type: replace-cross Abstract: Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across diverse variables.
arXiv:2604. 16325v3 Announce Type: replace-cross Abstract: Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges.
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.
LongVU‑TTT is a causal test‑time training method for long‑video multimodal large language models that inserts a convolutional resampler with fast‑weight updates between the vision encoder and the LLM. The fast weights adapt per video and contextualize frame features before compression, while a hybrid selector keeps explicit visual evidence for downstream reasoning. Experiments show that TTT‑Conv outperforms TTT‑MLP and bidirectional Mamba2 on MLVU, and beats attention‑ and fixed‑state recurrent resamplers on three benchmarks, achieving competitive results on five video‑understanding tasks after reducing 512 frames to 128 LLM frames.