← Back to all news
arXiv Computer Vision By Rajiv Ranjan, Udaiveer Singh, Shashank Tamaskar, Dharmendra Saraswat

SPEAR NeXT Causal Latent Forecasting Across Multiple Horizons for Spectral Temporal Earth Representation Learning

Read the original on arXiv Computer Vision →

SPEAR NeXT is a compact, pixel‑wise multimodal spectral‑temporal foundation model that learns temporal self‑supervision by predicting future latent Earth states from past observations. It encodes instantaneous states from optical, radar, and environmental data into 32‑dimensional embeddings, then models their evolution with a causally masked transformer that forecasts multiple future horizons. The model uses Rotary Position Embeddings to capture relative temporal order and month/year embeddings to encode seasonal and interannual context.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
5d ago

WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting

WorldTS is a new forecasting framework that models latent dynamics conditioned on multimodal covariates to improve time‑series prediction. It uses a two‑stage training process: first learning latent state dynamics from historical data and covariates, then training a decoder to map predicted latent states back to future observations. Experiments on 21 real‑world datasets demonstrate the effectiveness of this approach.

By Yuhan Zhu, Xiangfei Qiu, Hanyin Cheng, Wangmeng Shen, Chenjuan Guo, Bin Yang, Jilin Hu, Christian S. Jensen
multimodal
More like this →
arXiv AI
Aug 26

In-Context Inpainting for Time Series Forecasting

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.

By Thang Nguyen, Dung Nguyen, Romero Morais, Truyen Tran
llmsfine-tuning
More like this →
arXiv Machine Learning
Jun 9

GNSS-FM: A Self-Supervised Foundation Model for Daily GNSS Displacement Time Series

arXiv:2606. 07725v1 Announce Type: cross Abstract: Displacement time series from Global Navigation Satellite Systems (GNSS) are essential for a wide range of applications, including monitoring tectonic crustal deformations and investigating the different stages of the earthquake cycle.

By Nick Teutschmann (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland), Laura Crocetti (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland), Fanny Lehmann (ETH AI Center, Switzerland), Leonardo Trentini (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland), Benedikt Soja (Institute of Geodesy and Photogrammetry, ETH Zurich, Switzerland)
fine-tuningefficiency
More like this →