← Back to all news
arXiv Computer Vision

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

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.

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 →
arXiv Machine Learning
Sep 1

Season-Aware Hybrid Convolutional-Transformer for Antarctic Sea Ice Concentration Forecasting

The paper presents a hybrid Convolutional‑Transformer model for forecasting Antarctic sea ice concentration (SIC) on a monthly basis. It combines convolutional encoding for spatial features with factorised self‑attention to capture spatio‑temporal dependencies, and introduces two seasonal prior mechanisms: a month‑aware positional encoding and a seasonal temporal bias. Experiments show the model outperforms convolutional and recurrent baselines, with ablation studies confirming the benefits of the seasonal priors for both short‑ and long‑horizon predictions.

By Danyang Li, John Taylor, Thang Bui, Quanling Deng
llmsbenchmarkssafety
More like this →
Hugging Face Trending Papers
6d ago

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

The paper introduces PaCTS, a method that generates instance‑adaptive latent prompts—continuous embedding tokens—to provide compact contextual information for frozen time‑series foundation models (TSFMs). These prompts are constructed from instance‑specific global statistics and refined with segment‑level temporal data, enabling the model to capture both global characteristics and local temporal variations. Experiments show that PaCTS improves forecasting performance across various context lengths and model architectures, often outperforming the same backbone with double the context while reducing inference computation, and it also offers stronger improvements and better out‑of‑distribution generalization compared to weight‑space adaptation methods.

rag
More like this →