AIRI - Artificial Intelligence Research Institute

2 related articles

Subscribe to updates

researchsquare.com Oct 30, 2026
Six-hourly archives lack the hours apps need: WeatherBridge fills them with bidirectional transport, cutting held-out-hour error 48.6% below linear interpolation
Many global forecast archives store fields every six hours, while applications need hourly states. WeatherBridge reconstructs the interior state as query-conditioned bidirectional second-order transport between the two anchors, plus multiscale and spherical-harmonic residual corrections, and reaches the lowest aggregate error at held-out query hours on the 2020 ERA5 benchmark: normalised RMSE 0.07431 at six hours, 48.6% below linear interpolation's 0.144 and 9.0% below WeatherDCAE-14M. The advantage is not field-uniform; WeatherDCAE-14M remains better for geopotential and MSLP.
Many global forecast archives store fields every six hours, while applications need hourly states. WeatherBridge reconstructs the interior state as query-conditioned bidirectional second-order transport between the two anchors, plus multiscale and spherical-harmonic residual corrections, and reaches the lowest aggregate error at held-out query hours on the 2020 ERA5 benchmark: normalised RMSE 0.07431 at six hours, 48.6% below linear interpolation's 0.144 and 9.0% below WeatherDCAE-14M. The advantage is not field-uniform; WeatherDCAE-14M remains better for geopotential and MSLP.
AIRI - Artificial Intelligence Research Institute
Daniil Sukhorukov（First author, Corresponding author）
WeatherBridge Weather Field Temporal Interpolation Bidirectional Anchor Transport ERA5 Reanalysis IFS HRES Forecast Anchors
arXiv Sep 28, 2026
Tactile-JEPA pretrains on the taxel connectivity graph and cuts force-estimation error by 6.3% and in-hand pose error by 20.8%
The work introduces Tactile-JEPA, a self-supervised pretraining method for distributed tactile sensors (e-skins) that samples masks at local and global scales over the taxel connectivity graph and predicts the embeddings of masked taxels; across magnetic and piezoresistive sensors and three datasets (Sparsh-skin, Tactile socks, DECO-50) it reduces force-estimation RMSE by 6.3% and in-hand pose RMSE by 20.8% over the strongest prior baseline, with consistent gains in action classification, object classification, and tactile-conditioned policy learning.
The work introduces Tactile-JEPA, a self-supervised pretraining method for distributed tactile sensors (e-skins) that samples masks at local and global scales over the taxel connectivity graph and predicts the embeddings of masked taxels; across magnetic and piezoresistive sensors and three datasets (Sparsh-skin, Tactile socks, DECO-50) it reduces force-estimation RMSE by 6.3% and in-hand pose RMSE by 20.8% over the strongest prior baseline, with consistent gains in action classification, object classification, and tactile-conditioned policy learning.
AIRI - Artificial Intelligence Research Institute Skolkovo Institute of Science and Technology National Research University Higher School of Economics
Elizaveta Kovtun（First author）
Tactile-JEPA Tactile Representation Learning Graph-Based Mask Sampling Distributed Tactile Sensors

You’re all caught up

Six-hourly archives lack the hours apps need: WeatherBridge fills them with bidirectional transport, cutting held-out-hour error 48.6% below linear interpolation

Tactile-JEPA pretrains on the taxel connectivity graph and cuts force-estimation error by 6.3% and in-hand pose error by 20.8%