Relationship Between Subduction Erosion and the Up‐Dip Limit of the 2014 Mw 8.1 Iquique Earthquake
GEOPHYSICAL RESEARCH LETTERS(2021)
GEOMAR Helmholtz Ctr Ocean Res Kiel
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Density Structure, Flexure, and Tectonics of the Iquique Ridge, Northern Chile
被引用8
被引用4
Crustal Structure of the Incoming Iquique Ridge Offshore Northern Chile
被引用15
Megathrust Reflectivity Reveals the Updip Limit of the 2014 Iquique Earthquake Rupture
被引用9
被引用4
PickBlue: Seismic Phase Picking for Ocean Bottom Seismometers with Deep Learning
被引用4
Impact of the Iquique Ridge on Structure and Deformation of the North Chilean Subduction Zone
被引用5
被引用2
The Northern Chile Forearc Constrained by 15 Years of Permanent Seismic Monitoring
被引用9
被引用2
Geomorphology and Mechanisms of Subduction Erosion in the Sediment-Starved Mariana Convergent Margin
被引用0
Accretion Versus Erosion and Sediment Transfer Balance Near the Subduction Interface
被引用1
Offshore Geometry of the South America Subduction Zone Plate Boundary
被引用0
被引用0
Impact of Upper‐Plate Faulting on Megathrust Foreshocks: Insights from the 2014 Iquique Earthquake
被引用0