Look, Reason, Draw a Region: Recursive Refinement for Spatial Context Prediction
Spatial-TRM raises RoboSpatial-Home context accuracy to 29.51% with 11.2M trainable parameters.
Stories per day · 30 days
2 RSS
4 stories, newest first · one card per story
Stories tagged #parameter-efficiency
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
A recurrent vision Transformer matches full-depth encoder accuracy with about 70% fewer stored parameters.
ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning
ALPINE is an ultra-lightweight few-shot image classifier that beats Prototypical Networks, Relation Networks, and MAML with 27-53% fewer parameters.
Local gradient neural operator
Researchers propose LGNO, a lightweight interpretable neural operator using learnable local stencils, matching global-operator accuracy on PDE benchmarks with fewer parameters.