Stroke causes loss of neurological function. Recovery after stroke is facilitated by forced use of the affected limb and is associated with sprouting of new connections, a process that is sharply confined in the adult brain. We show that ephrin-A5 is induced in reactive astrocytes in periinfarct cortex and is an inhibitor of axonal sprouting and motor recovery in stroke. Blockade of ephrin-A5 signaling using a unique tissue delivery system induces the formation of a new pattern of axonal projections in motor, premotor, and prefrontal circuits and mediates recovery after stroke in the mouse through these new projections. Combined blockade of ephrin-A5 and forced use of the affected limb promote new and surprisingly widespread axonal projections within the entire cortical hemisphere ipsilateral to the stroke. These data indicate that stroke activates a newly described membrane-bound astrocyte growth inhibitor to limit neuroplasticity, activity-dependent axonal sprouting, and recovery in the adult.cortical map | regeneration | repair | motor function | EphA4

We show that Transformer encoder architectures can be massively sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear transformations, along with simple nonlinearities in feed-forward layers, are sufficient to model semantic relationships in several text classification tasks. Perhaps most surprisingly, we find that replacing the self-attention sublayer in a Transformer encoder with a standard, unparameterized Fourier Transform achieves 92% of the accuracy of BERT on the GLUE benchmark, but pre-trains and runs up to seven times faster on GPUs and twice as fast on TPUs. The resulting model, which we name FNet, scales very efficiently to long inputs, matching the accuracy of the most accurate "efficient" Transformers on the Long Range Arena benchmark, but training and running faster across all sequence lengths on GPUs and relatively shorter sequence lengths on TPUs. Finally, FNet has a light memory footprint and is particularly efficient at smaller model sizes: for a fixed speed and accuracy budget, small FNet models outperform Transformer counterparts.

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. Most surprisingly, we find that replacing the self-attention sublayer in a Transformer encoder with a standard, unparameterized Fourier Transform achieves 92-97% of the accuracy of BERT counterparts on the GLUE benchmark, but trains 80% faster on GPUs and 70% faster on TPUs at standard 512 input lengths. At longer input lengths, our FNet model is significantly faster: when compared to the "efficient Transformers" on the Long Range Arena benchmark, FNet matches the accuracy of the most accurate models, while outpacing the fastest models across all sequence lengths on GPUs (and across relatively shorter lengths on TPUs). Finally, FNet has a light memory footprint and is particularly efficient at smaller model sizes; for a fixed speed and accuracy budget, small FNet models outperform Transformer counterparts. 1

We show how to continuously map a texture onto a 3D triangle mesh when some of the mesh vertices are constrained to have given (u, v) coordinates. This problem arises frequently in interactive texture mapping applications and, to the best of our knowledge, a complete and efficient solution is not available. Our techniques always guarantee a solution by introducing extra (Steiner) vertices in the triangulation if needed. We show how to apply our methods to texture mapping in multi‐resolution scenarios and image warping and morphing.

A feature-oriented generic progressive lossless mesh coder (FOLProM) is proposed to encode triangular meshes with arbitrarily complex geometry and topology. In this work, a sequence of levels of detail (LODs) are generated through iterative vertex set split and bounding volume subdivision. The incremental geometry and connectivity updates associated with each vertex set split and/or bounding volume subdivision are entropy coded. Due to the visual importance of sharp geometric features, the whole geometry coding process is optimized for a better presentation of geometric features, especially at low coding bitrates. Feature-oriented optimization in FOLProM is performed in hierarchy control and adaptive quantization. Efficient coordinate representation and prediction schemes are employed to reduce the entropy of data significantly. Furthermore, a simple yet efficient connectivity coding scheme is proposed. It is shown that FOLProM offers a significant rate-distortion (R-D) gain over the prior art, which is especially obvious at low bitrates.