Do we really need a large number of visual prompts?

Due to increasing interest in adapting models on resource-constrained edges, parameter-efficient transfer learning has been widely explored. Among various methods, Visual Prompt Tuning (VPT), prepending learnable prompts to input space, shows competitive fine-tuning performance compared to training of full network parameters. However, VPT increases the number of input tokens, resulting in additional computational overhead.

Sharing leaky-integrate-and-fire neurons for memory-efficient spiking neural networks.

Spiking Neural Networks (SNNs) have gained increasing attention as energy-efficient neural networks owing to their binary and asynchronous computation. However, their non-linear activation, that is Leaky-Integrate-and-Fire (LIF) neuron, requires additional memory to store a membrane voltage to capture the temporal dynamics of spikes. Although the required memory cost for LIF neurons significantly increases as the input dimension goes larger, a technique to reduce memory for LIF neurons has not been explored so far.

Regulation of the hypothalamic GnRH-GnIH system by putrescine in adult female rats and GT1-7 neuronal cell line.

The gonadotropin-releasing hormone-gonadotropin inhibitor (GnRH-GnIH) system in the hypothalamus of mammals is the key factor that controls the entire reproductive system. The aim of this study was to immunolocalize GnIH (RFRP-3) in the hypothalamus during the estrous cycle and to study the effect of putrescine on the expression of GnRH-I and GnIH through both in vivo and in vitro (GT1-7 cells) approach and the circulatory levels of GnRH-I, GnIH, and gonadotropins were also investigated. The study also aims in analyzing all the immunofluorescence images by measuring the relative pixel count of an image.