An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-training

An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-training Academic Background In recent years, self-supervised learning (SSL) has made significant progress in the field of computer vision. In particular, the successful application of masked image modeling (MIM) pre-training methods on large-sca...

High-Throughput Discovery of Inhibitory Protein Fragments with AlphaFold

High-Precision Prediction of Protein Fragment Inhibitory Activity: The Application of FragFold Academic Background Protein interactions play a crucial role in cellular life activities, and peptides or protein fragments can regulate protein functions by binding to specific protein interfaces, even acting as inhibitors. Recent developments in high-th...

Robust Inattentive Discrete Choice

In today’s era of information explosion, decision-makers are faced with a vast amount of information, not all of which is relevant to their decisions. To better make optimal decisions in data-rich environments, the Rational Inattention (RI) model has been introduced into the field of economics. The core idea of this model is that decision-makers ne...

Identifying New Classes of Financial Price Jumps with Wavelets

Research Report on Identifying New Classes of Financial Price Jumps Using Wavelets Academic Background Price jumps in financial markets refer to significant price fluctuations occurring within an extremely short period, typically caused by exogenous factors (such as sudden news) or endogenous factors (internal market feedback mechanisms). Distingui...

Out-of-Distribution Generalization via Composition: A Lens Through Induction Heads in Transformers

Study on Out-of-Distribution Generalization and Composition Mechanisms in Large Language Models Paper Background In recent years, large language models (LLMs) such as GPT-4 have demonstrated remarkable creativity in handling novel tasks, often solving problems with just a few examples. These tasks require models to generalize on distributions diffe...

Adaptive Quantized Control for a Class of Hysteresis Nonlinear System with Irregular Constraints and Its Application to Piezoelectric Positioning Stage

Adaptive Quantized Control Research for Hysteresis Nonlinear Systems in Piezoelectric Positioning Stages Background Introduction In modern high-precision positioning systems, smart materials (such as piezoelectric ceramics) are widely used in micro/nano manufacturing and soft robotics due to their excellent performance. However, the inherent hyster...