A Mutual Supervision Framework for Referring Expression Segmentation and Generation Research Background and Problem Statement In recent years, vision-language interaction technology has made remarkable progress in the field of artificial intelligence. Among these advancements, referring expression segmentation (RES) and referring expression generat...

GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection Research Background and Problem Statement In real-world applications, machine learning models often face changes in data distribution, such as the emergence of new categories. This phenomenon is known as “Out-of-Distribution Detection (OOD).” To ensure the...

Lidar-Guided Geometric Pretraining Enhances Performance of Vision-Centric 3D Object Detection Background Introduction In recent years, multi-camera 3D object detection has garnered significant attention in the field of autonomous driving. However, vision-based methods still face challenges in precisely extracting geometric information from RGB imag...

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-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...

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...

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...

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 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...

Balance and Task Evaluation of Construction Workers Assisted by Knee Exoskeletons Background Introduction Construction workers face serious safety and health risks in hazardous working environments, especially when working at heights. Prolonged standing and kneeling postures can lead to knee injuries, musculoskeletal disorders, and visual disturban...