This repository contains code and datasets for our research on developing machine learning models that mimic human visual motion perception. While state-of-the-art computer vision (CV) models, such as ...

The research introduced a two-phase training process. First, they used supervised fine-tuning (SFT) on high-quality trajectories sampled from Claude-4 Sonnet using rejection sampling, effectively ...

We present scLAMBDA, a deep generative learning framework designed to model and predict single-cell transcriptional responses to genetic perturbations, including single-gene and combinatorial ...

Abstract: Accurately predicting pedestrian intentions is a critical task for enhancing pedestrian safety in intelligent transportation systems, particularly in 6G-driven complex dynamic urban ...

National Key Laboratory of Advanced Micro and Nano Manufacture Technology, Shanghai Jiao Tong University, Shanghai 200240, China Department of Micro/Nano Electronics, School of Electronic Information ...

ABSTRACT: In 2010, Guinea, through multi-level governance, undertook profound legal and institutional reforms to promote more participatory, equitable and sustainable mining development and the ...

Introduction: Parkinson's disease (PD) is characterized by muscle stiffness, bradykinesia, and balance disorders, significantly impairing the quality of life for affected patients. While motion pose ...

Large Language Models (LLMs) have become indispensable tools for diverse natural language processing (NLP) tasks. Traditional LLMs operate at the token level, generating output one word or subword at ...

Large language models (LLMs) have transformed the landscape of natural language processing, becoming indispensable tools across industries such as healthcare, education, and technology. These models ...