杨贵妃传媒

This research project investigates the development of an autonomous, iterative pipeline designed to enhance the capabilities of small- to mid-sized large language models (LLMs) by enabling them to refine both system and user prompts for a given task. We explore strategies for self-prompting frameworks in which the LLM iteratively analyzes a user prompt, generates optimized system-level instructions, and refines the prompt to improve task-specific performance in terms of quality and relevance of the generated response.

The largest state-of-the-art LLMs often demonstrate superior capabilities. However, smaller models are more accessible for resource-constrained environments, such as edge and personal devices. Enhancing the utility of these lightweight LLMs without fine-tuning or expanding their parameter counts could significantly broaden their practical applications.

To assess the effectiveness of this self-prompting framework, the project will establish both qualitative and quantitative benchmarks, including NLP-based similarity scoring and task-specific performance metrics. The interdisciplinary scope will be supported through collaboration with subject matter experts across multiple academic fields to design diverse input prompts and evaluate the quality of the generated outputs.

While this project aims to expand the capabilities of resource-efficient LLMs, we also seek to identify reusable, LLM-specific strategies for improving prompt effectiveness across domains. The findings may later be integrated into existing self-correcting LLM pipelines for tasks involving scientific code generation, contributing to the further advancement of autonomous LLM techniques in scientific contexts.

The advancement of machine learning (ML), particularly deep learning (DL) and natural language processing (NLP) technologies, along with increased computing power, has further enhanced biotechnological applications, including protein design and engineering . These developments have led to the creation of Large Protein Language Models (LPLMs), which assist in discovering the evolutionary, structural, and functional properties across protein space by encoding amino-acid sequences into numeric vector representations we leverage pretrained LPLMs to extract features for antibody design specifically targeting ADAM17 (A Disintegrin and Metalloproteinase 17) and MMP-9cd (Matrix Metalloproteinase-9 catalytic domain). Both ADAM17 and MMP-9 play critical roles in pathological processes such as inflammation, cancer metastasis, and tissue remodeling, making them promising therapeutic targets.

Book abstract.

AI progressing into AGI creates conditions for the real Industrial Revolution 5.0, thus enabling Digital Transformation 5.0

The goal is to explore productive links between Artificial General Intelligence, and Digital Transformation in Management.. 

chapter 1. Industry 4.5 reaching for the Horizon

Chapter 2. Discovery Engines: Compute at the edge of chaos: Goertzel-Hanson's Sophia; meets Thaler's DABUS.

Paraconsistent human and artificial creativity engines, and values.

Chapter 3. The alignment problem taken care of  AGI that knows what's going on (Sanz); AGI's inculcated into Gemeinschaft of human practices and emergent values

Chapter 4, Paraconsistent creati

Chapter 5. Floridi's dethronement of naive, homocentric humanism (Kopernicus; Darwin, Freud/Velmans; Turing/DABUS). Paradoxical axiology of Pico della Mirandola as the sole basis of human exceptionalism, if at all.

Chapter 6. Digital Transformation beyond Taylorizations. The Poverty of Philosophy part two. The Value proposition beyond Rogers flooding customers by apps; beyond ChallGalla's shrood marketing; and beyond Proudhon-style naive socialism.

hapter 7. Machine consciousness -- relevant dimesnions

Trustworthy AI project aims to survey and uncover relevant dimensions and factors in businesses or organizations. The initial stage involves a systematic literature review with bibliometric analysis, with impactful insights leading to prominent future implications, applications, or funding chances. 

Building a high-performance computer (HPC) involves carefully designing, assembling, and configuring a system to deliver exceptional computationalpower. Key stages include assessing needs, selecting hardware, assembly, software configuration, and rigorous testing. The HPC empowers researchers with a robust computing platform for cutting-edge research and data-intensive computations.