A5058271339- Topic Modeling
- Data Quality and Management
- Diabetes Management and Research
- Multimodal Machine Learning Applications
- Protein Structure and Dynamics
- Pancreatic function and diabetes
- Deception detection and forensic psychology
- Smart Grid Energy Management
- Advanced machining processes and optimization
- Mechanical Engineering and Vibrations Research
- Drilling and Well Engineering
- Advanced Graph Neural Networks
- Tunneling and Rock Mechanics
- Computational Drug Discovery Methods
- Cardiovascular Function and Risk Factors
- Explainable Artificial Intelligence (XAI)
- Robot Manipulation and Learning
- Smart Agriculture and AI
- Artificial Intelligence in Healthcare and Education
- Polydiacetylene-based materials and applications
- Antimicrobial Peptides and Activities
- Occupational Health and Safety Research
- Machine Learning in Materials Science
- Advanced Bandit Algorithms Research
- Antimicrobial agents and applications
East China University of Science and Technology
2023-2024
Beijing Information Science & Technology University
2023-2024
ChatGPT, an artificial intelligence generated content (AIGC) model developed by OpenAI, has attracted world-wide attention for its capability of dealing with challenging language understanding and generation tasks in the form conversations. This paper briefly provides overview on history, status quo potential future development helping to provide entry point think about ChatGPT. Specifically, from limited open-accessed resources, we conclude core techniques mainly including large-scale...
In recent years, artificial intelligence has played an important role on accelerating the whole process of drug discovery. Various molecular representation schemes different modals (e.g., textual sequence or graph) are developed. By digitally encoding them, chemical information can be learned through corresponding network structures. Molecular graphs and Simplified Input Line Entry System (SMILES) popular means for learning in current. Previous works have done attempts by combining both them...
To address the challenges of long commuting times, traffic congestion, high energy consumption, and emissions in inter-city travel, a new type flying coach has been developed. This innovation aims to significantly shorten enhance travel efficiency, simultaneously reduce consumption emissions. The integrates rail power supply technology, an intelligent operating system, advanced materials, comprising catenary guide rod various sensor components. Based on analysis traditional aircraft design...
The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM). However, designing an effective policy the AP remains challenging due to complex physiological processes, delayed insulin response, and inaccurate measurements. While model predictive (MPC) offers safety stability through dynamic constraints, it lacks individualization is adversely affected by unannounced meals. Conversely, deep...
Summarizing the causation of aviation accidents is conducive to enhancing safety. The knowledge graph accident causation, constructed based on reports, can assist in analyzing causes accidents. With continuous development artificial intelligence technology, leveraging large language models for information extraction and construction has demonstrated significant advantages. This paper proposes an method Claude-prompt, which relies large-scale pre-trained model Claude 3.5. Through prompt...
Host defense peptide (HDP)-mimicking polymers are promising therapeutic alternatives to antibiotics and have large-scale untapped potential. Artificial intelligence (AI) exhibits performance on chemical-content design, however, existing AI methods face difficulties scarcity data in each family of HDP-mimicking (<10
While recent advancements in large language model (LLM) alignment have enabled the effective identification of malicious objectives involving scene nesting and keyword rewriting, our study reveals that these methods remain inadequate at detecting expressed through context within nested harmless objectives. This identifies a previously overlooked vulnerability, which we term Attack via Implicit Reference (AIR). AIR decomposes objective into permissible links them implicit references context....
Because of the lack description information, significant attribute differences and substantial relationship heterogeneity existing in alignment domain knowledge graphs general graphs, information is embedded through graph attention mechanism, entity representation vector obtained by embedding used as initial relation embedding, network for an containing obtained. The aligned similarity calculation. Experimental results on dataset CAKG-ONTK demonstrate that proposed model outperforms other...
Manipulating deformable objects, such as ropes (1D), fabrics (2D), and bags (3D), poses a significant challenge in robotics research due to their high degree of freedom physical state nonlinear dynamics. Compared with single-dimensional multi-dimensional object manipulation suffers from the difficulty recognizing characteristics correctly making an accurate action decision on various dimensions. Some methods are proposed use neural networks rearrange objects all dimensions, but approaches...
Objective: The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM). However, designing an effective policy the AP remains challenging due to complex physiological processes, delayed insulin response, and inaccurate measurements. While model predictive (MPC) offers safety stability through dynamic constraints, it lacks individualization is adversely affected by unannounced meals. Conversely, deep...