Research Groups | 南京大学大模型研究协同创新中心

Large Language Model Research Group

Large Language Models: A New Era of Artificial Intelligence in Language Understanding and Generation Large Language Models (LLMs) are one of the most groundbreaking technologies in the field of artificial intelligence in recent years. Trained on massive datasets, they are capable of understanding and generating natural language, demonstrating near-human-level performance in tasks such as text generation, translation, and question answering. This marks the dawn of a new era in artificial intelligence for language understanding and generation.

Jan 1, 1030

Multimodal Large Model Research Group

Multimodal Large Model Research Group is committed to promoting the research and application of multimodal large models, exploring key technologies in multimodal information fusion, interaction, and reasoning, and driving the application of multimodal large models in visual, speech, text, and other multimodal data, thereby providing technical support for the development of multimodal intelligent technologies.

Jan 1, 1020

Embodied Decision Large Model Research Group

Embodied Decision Large Model Research Group focuses on cutting-edge research in embodied intelligence, aiming to build a generalizable embodied agent through study in representation learning, policy learning, and hierarchical planning and execution.

Jan 1, 1017

Large Model Knowledge Enhancement Research Group

The LLM + Knowledge research group has been engaged in long-term research on large language model knowledge enhancement, controllable generation, and domain-specific construction.

Jan 1, 1015

Large Model Learning Algorithms and Platform Research Group

The Large Model Learning Algorithms and Platform Research Group focuses on the construction of systems based on large models, large-scale training/inference deployment, and the application of large models. The group conducts research to address key challenges in efficient training, deployment, and the integration of domain knowledge into large models. In terms of applications, the group has a strong focus on reasoning tasks such as Automated Theorem Proving (ATP). In undergraduate education, the group offers courses on large model development, training students to build large models from scratch.

Jan 1, 1010

Large Model Systems and Platforms Research Group

## Large Model Systems and Platforms: The Core Engine Driving the Scalable Application of Artificial Intelligence With the rapid development of large model technology, efficiently training, deploying, and managing these massive models has become a critical challenge. **Large model systems and platforms** have emerged to address this need, providing the infrastructure and toolchains necessary for the development and application of large-scale artificial intelligence models. They serve as the core engine driving the scalable application of AI. ### Core Features and Capabilities Large model systems and platforms typically offer the following core functionalities: 1. **Distributed Training**: - Supports distributed training for massive datasets and ultra-large models. - Provides efficient parallel computing and communication optimization, such as data parallelism, model parallelism, and pipeline parallelism. - Representative examples: Megatron-LM, DeepSpeed. 2. **Efficient Inference**: - Optimizes inference for large models to reduce latency and resource consumption. - Supports model compression, quantization, and acceleration techniques. - Representative examples: TensorRT, ONNX Runtime. 3. **Model Management and Deployment**: - Offers version control, monitoring, and updating capabilities for models. - Supports deployment across multiple environments, including cloud, edge, and devices. - Representative examples: MLflow, Kubeflow. 4. **Developer Tools and Ecosystem**: - Provides user-friendly APIs, SDKs, and visualization tools. - Builds open developer communities and ecosystems. - Representative examples: Hugging Face, OpenAI API. ### Representative Platforms and Systems The following are some notable large model systems and platforms: - **Hugging Face**: Offers a rich collection of pre-trained models and datasets, supporting model training, fine-tuning, and deployment. - **OpenAI API**: Provides powerful interfaces for large model services, enabling tasks like text generation and code generation. - **DeepSpeed**: Developed by Microsoft, focuses on distributed training and optimization for large-scale models. - **Colossal-AI**: Delivers efficient solutions for parallel training and inference, supporting ultra-large models. ### Future Development Trends The future development of large model systems and platforms will focus on the following directions: 1. **Performance Optimization**: Further improves training and inference efficiency while reducing resource consumption. 2. **Usability Enhancement**: Simplifies development processes and lowers the barrier to entry. 3. **Ecosystem Expansion**: Builds a more open and thriving developer ecosystem. 4. **Security and Trustworthiness**: Strengthens model security and explainability to ensure reliable applications. --- **In summary, large model systems and platforms are the critical enablers for the practical application of large model technology.** With continuous technological advancements and ecosystem improvements, they will provide stronger momentum for the scalable application of artificial intelligence, driving intelligent transformation across industries.

Jan 1, 1010

Scientific Large Model Research Group

The Scientific Large Model Research Group is dedicated to advancing interdisciplinary research in drug development, materials innovation, and energy optimization through state-of-the-art computational simulations.

Jan 1, 1005

Medical Imaging Large Model Research Group

The Nanjing University Medical Imaging Large Model Research Group has been deeply engaged in the field of intelligent medical imaging, focusing on efficient training and low-cost fine-tuning of large models to explore cutting-edge applications in medical image segmentation, auxiliary diagnosis, and precision treatment. Facing the challenge of high annotation costs, the group is dedicated to methods such as sparse supervision, efficient data utilization, and pseudo-label optimization to reduce reliance on large-scale manual annotations while enhancing model generalization and robustness.

Jan 1, 1004

Edge Large Model System Research Group

The Edge Large Model System Research Group focuses on frontier optimization techniques for large model systems. Centered on building a high-precision, low-latency, and scalable large model service framework, our research covers operator optimization, adaptive parameter tuning, and multimodal task scheduling.

Jan 1, 1003

Large Language Model System Research Group

The NASA research group of Nanjing University, in collaboration with renowned institutions such as Pengcheng Laboratory and Huawei Technologies Co., Ltd., has conducted comprehensive and in-depth research on key topics including large model training/inference performance and power consumption. The research achievements have not only been published at top conferences in the field of computer architecture, but have also been successfully deployed in relevant enterprises, making positive contributions to bridging the gap between theory and practice.

Dec 1, 1002