Junping Li

I’m Junping Li, MS in Marine Science at Shanghai Jiao Tong University and BE in Automation (EECS) at Ocean University of China. I study large model and applications at AI Institute, Shanghai Jiao Tong University, prior to this, I studied control & deep learning of cross environment vehicle, such as factor, condition, control strategy and deep reinforcement learning, at Shanghai Jiao Tong University. During my university years, I was awarded Outstanding Student, Outstanding Graduate, Academic Excellence Scholarship and Practice Scholarship.

My research covers model training, inference, agent and applications, such as interaction of multiple models in space, mapping nonlinearity of modal space, and social simulation of agent or model space with cognition friction or other social factors. I have been learning and enjoy acquiring new knowledge, such as AI trend, linguistics, causal inference, cognitive science, game theory and so on, also interested in society, sometimes thinking something interesting: human non Bayesian or non scientific mind but enough natural/effective, fuzzy learning that we in most cases are based on rules and fuzzy logic, with explainable expression and network compatibility.

I hope to combine AI, psychology, linguistics, cybernetics and multiple disciplines to propose new ideas, theories and works, and make contributions to the development of human and society and the world we live in.

Projects & Publications

Large Model Multi-Agent Social Simulation with Social Factors

Junping Li, et al. Large model multi-agent social simulation with cognitive friction. in preparation, 2026.

Integrate cognitive dissonance theory in psychology and conflict functionalism in sociology to form the friction coefficient, consist of semantic distance, value conflict, emotional polarity difference or others, for the issues of excessive smoothness and false consensus in social simulations.

Interaction of Multiple Large Models in the Perspective of Space

Junping Li, Y Bai, S Wen, et al. Interaction of Multiple Large Models in Representation Space: A Comprehensive Survey. Preprint, 2025. junpingli.com/p/interact_multi_lm_space

Spatial representation and cross-modal alignment & mapping; Model merging & ensembling in representation space; Multi-agent system, representation space interaction, social simulation and metaphor/evolution; Geometric analysis, interpretability and theory of space and interaction.

Project Large Model Know System Engineering

junpingli.com/proj_lm_kn_sys_eng

Machine learning and deep learning fundamental, Transformer, language model, Training, Fine-tuning and RL, Inference, Large model advance, Multi modal, Agent, Field application

Nonlinear Control and Deep Reinforcement Learning of Cross Environment Vehicle

Junping Li, H Zhou, D Lu, et al. Nonlinear and reinforcement learning control for motion of hybrid aerial underwater vehicle. Neural Computing and Applications, 2025.

Proposed a 3-D space cross model; Key issues: uncertainty, cross environment(CE), constraint of environment difference; Nonlinear control laws with robustness, adaptation and fuzzy logic; Deep reinforcement learning of CE vehicle by deterministic policy, neural networks and temporal difference learning; Various methods in the tracking cases of issues.

Cross Domain Strategy, Factors and Conditions

Junping Li, Y Jin, R Hu, et al. Trajectory tracking control of hybrid aerial underwater vehicle subject to wind and wave disturbances. Journal of Intelligent & Robotic Systems, 2024.

Proposed a strategy to address the control convergence problem caused by the large change of environment transition; Key factors and conditions of the cross environment in the various scenarios with multiple variables; Critical relations and feasible domains of the factors that control conditions need to meet.

Skills

C/C++, Matlab & Simulink, Python, LaTeX, PyTorch, TensorBoard, OpenBayes, drawio, Transformers, Datasets, Pre-training, Continued training, MoE, SFT/instruct fine-tuning, PEFT, LoRA, unsloth, llama-factory, RLHF/AIF, DPO, PPO, GRPO, trl, API, function call, prompt engineering, RAG, llamaindex, milvus, RAGFlow, Agent, CoT, ReAct, Reflection, MCP, langchain/langgraph, Multi modal, CLIP, LLaVA, Distributed parallel, Accelerate, Deepspeed, FastAPI, vllm, Quantization, Distillation

Academic Services

Neural Computing and Applications, ICRA, IROS

Contact

Email: ljp.id [at] sjtu.edu.cn
Web: junpingli.com
Address: Shanghai Jiao Tong University, 800 Dongchuan Road, Shanghai 200240