Lichao Sun

South China Agricultural University — China

Computer Science · Physical Sciences

44h-index8.4kcitations283works13.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Privacy-Preserving Technologies in Data(57), Topic Modeling(51), Adversarial Robustness in Machine Learning(43), Natural Language Processing Techniques(30), Advanced Graph Neural Networks(29)

Publications283 total

MM‐LIMA: Less Is More for Alignment in Multi‐Modal Datasets
Artificial Intelligence for Engineering·2025Open Access
Prompt engineering for healthcare: Methodologies and applications
Meta-Radiology·2025· 3 citedOpen Access
Jailbreaking LLMs Through Alignment Vulnerabilities in Out-of-Distribution Settings
2025· 1 citedOpen Access
Scaling up biomedical vision-language models: Fine-tuning, instruction tuning, and multi-modal learning
Journal of Biomedical Informatics·2025· 1 citedOpen Access
Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
arXiv (Cornell University)·2025Open Access
The Role of Computing Resources in Publishing Foundation Model Research
arXiv (Cornell University)·2025Open Access
Agentic AutoSurvey: Let LLMs Survey LLMs
arXiv (Cornell University)·2025Open Access
SAMed-2: Selective Memory Enhanced Medical Segment Anything Model
Lecture notes in computer science·2025· 1 cited
Continual Diffuser (CoD): Mastering Continual Offline RL With Experience Rehearsal
IEEE Transactions on Neural Networks and Learning Systems·2025· 2 cited
Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach
ACM Transactions on Software Engineering and Methodology·2025· 2 cited
RadFabric: Agentic AI System with Reasoning Capability for Radiology
arXiv (Cornell University)·2025· 1 citedOpen Access
Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction
arXiv (Cornell University)·2025Open Access
BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
2025· 2 cited
Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
arXiv (Cornell University)·2025Open Access
Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
arXiv (Cornell University)·2025Open Access
Decision Flow Policy Optimization
arXiv (Cornell University)·2025Open Access
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
arXiv (Cornell University)·2025Open Access
MMLU-Reason: Benchmarking Multi-Task Multi-modal Language Understanding and Reasoning
arXiv (Cornell University)·2025Open Access
Generative AI for Autonomous Driving: Frontiers and Opportunities
arXiv (Cornell University)·2025Open Access
Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
arXiv (Cornell University)·2025Open Access
page 1 of 15Next →

Frequent Co-authors

Philip S. Yu(23), Lifang He(12), Hao Peng(7), Lingjuan Lyu(6), Zhiling Yan(6), Yutong Dai(5), Tianming Liu(5), Qiben Yan(4), Witawas Srisa‐an(4), Congying Xia(4), Yixin Liu(4), Kai Zhang(4), Caiming Xiong(4), Yingtong Dou(4), Carl Yang(4), Ji Wang(4), Zhengliang Liu(4), Quanzheng Li(4), Dezhong Yao(4), Hai Jin(4)