Efficient LLM Inference
KV-cache reuse, semantic cache distillation, state transfer, selective recomputation, and bandwidth-aware serving.
AI systems, efficient inference, trustworthy machine learning
Qianli Ma
I am a Ph.D. student at Beijing Normal University, working on efficient LLM systems, semantic state transfer, multi-candidate reasoning, and security-oriented machine learning.
Research
Building efficient and reliable AI systems.
Reasoning Pipelines
Candidate construction, fixed-verifier reranking, coverage-conversion gaps, and answer-mode compatibility.
Trustworthy ML
Backdoor attacks, frequency-domain robustness, model behavior under perturbation, and security evaluation.
Applied Computer Vision
Vision pipelines for smart livestock systems, identity-related signals, weight estimation, and agricultural AI.
Selected publications
Recent work
Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching
Qianli Ma, Zhiqing Tang, Hanshuai Cui, Zhi Yao, Weijia Jia
Proceedings of the 43rd International Conference on Machine Learning.
Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
Qianli Ma
Manuscript under review.
Stealthy Frequency-Domain Backdoor Attacks: Fourier Decomposition and Fundamental Frequency Injection
Qianli Ma, Junping Qin, Kai Yan, Lei Wang, Hao Sun
Perceptually Imperceptible Backdoor Attacks Using High-Frequency Information in Deep Learning Models
Qianli Ma, Junping Qin, Yin Cao, Jiaqi Ren
FastFaceCLIP: A Lightweight Text-driven High-Quality Face Image Manipulation
Jiaqi Ren, Junping Qin, Qianli Ma, Yin Cao
Experience
Systems-oriented research with applied ML depth.
Semantic cache distillation for bandwidth-limited deployment
Designed REUSE and PATCH mechanisms for state transfer between shared-architecture, weight-mismatched models.
Backdoor behavior and frequency-domain attack analysis
Studied stealthy backdoor mechanisms, trigger design, and robustness-oriented model analysis.
Computer vision for livestock systems
Built applied pipelines for cattle image acquisition, weight estimation, visual signal analysis, and farm decision support.
Contact