关于我
我是占俊飞，来自中国，现为帝国理工学院计算系博士生，师从 Giuliano Casale 教授。我于宾夕法尼亚大学获得电气工程专业硕士学位，硕士期间的研究由 Saswati Sarkar 教授指导。本科期间的研究分别由 Tengjiao He 教授和 Kwan-Wu Chin 教授指导。
我的研究兴趣主要集中在 optimization、Large Language Models (LLMs) 和数据驱动决策，特别是在能量受限的计算环境中。我主导和参与了多个关于 task scheduling、LLMs 和 green IoT networks 的研究项目。我热衷于将数学建模、机器学习和控制理论相结合，以解决现实世界的系统挑战。
在学术之外，和朋友聚餐、社交是我最喜欢的活动之一。运动也是我生活中重要的一部分，我曾在短跑、攀岩、赛艇和乒乓球方面获得过奖项。
- Large Language Models
- Optimization
- Network Science
计算机科学博士
帝国理工学院，英国
电气工程硕士
宾夕法尼亚大学，美国
应用数学与信息计算科学双学士
伯明翰大学（英国）& 暨南大学（中国）
- Sep 24 2026
在广东深圳举办的「EvoTavern 进化酒馆黑客松｜深圳站」中，我们获得了原生 Agent 赛道冠军。我们的作品 Frowang 是一款 AI 协作的论文阅读工作台。
- Sep 04 2026
很高兴入选 GMI Cloud 的 GMI Clouder 大使计划，成为其全球开发者、创作者、创业者、研究者与 AI 领袖社区的一员。
- Aug 21 2026
论文「Trains but Doesn’t Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers」被 The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026) 录用。
- Jul 10 2026
论文「Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference」被 The 34th ACM International Conference on Multimedia (ACM MM 2026) 录用。
- May 10 2026
论文「Orchestrating Data Collection and Computation in Green IoT Networks」被 IEEE Internet of Things Journal 录用。
- Apr 27 2026
合作论文「Graph Learning-based Update Manipulation Attack on Federated Fine-Tuning of LLMs over Wireless Networks」被 The 24th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys '26 Posters) 录用。
- Apr 24 2026
获 2026 ESE Department Master's Top 10% GPA Award，表彰在硕士阶段的学术表现。
- Feb 13 2026
合作论文「Joint Function Configuration and Multislot Offloading in Solar-Powered Serverless Edge Computing」被 IEEE Internet of Things Journal 录用。
- Jan 16 2026
合作论文「SpikeBP: Efficient Spike-Driven Transformer for Blood Pressure Waveform Generation with Frequency Knowledge Distillation」被 IEEE ICASSP 2026 选为 口头报告（Oral）。
- EMNLP 2026
Trains but Doesn’t Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026. To appear
- ACM MM 2026
Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference
Proceedings of the 34th ACM International Conference on Multimedia (ACM MM), 2026. To appear · arXiv:2607.09520
- AAAI 2026
PRISM: Privacy-Aware Routing for Adaptive Cloud–Edge LLM Inference via Semantic Sketch Collaboration
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026
- IoT-J 2026
Orchestrating Data Collection and Computation in Green IoT Networks
IEEE Internet of Things Journal, 2026
- IoT-J 2026
Joint Function Configuration and Multi-Slot Offloading in Solar-Powered Serverless Edge Computing
IEEE Internet of Things Journal, 2026
- ICASSP 2026
SpikeBP: Efficient Spike-Driven Transformer for Blood Pressure Waveform Generation with Frequency Knowledge Distillation
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026 · Oral
- MobiSys 2026
Poster: Graph Learning-based Update Manipulation Attack on Federated Fine-Tuning of LLMs over Wireless Networks
Proceedings of the 24th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys Posters), 2026
- SMC 2025
RL-Enhanced Disturbance-Aware MPC for Fast and Robust UAV Trajectory Tracking
IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2025
- IEEE LNET 2024
Task Offloading and Approximate Computing in Solar Powered IoT Networks
IEEE Networking Letters, 6(1), 26–30, 2024
最新的具体出版物，请关注我的谷歌学术主页。
访客地图
过去 24 小时的访客位置