About Me
Here is Shifeng XIE.
I am a PhD student in Prof. Themis Palpanas’s group at Université Paris Cité. Previously, I studied engineering at Télécom Paris and the Institut Polytechnique de Paris. My research interests focus on time series foundation models and agentic systems for forecasting, reasoning, and decision-making.
I am planning to apply for PhD intern positions in 2027 and welcome opportunities worldwide!
If you are interested in my work, please feel free to reach out: shifeng.xie@telecom‑paris.fr.
Research Experiences
Time Series Foundation Models
Huawei Paris Noah’s Ark Lab, France
February 2025 – August 2025
- Designed classification time‑series foundation models and demonstrated that high‑performance pretraining is possible using only synthetic data.
- First author of “CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data Only,” accepted by ICML 2025 Workshop on Foundation Models for Structured Data (Best Time Series Paper).
- Collaborated with Ievgen Redko and researchers from Huawei Paris.
In‑Context Learning and Mixture of Experts
Stellantis, France
July 2024 – January 2025
- Investigated in‑context learning and gradient descent in transformers and mixture‑of‑experts (MoE) models.
- First author of “The Initialization Determines Whether In‑Context Learning Is Gradient Descent,” published in Transactions on Machine Learning Research (TMLR), 2025.
- Worked closely with Rui Yuan, Simone Rossi and Thomas Hannagan.
Graph Neural Networks and Graph Representation Learning
Télécom Paris (Polytechnic Institute of Paris), France
December 2023 – September 2024
- Conducted research on variational graph contrastive learning and subgraph Gaussian embedding for self‑supervised graph representation.
- First author of “Variational Graph Contrastive Learning,” accepted by NeurIPS 2024 Workshop on Self‑Supervised Learning – Theory and Practice.
- First author of “Subgraph Gaussian Embedding Contrast for Self‑Supervised Graph Representation Learning,” accepted by ECML‑PKDD 2025.
- Supervised by Jhony H. Giraldo.
Image Processing and High‑Dynamic‑Range Reconstruction
Xidian University, China
February 2023 – September 2023
- Developed FTUnet for single HDR image reconstruction.
- First author of “FTUnet: Feature Transferred U‑Net for Single HDR Image Reconstruction,” accepted by ACM Multimedia Asia (MMA) 2023, oral presentation.
- Advised by Liu Yi.
Data Twin and Intelligent Healthcare
Xidian University, China
April 2021 – September 2021
- Researched the feasibility of intelligent healthcare based on digital twin and data mining.
- First author of “Feasibility Study of Intelligent Healthcare Based on Digital Twin and Data Mining,” accepted by CISAI 2021.
Education
Master in Engineering – Signal Processing for Artificial Intelligence
Télécom Paris & Polytechnic Institute of Paris, France
August 2023 – Present
- Current grade: 15.3 / 20.
Summer Exchange Program – Machine Learning
McGill University, Canada
July 2021 – August 2021
- Achieved grade: A.
Bachelor of Engineering – Electronic Information Engineering
Xidian University, China
August 2019 – May 2023
- GPA: 3.8 / 4.0.
- Rank: 4 / 97.
Selected Projects
- Pretraining tiny vision & language models (≈ 2 billion parameters): Trained mixture‑of‑experts models using 8 A100 80 GB GPUs on the C4 and ImageNet datasets.
- Fine‑tuning MoE language models with permutation symmetries and LoRA (patented): Applied permutation symmetries and Low‑Rank Adaptation to MoE models (e.g., Mistral, DeepSeek, Qwen) to improve efficiency.
- Unsupervised face recognition with PCA and ICA: Implemented PCA and ICA to extract and modify facial features, enhancing recognition accuracy.
- Self‑supervised learning for medical image classification: Developed contrastive learning methods on the MedMNIST database to learn representations without annotations.
- Neural network parameter diffusion (patented): Compressed experts from MoE models into a latent space via autoencoders and trained latent diffusion models to generate new experts.
Skills & Service
- Languages: Chinese (native), English (C1), French (B2).
- Programming: Python (PyTorch, TensorFlow, JAX, SciPy, Pandas), JavaScript, Java, C++ and C.
- Hardware: Arduino, STM32, SolidWorks, VHDL, ARM and RISC.
- Professional service: Reviewer for NeurIPS 2024 Workshop on Compression, COLM 2025, and NeurIPS 2025.