About Xupeng Chen

Basic Info

Hi, It’s Xupeng. I obtained my Ph.D. on May 2025 from NYU Tandon School, advised by Prof. Yao Wang in NYU Video Lab. I am co-advised by Prof. Adeen Finker

<aside> 💡

Xupeng Chen is a Research Scientist at TikTok

Trained multimodal LLMs with SFT + RL (RLHF / reward modeling variants), focusing on reasoning quality and uncertainty calibration.
Researched grounding & alignment methods including verifiable reward design, retrieval-augmented reasoning (RAG), and semantic consistency regularization.
Built production-grade multimodal moderation systems for e-commerce, supporting multi-market deployment with improved precision/recall trade-offs and reduced labeling cost. </aside>

Chen, X., Wang, R., Khalilian-Gourtani, A., Yu, L., Dugan, P., Friedman, D., Doyle, W., Devinsky, O., Wang, Y. and Flinker, A. "A Neural Speech Decoding Framework Leveraging Deep Learning and Speech Synthesis." Nature Machine Intelligence (2024)}. doi: 10.1038/s42256-024-00824-8
Wang, R., Chen, X., Khalilian-Gourtani, A., Yu, L., Dugan, P., Friedman, D., Doyle, W., Devinsky, O., Wang, Y. and Flinker, A. "Distributed feedforward and feedback cortical processing supports human speech production." Proceedings of the National Academy of Sciences (PNAS) 120, no. 42 (2023): e2300255120. doi:10.1073/pnas.2300255120
Chen, X., Lai, Z, Ruan, K, Liu, J, Chen, S. "R-LLaVA: Advancing Biomedical VQA through Doctor-Guided Region of Interest Annotation." IJCNN 2025 (2024)
Christou, P., Chen, S., Chen, X., Dube, P. "Test Time Learning for Time Series Forecasting." NeurIPS 2024 Workshop on Time Series in the Age of Large Models (2024) link