collaborators

6 papers

cs.LG2026

RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis

Robin Yadav, Qi Yan, Guy Wolf +2

A fundamental problem in organic chemistry is identifying and predicting the series of reactions that synthesize a desired target product molecule. Due to the combinatorial nature…

cs.CV2026

StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams

Zike Wu, Qi Yan, Xuanyu Yi +2

Real-time reconstruction of dynamic 3D scenes from uncalibrated video streams demands robust online methods that recover scene dynamics from sparse observations under strict latenc…

cs.LG2026

Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction

Yuanpei Gao, Qi Yan, Yan Leng +1

While deep learning methods have achieved strong performance in time series prediction, their black-box nature and inability to explicitly model underlying stochastic processes oft…

cs.LG2025

Score Augmentation for Diffusion Models

Liang Hou, Yuan Gao, Boyuan Jiang +6

Diffusion models have achieved remarkable success in generative modeling. However, this study confirms the existence of overfitting in diffusion model training, particularly in dat…

cs.CV2025

TrajFlow: Multi-modal Motion Prediction via Flow Matching

Qi Yan, Brian Zhang, Yutong Zhang +8

Efficient and accurate motion prediction is crucial for ensuring safety and informed decision-making in autonomous driving, particularly under dynamic real-world conditions that ne…

cs.CV2025

MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation

Yuxiang Fu, Qi Yan, Lele Wang +2

In this paper, we address the problem of human trajectory forecasting, which aims to predict the inherently multi-modal future movements of humans based on their past trajectories…