6 papers
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
Zhenhan Fang, Aixin Tan, Jian Huang
Constructing valid and informative conformal prediction regions for multi-dimensional outputs remains a fundamental challenge. While conformal prediction provides finite-sample, di…
Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching
Fangran Miao, Jian Huang, Ting Li
Human motion generation is often learned in Euclidean spaces, although valid motions follow structured non-Euclidean geometry. We present Riemannian Motion Generation (RMG), a unif…
Conditional Stochastic Interpolation for Generative Learning
Ding Huang, Jian Huang, Ting Li +1
We propose a conditional stochastic interpolation (CSI) method for learning conditional distributions. CSI is based on estimating probability flow equations or stochastic different…
DeepSuM: Deep Sufficient Modality Learning Framework
Zhe Gao, Jian Huang, Ting Li +1
Multimodal learning has become a pivotal approach in developing robust learning models with applications spanning multimedia, robotics, large language models, and healthcare. The e…
Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation
Yifan Feng, Jiangang Huang, Shaoyi Du +6
We introduce Hyper-YOLO, a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Traditional YOL…
Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
Ding Huang, Ting Li, Jian Huang
We propose a Bayesian framework for fine-tuning large diffusion models with a novel network structure called Bayesian Power Steering (BPS). We clarify the meaning behind adaptation…