activity
20242026
collaborators

5 papers

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.CL2025

Test-Time Steering for Lossless Text Compression via Weighted Product of Experts

Qihang Zhang, Muchen Li, Ziao Wang +2

Lossless compression techniques are crucial in an era of rapidly growing data. Traditional universal compressors like gzip offer low computational overhead, high speed, and broad a…

cs.CV2025

Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Models

Bicheng Xu, Qi Yan, Renjie Liao +2

We introduce a framework for joint grounded scene graph - image generation, a challenging task involving high-dimensional, multi-modal structured data. To effectively model this co…

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…

cs.IT2024

An Information-Theoretic Framework for Out-of-Distribution Generalization with Applications to Stochastic Gradient Langevin Dynamics

Wenliang Liu, Guanding Yu, Lele Wang +1

We study the Out-of-Distribution (OOD) generalization in machine learning and propose a general framework that establishes information-theoretic generalization bounds. Our framewor…