Xiao Li

10

Papers

76

Total Citations

Papers (10)

ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification

Language-Driven Anchors for Zero-Shot Adversarial Robustness

PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition

StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data

PBCAT: Patch-Based Composite Adversarial Training against Physically Realizable Attacks on Object Detection

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video

Neural Collapse in Multi-label Learning with Pick-all-label Loss