Xiao Li

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective

On the Inherent Vulnerability of Randomized Models to Nagging Attack

ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification

Efficient Neuron Segmentation in Electron Microscopy by Affinity-Guided Queries

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

HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks