Jiaming Zhang

10

Papers

83

Total Citations

Papers (10)

Adversarial Prompt Tuning for Vision-Language Models

Navigating Open Set Scenarios for Skeleton-Based Action Recognition

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning

NeurIPS 2025arXiv

SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity

One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models

Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation

Scene-agnostic Pose Regression for Visual Localization