Ang Li

31

Papers

145

Total Citations

Papers (31)

Agent S: An Open Agentic Framework that Uses Computers Like a Human

LLM Generated Persona is a Promise with a Catch

NeurIPS 2025arXiv

Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning

MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

Coordinating Multiple Disparity Proposals for Stereo Computation

Generating Holistic 3D Scene Abstractions for Text-Based Image Retrieval

Dynamic Zoom-In Network for Fast Object Detection in Large Images

NISP: Pruning Networks Using Neuron Importance Score Propagation

PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving

Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Visual Relationship Detection With Internal and External Linguistic Knowledge Distillation

Learning Visual N-Grams From Web Data

Layout-Induced Video Representation for Recognizing Agent-in-Place Actions

Cross-View Policy Learning for Street Navigation

AutoReP: Automatic ReLU Replacement for Fast Private Network Inference

PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning

Hybrid Models for Open Set Recognition

Short-Term and Long-Term Context Aggregation Network for Video Inpainting

Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training

SphereFed: Hyperspherical Federated Learning

Semi-Supervised Vision Transformers

Selective Encoding for Recognizing Unreliably Localized Faces

Probabilities of Causation with Nonbinary Treatment and Effect

Unit Selection with Nonbinary Treatment and Effect

Learning to Incentivize Other Learning Agents

FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective

Adversarial Examples Are Not Real Features

FedNAR: Federated Optimization with Normalized Annealing Regularization