Ang Li

Affiliations

DeepMind

papers

1,148

total citations

papers (24)

Hybrid Models for Open Set Recognition

ECCV 2020arXiv

204

citations

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

CVPR 2020arXiv

156

citations

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

NEURIPS 2021arXiv

110

citations

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

ECCV 2022arXiv

citations

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

ICML 2024arXiv

citations

PersonalLLM: Tailoring LLMs to Individual Preferences

ICLR 2025arXiv

citations

SphereFed: Hyperspherical Federated Learning

ECCV 2022arXiv

citations

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

CVPR 2024arXiv

citations

Adversarial Examples Are Not Real Features

NEURIPS 2023arXiv

citations

Unit Selection with Nonbinary Treatment and Effect

AAAI 2024arXiv

citations

FedNAR: Federated Optimization with Normalized Annealing Regularization

NEURIPS 2023arXiv

citations

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

ICML 2024arXiv

citations

Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning

AAAI 2025

citations

Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling

NEURIPS 2025arXiv

citations

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

CVPR 2021

citations

PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning

ICCV 2023

citations

Ang Li

Affiliations

papers (24)

Hybrid Models for Open Set Recognition

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

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

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

Learning to Incentivize Other Learning Agents

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Semi-Supervised Vision Transformers

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

LLM Generated Persona is a Promise with a Catch

AutoReP: Automatic ReLU Replacement for Fast Private Network Inference

Probabilities of Causation with Nonbinary Treatment and Effect

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

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

PersonalLLM: Tailoring LLMs to Individual Preferences

SphereFed: Hyperspherical Federated Learning

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

Adversarial Examples Are Not Real Features

Unit Selection with Nonbinary Treatment and Effect

FedNAR: Federated Optimization with Normalized Annealing Regularization

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning

Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling

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

PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning

papers (24)

Hybrid Models for Open Set Recognition

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

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

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

Learning to Incentivize Other Learning Agents

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Semi-Supervised Vision Transformers

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

LLM Generated Persona is a Promise with a Catch

AutoReP: Automatic ReLU Replacement for Fast Private Network Inference

Probabilities of Causation with Nonbinary Treatment and Effect

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

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

PersonalLLM: Tailoring LLMs to Individual Preferences

SphereFed: Hyperspherical Federated Learning

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

Adversarial Examples Are Not Real Features

Unit Selection with Nonbinary Treatment and Effect

FedNAR: Federated Optimization with Normalized Annealing Regularization

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning

Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling

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

PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning