Chaowei Xiao

papers

2,349

total citations

papers (22)

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

NEURIPS 2022arXiv

452

citations

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

NEURIPS 2020arXiv

358

citations

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

CVPR 2023arXiv

349

citations

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

ECCV 2020arXiv

199

citations

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

NEURIPS 2022arXiv

citations

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

CVPR 2023arXiv

citations

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

CVPR 2024arXiv

citations

DataGen: Unified Synthetic Dataset Generation via Large Language Models

ICLR 2025arXiv

citations

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception

ICLR 2024arXiv

citations

SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination

ECCV 2022arXiv

citations

LeanAgent: Lifelong Learning for Formal Theorem Proving

ICLR 2025arXiv

citations

Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation

ECCV 2024arXiv

citations

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines

ICML 2025arXiv

citations

Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions

NEURIPS 2021

citations

Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings?

ICCV 2021

citations

Position: TrustLLM: Trustworthiness in Large Language Models

ICML 2024

citations

Chaowei Xiao

papers (22)

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

Long-Short Transformer: Efficient Transformers for Language and Vision

On the Exploitability of Instruction Tuning

AugMax: Adversarial Composition of Random Augmentations for Robust Training

Dolphins: Multimodal Language Model for Driving

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

AdvDO: Realistic Adversarial Attacks for Trajectory Prediction

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

DataGen: Unified Synthetic Dataset Generation via Large Language Models

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception

SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination

LeanAgent: Lifelong Learning for Formal Theorem Proving

Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines

Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions

Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings?

Position: TrustLLM: Trustworthiness in Large Language Models

papers (22)

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

Long-Short Transformer: Efficient Transformers for Language and Vision

On the Exploitability of Instruction Tuning

AugMax: Adversarial Composition of Random Augmentations for Robust Training

Dolphins: Multimodal Language Model for Driving

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

AdvDO: Realistic Adversarial Attacks for Trajectory Prediction

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

DataGen: Unified Synthetic Dataset Generation via Large Language Models

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception

SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination

LeanAgent: Lifelong Learning for Formal Theorem Proving

Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines

Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions

Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings?

Position: TrustLLM: Trustworthiness in Large Language Models