Haozhao Wang

papers

713

total citations

papers (21)

Parameterized Knowledge Transfer for Personalized Federated Learning

NEURIPS 2021arXiv

231

citations

PMR: Prototypical Modal Rebalance for Multimodal Learning

CVPR 2023arXiv

161

citations

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

ICLR 2025arXiv

citations

Towards Efficient Replay in Federated Incremental Learning

CVPR 2024arXiv

citations

Aligning Language Models with Human Preferences via a Bayesian Approach

NEURIPS 2023arXiv

citations

Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching

ECCV 2024arXiv

citations

FR: Folded Rationalization with a Unified Encoder

NEURIPS 2022arXiv

citations

D-Separation for Causal Self-Explanation

NEURIPS 2023arXiv

citations

Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement

AAAI 2024arXiv

citations

ProCC: Progressive Cross-Primitive Compatibility for Open-World Compositional Zero-Shot Learning

AAAI 2024arXiv

citations

FedBAT: Communication-Efficient Federated Learning via Learnable Binarization

ICML 2024arXiv

citations

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

ICML 2025arXiv

citations

Knowledge-Aware Parameter Coaching for Personalized Federated Learning

AAAI 2024

citations

Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization

ICLR 2025arXiv

citations

Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection

ECCV 2024arXiv

citations

Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets

ICML 2025arXiv

citations

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

AAAI 2024arXiv

citations

Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack

ICCV 2025arXiv

citations

Haozhao Wang

papers (21)

Parameterized Knowledge Transfer for Personalized Federated Learning

PMR: Prototypical Modal Rebalance for Multimodal Learning

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

Towards Efficient Replay in Federated Incremental Learning

Aligning Language Models with Human Preferences via a Bayesian Approach

Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching

FR: Folded Rationalization with a Unified Encoder

D-Separation for Causal Self-Explanation

Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement

ProCC: Progressive Cross-Primitive Compatibility for Open-World Compositional Zero-Shot Learning

FedBAT: Communication-Efficient Federated Learning via Learnable Binarization

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

Knowledge-Aware Parameter Coaching for Personalized Federated Learning

Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization

Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection

Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack

DaFKD: Domain-Aware Federated Knowledge Distillation

C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation

BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach

papers (21)

Parameterized Knowledge Transfer for Personalized Federated Learning

PMR: Prototypical Modal Rebalance for Multimodal Learning

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

Towards Efficient Replay in Federated Incremental Learning

Aligning Language Models with Human Preferences via a Bayesian Approach

Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching

FR: Folded Rationalization with a Unified Encoder

D-Separation for Causal Self-Explanation

Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement

ProCC: Progressive Cross-Primitive Compatibility for Open-World Compositional Zero-Shot Learning

FedBAT: Communication-Efficient Federated Learning via Learnable Binarization

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

Knowledge-Aware Parameter Coaching for Personalized Federated Learning

Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization

Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection

Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack

DaFKD: Domain-Aware Federated Knowledge Distillation

C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation

BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach