Han Zhao

papers

672

total citations

papers (25)

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

CVPR 2021arXiv

113

citations

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

AAAI 2025arXiv

110

citations

Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning

CVPR 2023arXiv

citations

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

NEURIPS 2023arXiv

citations

Quantifying and Improving Transferability in Domain Generalization

NEURIPS 2021arXiv

citations

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

ICLR 2025arXiv

citations

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

ICML 2025arXiv

citations

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

NEURIPS 2025arXiv

citations

Exploring Gradient-Based Multi-directional Controls in GANs

ECCV 2022arXiv

citations

Learning List-Level Domain-Invariant Representations for Ranking

NEURIPS 2023arXiv

citations

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

NEURIPS 2025arXiv

citations

Differentially Private Post-Processing for Fair Regression

ICML 2024arXiv

citations

Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation

CVPR 2024

citations

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

NEURIPS 2025arXiv

citations

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation

NEURIPS 2020arXiv

citations

Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport

ICLR 2025arXiv

citations

Rethinking Controllable Variational Autoencoders

CVPR 2022

citations

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

NEURIPS 2020

citations

Efficient Learning of Linear Graph Neural Networks via Node Subsampling

NEURIPS 2023

citations

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

NEURIPS 2025arXiv

citations

Deep Fair Clustering for Visual Learning

CVPR 2020

citations

Han Zhao

papers (25)

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

Quantifying and Improving Transferability in Domain Generalization

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

Neural Methods for Point-wise Dependency Estimation

Model-based Policy Optimization with Unsupervised Model Adaptation

Pairwise Alignment Improves Graph Domain Adaptation

Robust Multi-Task Learning with Excess Risks

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

Exploring Gradient-Based Multi-directional Controls in GANs

Learning List-Level Domain-Invariant Representations for Ranking

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

Differentially Private Post-Processing for Fair Regression

Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation

Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport

Rethinking Controllable Variational Autoencoders

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

Efficient Learning of Linear Graph Neural Networks via Node Subsampling

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

Deep Fair Clustering for Visual Learning

papers (25)

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

Quantifying and Improving Transferability in Domain Generalization

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

Neural Methods for Point-wise Dependency Estimation

Model-based Policy Optimization with Unsupervised Model Adaptation

Pairwise Alignment Improves Graph Domain Adaptation

Robust Multi-Task Learning with Excess Risks

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

Exploring Gradient-Based Multi-directional Controls in GANs

Learning List-Level Domain-Invariant Representations for Ranking

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

Differentially Private Post-Processing for Fair Regression

Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation

Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport

Rethinking Controllable Variational Autoencoders

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

Efficient Learning of Linear Graph Neural Networks via Node Subsampling

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

Deep Fair Clustering for Visual Learning