Han Zhao

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model AAAI 2026 ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver AAAI 2026 Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization UAI 2025 Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks NAACL 2025 ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning ICML 2025 Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference AAAI 2025 Multiobjective distribution matching ICML 2025 Accelerating Neural ODEs: A Variational Formulation-based Approach ICLR 2025 Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport ICLR 2025 VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation ICLR 2025 When LRP Diverges from Leave-One-Out in Transformers EMNLP 2025 MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning EMNLP 2025 Scaling Laws for Multilingual Language Models ACL 2025 Efficient Modality Selection in Multimodal Learning JMLR 2024 LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch NIPS 2024 FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning NIPS 2024 On the Expressive Power of Tree-Structured Probabilistic Circuits NIPS 2024 Learning Structured Representations with Hyperbolic Embeddings NIPS 2024 Most Influential Subset Selection: Challenges, Promises, and Beyond NIPS 2024 Dynamic Reactive Spiking Graph Neural Network AAAI 2024 Fair and Optimal Prediction via Post-Processing AAAI 2024 CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers ACL 2024 Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards ACL 2024 Fast 1-Wasserstein distance approximations using greedy strategies AISTATS 2024 Towards Practical Non-Adversarial Distribution Matching AISTATS 2024 Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation CVPR 2024 PiTe: Pixel-Temporal Alignment for Large Video-Language Model ECCV 2024 QUAR-VLA: Vision-Language-Action Model for Quadruped Robots ECCV 2024 Mitigating the Alignment Tax of RLHF EMNLP 2024 Semi-Supervised Reward Modeling via Iterative Self-Training EMNLP 2024 Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts EMNLP 2024 FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods ICLR 2024 Robust Multi-Task Learning with Excess Risks ICML 2024 Pairwise Alignment Improves Graph Domain Adaptation ICML 2024 Differentially Private Post-Processing for Fair Regression ICML 2024 Gradual Domain Adaptation: Theory and Algorithms JMLR 2024 RL2AC: Reinforcement Learning-based Rapid Online Adaptive Control for Legged Robot Robust Locomotion RSS 2024 An Adaptive Prompt Generation Framework for Task-oriented Dialogue System EMNLP 2023 Understanding the Impact of Adversarial Robustness on Accuracy Disparity ICML 2023 Structural Re-weighting Improves Graph Domain Adaptation ICML 2023 Fair and Optimal Classification via Post-Processing ICML 2023 Adaptive Power Method: Eigenvector Estimation from Sampled Data ALT 2023 Efficient Learning of Linear Graph Neural Networks via Node Subsampling NIPS 2023 Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective NIPS 2023 Adaptation Augmented Model-based Policy Optimization JMLR 2023 Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning CVPR 2023 Learning Structured Representations by Embedding Class Hierarchy ICLR 2023 Learning List-Level Domain-Invariant Representations for Ranking NIPS 2023 Conditional Supervised Contrastive Learning for Fair Text Classification EMNLP 2022 Inherent Tradeoffs in Learning Fair Representations JMLR 2022 Fundamental Limits and Tradeoffs in Invariant Representation Learning JMLR 2022 DD-TIG at Constraint@ACL2022: Multimodal Understanding and Reasoning for Role Labeling of Entities in Hateful Memes ACL 2022 DD-TIG at SemEval-2022 Task 5: Investigating the Relationships Between Multimodal and Unimodal Information in Misogynous Memes Detection and Classification NAACL 2022 Cross-Lingual Transfer with Class-Weighted Language-Invariant Representations ICLR 2022 Conditional Contrastive Learning with Kernel ICLR 2022 Greedy modality selection via approximate submodular maximization UAI 2022 Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond ICML 2022 Provable Domain Generalization via Invariant-Feature Subspace Recovery ICML 2022 Invariant Information Bottleneck for Domain Generalization AAAI 2022 DD-TIG at SemEval-2022 Task 5: Investigating the Relationships Between Multimodal and Unimodal Information in Misogynous Memes Detection and Classification SEMEVAL 2022 Exploring Gradient-Based Multi-directional Controls in GANs ECCV 2022 Rethinking Controllable Variational Autoencoders CVPR 2022 Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning COLING 2022 Online Continual Adaptation with Active Self-Training AISTATS 2022 Towards Return Parity in Markov Decision Processes AISTATS 2022 Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation ICML 2021 EventKE: Event-Enhanced Knowledge Graph Embedding EMNLP 2021 On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections ICLR 2021 Self-supervised Representation Learning with Relative Predictive Coding ICLR 2021 Quantifying and Improving Transferability in Domain Generalization NIPS 2021 Understanding and Mitigating Accuracy Disparity in Regression ICML 2021 Information Obfuscation of Graph Neural Networks ICML 2021 Graph Debiased Contrastive Learning with Joint Representation Clustering IJCAI 2021 Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation CVPR 2021 Model-based Policy Optimization with Unsupervised Model Adaptation NIPS 2020 Deep Fair Clustering for Visual Learning CVPR 2020 Neural Methods for Point-wise Dependency Estimation NIPS 2020 Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation NIPS 2020 Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift NIPS 2020 On Learning Language-Invariant Representations for Universal Machine Translation ICML 2020 Conditional Learning of Fair Representations ICLR 2020 Continual Learning with Adaptive Weights (CLAW) ICLR 2020 Inherent Tradeoffs in Learning Fair Representations NIPS 2019 Learning Neural Networks with Adaptive Regularization NIPS 2019 On Strategyproof Conference Peer Review IJCAI 2019 On Learning Invariant Representations for Domain Adaptation ICML 2019 Efficient Multitask Feature and Relationship Learning UAI 2019 Adversarial Multiple Source Domain Adaptation NIPS 2018 Linear Time Computation of Moments in Sum-Product Networks NIPS 2017 A Unified Approach for Learning the Parameters of Sum-Product Networks NIPS 2016 Collapsed Variational Inference for Sum-Product Networks ICML 2016 Online and Distributed Bayesian Moment Matching for Parameter Learning in Sum-Product Networks AISTATS 2016 Online Algorithms for Sum-Product Networks with Continuous Variables PGM 2016 On the Relationship between Sum-Product Networks and Bayesian Networks ICML 2015 Self-Adaptive Hierarchical Sentence Model IJCAI 2015