Han Zhao

33

Papers

274

Total Citations

Papers (33)

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

A Unified Approach for Learning the Parameters of Sum-Product Networks

NeurIPS 2016arXiv

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

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

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

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

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

Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport

Linear Time Computation of Moments in Sum-Product Networks

NeurIPS 2017arXiv

Exploring Gradient-Based Multi-directional Controls in GANs

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

Robust Multi-Task Learning with Excess Risks

Pairwise Alignment Improves Graph Domain Adaptation

Differentially Private Post-Processing for Fair Regression

Deep Fair Clustering for Visual Learning

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

Rethinking Controllable Variational Autoencoders

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

Adversarial Multiple Source Domain Adaptation

Learning Neural Networks with Adaptive Regularization

Inherent Tradeoffs in Learning Fair Representations

Neural Methods for Point-wise Dependency Estimation

Model-based Policy Optimization with Unsupervised Model Adaptation

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

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

Quantifying and Improving Transferability in Domain Generalization

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

Efficient Learning of Linear Graph Neural Networks via Node Subsampling

Learning List-Level Domain-Invariant Representations for Ranking

On the Relationship between Sum-Product Networks and Bayesian Networks

Collapsed Variational Inference for Sum-Product Networks

On Learning Invariant Representations for Domain Adaptation