Haoran Xu

Affiliations

Johns Hopkins UniversityXidian University

papers

707

total citations

papers (18)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

ICML 2024arXiv

414

citations

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

ICLR 2024arXiv

108

citations

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

NEURIPS 2022arXiv

citations

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

NEURIPS 2023arXiv

citations

ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update

ICLR 2024arXiv

citations

MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences

AAAI 2025arXiv

citations

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models

ICLR 2024arXiv

citations

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

ICCV 2025arXiv

citations

Information-Theoretic Reward Decomposition for Generalizable RLHF

NEURIPS 2025arXiv

citations

Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction

AAAI 2025

citations

VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning

CVPR 2025

citations

Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction

CVPR 2024

citations

Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning

ICCV 2023

citations

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

NEURIPS 2023

citations

DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning

CVPR 2024

citations

Haoran Xu

Affiliations

papers (18)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update

Federated Learning with Sample-level Client Drift Mitigation

SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes

PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

Information-Theoretic Reward Decomposition for Generalizable RLHF

Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction

VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning

Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction

Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning

papers (18)

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update

Federated Learning with Sample-level Client Drift Mitigation

SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes

PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

Information-Theoretic Reward Decomposition for Generalizable RLHF

Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction

VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning

Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction

Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning