Haoran Xu

17

Papers

140

Total Citations

1

Affiliations

Affiliations

Johns Hopkins University

Papers (17)

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

Federated Learning with Sample-level Client Drift Mitigation

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

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

PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

Information-Theoretic Reward Decomposition for Generalizable RLHF

Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction

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

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

Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion

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

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

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

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

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

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