Xianyuan Zhan

Affiliations

Institute for AI Industry Research

papers

747

total citations

papers (15)

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning

NEURIPS 2022arXiv

citations

Universal Actions for Enhanced Embodied Foundation Models

CVPR 2025arXiv

citations

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

NEURIPS 2023arXiv

citations

Adversarial Contrastive Learning via Asymmetric InfoNCE

ECCV 2022arXiv

citations

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

ICLR 2024arXiv

citations

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

ICML 2024arXiv

citations

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

NEURIPS 2023arXiv

citations

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

ICML 2024arXiv

citations

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

ICML 2024arXiv

citations

Are Expressive Models Truly Necessary for Offline RL?

AAAI 2025arXiv

citations

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

NEURIPS 2025arXiv

citations

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

ICML 2024arXiv

citations

Xianyuan Zhan

Affiliations

papers (15)

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning

Universal Actions for Enhanced Embodied Foundation Models

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

Adversarial Contrastive Learning via Asymmetric InfoNCE

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

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Are Expressive Models Truly Necessary for Offline RL?

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

papers (15)

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning

Universal Actions for Enhanced Embodied Foundation Models

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

Adversarial Contrastive Learning via Asymmetric InfoNCE

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

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Are Expressive Models Truly Necessary for Offline RL?

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts