Liyuan Mao

5 papers · 2024–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 👑 Triple Crown

Venues

ICLR (2) NeurIPS (2) ICML (1)

Top co-authors

Xianyuan Zhan (4) Weinan Zhang (3) Jinliang Zheng (2) Jianxiong Li (2) Jingjing Liu (2) Haoran Xu (2) Yinan Zheng (2) Rui Ai (1) Kexin Zheng (1) Zhengbang Zhu (1)

Research topics

Deep Learning (4) Machine Learning (4) Learning Types · Machine Learning (4) Artificial Intelligence (3) Reinforcement Learning (3) Core AI (3) Models (3) Methods (2) Computer Vision (1) Applications (1) Domain-Specific (1) Learning Types · Deep Learning (1)

Keywords

diffusion model (3) offline reinforcement learning (3) policy optimization (1) attention mechanism (1) autonomous driving (1) trajectory prediction (1) behavior cloning (1) multi-agent learning (1) bradley-terry model (1) multimodal behavior (1) teammate modeling (1) classifier guidance (1) trajectory planning (1) multimodal pretraining (1) behavior constraint (1) multi-agent system (1) closed-loop planning (1) distribution correction (1) distribution correction estimation (1) implicit preference (1)

Papers

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance ICLR 2025 DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning ICML 2024 Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning NeurIPS 2024 MADiff: Offline Multi-agent Learning with Diffusion Models NeurIPS 2024 ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update ICLR 2024