Jianxiong Li

机构：Institute for AI Industry Research (AIR), Tsinghua University

发表论文 30 篇 · 总被引 912 次 · h-index 14

代表论文

• X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model (2025 · arXiv.org · 被引 221)
• Diffusion-Based Planning for Autonomous Driving with Flexible Guidance (2025 · International Conference on Learning Representations · 被引 174)
• Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization (2023 · International Conference on Learning Representations · 被引 136)
• Universal Actions for Enhanced Embodied Foundation Models (2025 · Computer Vision and Pattern Recognition · 被引 100)
• Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model (2024 · International Conference on Learning Representations · 被引 83)
• PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning (2023 · arXiv.org · 被引 34)