Scholar
Xinran Li
Google Scholar ID: 6fYlKXgAAAAJ
The Hong Kong University of Science and Technology (HKUST)
Citations & Impact
Citations
48
H-index
4
i10-index
2
Publications
11
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments' posted on arXiv in June 2025
- Paper 'Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective' posted on arXiv in June 2025
- Paper 'C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning' accepted to ICML 2025
- Paper 'Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning' accepted to ICLR 2024
- Paper 'Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control' accepted to AISTATS 2025
- Paper 'Learn How to Query from Unlabeled Data Streams in Federated Learning' accepted to AAAI 2025
- Paper 'Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning' accepted to NeurIPS 2024
- Paper 'Context-aware Communication for Multi-agent Reinforcement Learning' published at AAMAS 2024
