Scholar
Xiaofeng Lin
Google Scholar ID: Fshb3ykAAAAJ
PhD Candidate, Boston University
Citations & Impact
Citations
13
H-index
2
i10-index
0
Publications
5
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- ‘Debunk the Myth of SFT Generalization’ (Preprint, 2025), first author; demonstrates SFT can match or surpass RL baselines with prompt diversity and chain-of-thought supervision
- ‘Efficient Reinforcement Learning in Probabilistic Reward Machines’ (AAAI 2025, Oral), first author; extends reward-free framework to non-Markovian reward settings
- ‘A Real-to-Sim-to-Real Approach for Vision-Based Autonomous MAV-Catching-MAV’ (Unmanned Systems, 2024), co-author; implements a fully autonomous vision-based MAV catching system
- ‘Leveraging Untrustworthy Commands for Multi-Robot Coordination...’ (ACC 2024), co-first author; combines untrustworthy commands with submodular coordination algorithm
- ‘Bandit Submodular Maximization for Multi-Robot Coordination...’ (RSS 2023), co-author; generalizes Sequential Greedy algorithm to bandit setting for multi-target tracking
- Reviewer for ACC, ICLR, NeurIPS, AISTATS, ICML
