Scholar
Bo Liu
Google Scholar ID: RlaKKWAAAAAJ
Meta FAIR
Citations & Impact
Citations
3,462
H-index
25
i10-index
33
Publications
20
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- Longhorn: State Space Models Are Amortized Online Learners (ENLSP@NeurIPS 2024)
- AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies (NeurIPS 2024)
- Memory-Efficient LLM Training with Online Subspace Descent (NeurIPS 2024)
- Communication Efficient Distributed Training with Distributed Lion (NeurIPS 2024)
- Asynchronous Local-SGD Training for Language Modeling (WANT@ICML 2024)
- Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts (ICLR 2024 Spotlight)
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency (paper/code)
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning (NeurIPS 2023 oral presentation at RAP4Robots, ICRA 2023, and TGR, CoRL 2023)
- FAMO: Fast Adaptive Multitask Optimization (NeurIPS 2023)
- Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning (AAAI 2023 oral presentation)
- BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach (NeurIPS 2022)
- Continual Learning and Private Unlearning (CoLLAs 2022)
- Conflict-Averse Gradient Descent for Multi-task Learning (NeurIPS 2021)
- Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition (ICML 2021 oral presentation)
- A lifelong learning approach to mobile robot navigation (RA-L / ICRA 2021)
- Firefly neural architecture descent: a general approach for growing neural networks (NeurIPS 2020)
Research Experience
- Nov 2024 - Present: Meta, Menlo Park, Senior Research Scientist (FAIR), Focus: Reasoning, Scaling RL; Manager: Yuandong Tian
- Jun - Oct 2023: DeepMind, London, Research Intern, Mentors: Arthur Szlam, Marc'aurelio Ranzato
- Jun - Sept 2020: Nvidia, Sunnyvale, Research Intern, Mentors: Animashree Anandkumar, Yuke Zhu
- Jun - Sept 2018/2019: Baidu, Sunnyvale, Research Intern, Mentor: Ping Li
- May - Aug 2015/2016: Google, Los Angeles, Software Engineer Intern
Background
- Currently a Senior Research Scientist at Meta, focusing on reasoning and large-scale reinforcement learning. Research interests include continual learning and reinforcement learning, particularly in designing theoretically sound algorithms and neural architectures for training large-scale multi-purpose agents.
Miscellany
- Contact: Email / Github / Google Scholar / X / Thesis
