Bo Liu

Be a scientist out of interest :)

I am a Member of Technical Staff at Recursive Superintelligence, working on pretraining and continual learning. My research interest lies in designing theoretically sound algorithms and neural architectures for agents with persistent memory and continual improvements. I received my Ph.D. from UT Austin, where I was fortunately co-advised by Prof. Peter Stone and Prof. Qiang Liu. Prior to that I completed my master degree at Stanford and my undergraduate degree at JHU.

Email / Github / Google Scholar / X / Thesis

Experience

Aug 2026 - Present	Recursive Superintelligence – Member of Technical Staff (RSI) Pretraining, Continual Learning
Nov 2025 - Aug 2026	Microsoft, Mountain View – Member of Technical Staff (MSI) Continual Learning; Manager: Weizhu Chen
Nov 2024 - Nov 2025	Meta, Menlo Park – Senior Research Scientist (MSL) Reasoning, Scaling RL; Manager: Yuandong Tian
Jun - Oct 2023	DeepMind, London – Research Intern Mentor: Arthur Szlam, Marc'aurelio Ranzato
Jun - Sept 2020	Nvidia, Sunnyvale – Research Intern Mentor: 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

Selected Publications (* ⇒ equal contribution)

Foundation Models, Architectures & Optimization

Maglev: Sliding Recurrent Memory

Bo Liu, Qiang Liu

Preprint, 2026

paper

Longhorn: State Space Models Are Amortized Online Learners

Bo Liu, Rui Wang, Lemeng Wu, Yihao Feng, Peter Stone, Qiang Liu

ICLR 2025; ENLSP @ NeurIPS 2024 Workshop Oral

paper / code

Cautious Optimizers: Improving Training with One Line of Code

*Kaizhao Liang, *Lizhang Chen, Bo Liu, Qiang Liu

ICLR 2026

paper / code

Memory-Efficient LLM Training with Online Subspace Descent

Kaizhao Liang, Bo Liu, Lizhang Chen, Qiang Liu

NeurIPS 2024

paper / code

Communication Efficient Distributed Training with Distributed Lion

*Bo Liu, *Lemeng Wu, *Lizhang Chen, Kaizhao Liang, Jiaxu Zhu, Chen Liang, Raghuraman Krishnamoorthi, Qiang Liu

NeurIPS 2024

paper

Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts

*Lizhang Chen, *Bo Liu, *Kaizhao Liang, Qiang Liu

ICLR 2024 Spotlight

paper

Asynchronous Local-SGD Training for Language Modeling

Bo Liu, Rachita Chhaparia, Arthur Douillard, Satyen Kale, Andrei A. Rusu, Jiajun Shen, Arthur Szlam, Marc'Aurelio Ranzato

WANT @ ICML 2024 Workshop Oral

paper / code

Firefly Neural Architecture Descent: A General Approach for Growing Neural Networks

*Lemeng Wu, *Bo Liu, Peter Stone, Qiang Liu

NeurIPS 2020

paper / code

Continual, Multi-Task & Meta Learning

FAMO: Fast Adaptive Multitask Optimization

Bo Liu, Yihao Feng, Peter Stone, Qiang Liu

NeurIPS 2023

paper / code

Conflict-Averse Gradient Descent for Multi-task Learning

Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, Qiang Liu

NeurIPS 2021

paper / code

Continual Learning and Private Unlearning

Bo Liu, Qiang Liu, Peter Stone

CoLLAs 2022

paper / code

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

*Bo Liu, *Mao Ye, Peter Stone, Steve Wright, Qiang Liu

NeurIPS 2022

paper / code

Reinforcement Learning & Decision Making

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

*Bo Liu, *Yuqian Jiang, Xiaohan Zhang, Qiang Liu, Shiqi Zhang, Joydeep Biswas, Peter Stone

Preprint, 2023

paper / code

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

Bo Liu, Yihao Feng, Qiang Liu, Peter Stone

AAAI 2023 Oral

paper / code

Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

Bo Liu, Qiang Liu, Peter Stone, Animesh Garg, Yuke Zhu, Animashree Anandkumar

ICML 2021 Oral

paper / code

Robotics & Embodied Learning

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

*Bo Liu, *Yifeng Zhu, *Chongkai Gao, Yihao Feng, Qiang Liu, Yuke Zhu, Peter Stone

NeurIPS 2023; RAP4Robots @ ICRA 2023 and TGR @ CoRL 2023 Workshop Oral

paper / code / website

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

*Jiaheng Hu, *Jay Shim, Chen Tang, Yoonchang Sung, Bo Liu, Peter Stone, Roberto Martin-Martin

RLC 2026 Outstanding Paper Award

paper / code

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

Huihan Liu, Changyeon Kim, Bo Liu, Minghuan Liu, Yuke Zhu

ICML 2026 Oral

paper / website

A Lifelong Learning Approach to Mobile Robot Navigation

*Bo Liu, *Xuesu Xiao, Peter Stone

RA-L / ICRA 2021

paper / code

Generative Modeling

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

Chenyu Wang, Paria Rashidinejad, DiJia Su, Song Jiang, Sid Wang, Siyan Zhao, Cai Zhou, Shannon Zejiang Shen, Feiyu Chen, Tommi Jaakkola, Yuandong Tian, Bo Liu

ICLR 2026

paper

Gumbel Distillation for Parallel Text Generation

*Chi Zhang, *Xixi Hu, Bo Liu, Qiang Liu

ICLR 2026

paper / code

Improving Rectified Flow with Boundary Conditions

*Xixi Hu, *Runlong Liao, Keyang Xu, Bo Liu, Yeqing Li, Eugene Ie, Hongliang Fei, Qiang Liu

ICCV 2025

paper

AMO Sampler: Enhancing Text Rendering with Overshooting

*Xixi Hu, *Keyang Xu, Bo Liu, Qiang Liu, Hongliang Fei

CVPR 2025

paper / code / website

AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies

Xixi Hu, Bo Liu, Xingchao Liu, Qiang Liu

NeurIPS 2024

paper / code

Teaching

Fall 2019	University of Texas at Austin – Teaching Assistant CS 394: Reinforcement Learning
Winter 2019	Stanford University – Teaching Assistant CS 234: Reinforcement Learning
Fall 2016	Johns Hopkins University – Teaching Assistant EN 601.665: Natural Language Processing
Fall 2015	Johns Hopkins University – Teaching Assistant EN 600.463: Algorithms