Selected Publications

Topics:

Past Topics: (* denotes equal contribution; † denotes corresponding author)

Showing all 12 publications.

Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures

Bowen Li, Mayank Mishra, Isabel Liu, Stone Tao, Nishanth Kumar, Alexander Gray, Ruwan Wickramarachchi, Jonathan Francis, Sebastian Scherer, Tom Silver

CoRL 2026

Paper Project

TL;DR: An online recovery reinforcement learning approach for joint skill and concept discovery.

Bilevel Learning for Bilevel Planning

Bowen Li, Tom Silver, Sebastian Scherer, Alexander Gray

RSS 2025

Paper Project Code

TL;DR: A bilevel learning framework that invents neural predicates for long-horizon hybrid planning.

Unifying Deep Predicate Invention with Pre-trained Foundation Models

Qianwei Wang*, Bowen Li*, Zhanpeng Luo, Yifan Xu, Alexander Gray, Tom Silver, Sebastian Scherer, Katia Sycara, Yaqi Xie

IEEE Transactions on Robotics (TR-O)

Paper Project

TL;DR: An agentic framework for discovering and optimizing deep predicates on real images.

SLAP: Shortcut Learning for Abstract Planning

Isabel Liu, Bowen Li, Benjamin Eysenbach, Tom Silver

ICLR 2026

Paper Code

TL;DR: A general framework for automated shortcut physical option discovery on provided hierarchical planners.

KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning

Yixuan Huang*, Bowen Li*, Vaibhav Saxena*, et al., Tom Silver

RSS 2026

Paper Project Code

TL;DR: A task suite and benchmark for long-horizon, embodied, and physical reasoning.

LogiCity: Advancing NeSy AI with Abstract Urban Simulation

Bowen Li, Zhaoyu Li, Qiwei Du, Jinqi Luo, Wenshan Wang, Yaqi Xie, Simon Stepputtis, Chen Wang, Katia Sycara, Pradeep Ravikumar, Alexander Gray, Xujie Si, Sebastian Scherer†

NeurIPS 2024 D&B Track

Paper Project Code, Data

TL;DR: A flexible First-Order Logical abstraction-based multi-agent urban simulator, where LLMs fail.

VoxDet: Voxel Learning for Novel Instance Detection

Bowen Li, Jiashun Wang, Yaoyu Hu, Chen Wang, Sebastian Scherer†

NeurIPS 2023 (★ SpotLight ★)

Paper Project Code, Data

TL;DR: A 3D-inspired framework for detecting ANY (Novel) specific instance in the wild.

Fast Task Planning with Neuro-Symbolic Relaxation

Qiwei Du, Bowen Li, et al. Chen Wang,

RA-L 2026

Paper Project

TL;DR: A general framework for learning-based ultra-fast task planning.

PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework overview

PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework

Bowen Li*, Ziyuan Huang*, Junjie Ye, Yiming Li, Sebastian Scherer, Hang Zhao, Changhong Fu†

ICCV 2023

Paper Project Code

TL;DR: A simple, general, and effective framework for end-to-end predictive tracking that largely compensates for onboard latency.

ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Tracking

Bowen Li, Changhong Fu, Fangqiang Ding, Junjie Ye, Fuling Lin

ICRA 2021

Paper Project Code

TL;DR: Low-light enhancement and target-aware dual filters enable robust nighttime UAV tracking at 34 FPS on a single CPU.

AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration

Bowen Li, Chen Wang, Pranay Reddy, Seungchan Kim, Sebastian Scherer†

ECCV 2022

Paper Project Code

TL;DR: Leverage class-agnostic relation to implement few-shot detection w/o fine-tuning, which enables fast and efficient robotic exploration.

Coding Agents for Generalized Task and Motion Planning Problems

Matteo Merler, Bowen Li, Josh Roy, Yichao Liang, Qianwei Wang, Yixuan Huang, Tom Silver

arXiv 2026

Paper Project Code

TL;DR: Coding agents synthesize reusable policies for generalized task and motion planning across 28 simulated environments.

Awards

  • Gibbons-Newell Graduate Fellowship 2023@RI, Carnegie Mellon University
  • National Scholarship (top 1%, twice) for Undergraduates
  • Shanghai Scholarship (top 2%) for Undergraduates
  • Robotics Institute Summer Scholar (RISS2021), Carnegie Mellon University
  • Excellent Student (top 1%), Tongji University
  • Academic Star Model of Tongji University (Ranking 1st)

Service

Academic Reviewer

  • International Conference on Machine Learning (ICML)
  • International Conference on Learning Representations (ICLR)
  • Annual Conference on Neural Information Processing Systems (NeurIPS)
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • IEEE/CVF International Conference on Computer Vision (ICCV)
  • European Conference on Computer Vision (ECCV)
  • IEEE International Conference on Robotics and Automation (ICRA)
  • International Journal on Robotics Research (IJRR)
  • IEEE Robotics and Automation Letters (RA-L)
  • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Area Chair

  • ICRA 2025 Workshop on Foundation Models and Neural-Symbolic AI for Robotics (FMNS)

Current and Past Affiliations

Mentors and Collaborators

Prof. Sebastian Scherer@CMU

Prof. Tom Silver@Princeton

Dr. Alexander Gray@Centaur AI

Prof. Chen Wang@Buffalo

Prof. Changhong Fu@Tongji

Prof. Hang Zhao@Tsinghua

Contact

  • bowenli2@cs.cmu.edu
  • +1-412-608-2217
  • 1723 Murray Ave, Robotics Institute SQH, Carnegie Mellon University, Pittsburgh, PA 15217, USA