Baiting Luo

Baiting Luo

AI Researcher · World Models · Reinforcement Learning · Planning under Uncertainty

Publications

You can also find my articles on my Google Scholar profile.

Planning with World Models and Learned Temporal Abstractions

Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction

Published in The Thirteenth International Conference on Learning Representations (ICLR 2025), 2025 Spotlight (top 5.1%)

This paper introduces the Latent Macro Action Planner (L-MAP), which learns temporally extended macro-actions with a state-conditioned VQ-VAE and plans over them with Monte Carlo Tree Search, enabling low-latency decision-making in stochastic, high-dimensional continuous control.

Recommended citation: Luo, B., Pettet, A., Laszka, A., Dubey, A., & Mukhopadhyay, A. (2025). "Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction." The Thirteenth International Conference on Learning Representations (ICLR 2025).
Paper | Code

Decision Making in Non-Stationary Environments

NS-Gym: Open-Source Simulation Environments and Benchmarks for Non-Stationary Markov Decision Processes

Published in Advances in Neural Information Processing Systems (NeurIPS 2025), Datasets and Benchmarks Track, 2025

NS-Gym is an open-source toolkit of simulation environments and benchmarks for evaluating online decision-making algorithms in non-stationary Markov decision processes.

Recommended citation: Keplinger, N. S., Luo, B., Bektas, I., Zhang, Y., Wray, K. H., Laszka, A., Dubey, A., & Mukhopadhyay, A. (2025). "NS-Gym: Open-Source Simulation Environments and Benchmarks for Non-Stationary Markov Decision Processes." Advances in Neural Information Processing Systems (NeurIPS 2025), Datasets and Benchmarks Track.
Paper | Code

Act as You Learn: Adaptive Decision-Making in Non-Stationary Markov Decision Processes

Published in Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024 Vanderbilt C.F. Chen Best Paper Runner-Up

This paper presents a heuristic search algorithm called Adaptive Monte Carlo Tree Search (ADA-MCTS) for decision-making in non-stationary Markov decision processes.

Recommended citation: Luo, B., Zhang, Y., Dubey, A., & Mukhopadhyay, A. (2024). "Act as You Learn: Adaptive Decision-Making in Non-Stationary Markov Decision Processes." Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. 1301-1309.
Paper | Code

Decision Making in Non-Stationary Environments with Policy-Augmented Search

Published in Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

This paper introduces Policy-Augmented Monte Carlo tree search (PA-MCTS), which combines out-of-date policy estimates with online search using up-to-date environment models for decision-making in non-stationary environments.

Recommended citation: Pettet, A., Zhang, Y., Luo, B., Wray, K., Baier, H., Laszka, A., Dubey, A., & Mukhopadhyay, A. (2024). "Decision Making in Non-Stationary Environments with Policy-Augmented Search." Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. 2417-2419.
Paper | Code

Adaptive Decision-Making in Non-Stationary Markov Decision Processes

Published in Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

This research addresses the challenge of effective decision-making in non-stationary environments, focusing on “anytime” decision-making and adaptive strategies that balance performance optimization and safety prioritization.

Recommended citation: Luo, B. (2024). "Adaptive Decision-Making in Non-Stationary Markov Decision Processes." Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. 2755-2757.
Paper

Decision Making under Partial Observability

ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs

Published in Advances in Neural Information Processing Systems (NeurIPS 2025), 2025

This paper introduces ESCORT, a temporal belief representation for partially observable Markov decision processes that combines Stein variational inference with sliced consistency optimization for efficient belief tracking.

Recommended citation: Zhang, Y., Luo, B., Mukhopadhyay, A., Karsai, G., & Dubey, A. (2025). "ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs." Advances in Neural Information Processing Systems (NeurIPS 2025).
Paper

Observation Adaptation via Annealed Importance Resampling for Partially Observable Markov Decision Processes

Published in Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS 2025), 2025

This paper presents an annealed importance resampling approach for adapting to incoming observations in partially observable Markov decision processes.

Recommended citation: Zhang, Y., Luo, B., Mukhopadhyay, A., & Dubey, A. (2025). "Observation Adaptation via Annealed Importance Resampling for Partially Observable Markov Decision Processes." Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS 2025).
Paper

Shrinking POMCP: A Framework for Real-Time UAV Search and Rescue

Published in IEEE International Conference on Assured Autonomy (ICAA 2024), 2024

This paper presents Shrinking POMCP, a framework for real-time UAV search and rescue built on partially observable Monte Carlo planning.

Recommended citation: Zhang, Y., Luo, B., Mukhopadhyay, A., Stojcsics, D., Elenius, D., Roy, A., Jha, S., Maroti, M., Koutsoukos, X., Karsai, G., & Dubey, A. (2024). "Shrinking POMCP: A Framework for Real-Time UAV Search and Rescue." IEEE International Conference on Assured Autonomy (ICAA 2024).
Paper

Runtime Safety Assurance of Autonomous Vehicles

Towards Assured Autonomy using Neuro-Symbolic Components and Systems

Published in Neuro-symbolic AI: Foundations and Applications, Chapter 4 (Wiley, in press), 2026

Book chapter on building assured autonomous systems from neuro-symbolic components and systems.

Recommended citation: Dubey, A., Johnson, T. T., Koutsoukos, X., Luo, B., Manzanas Lopez, D., Maroti, M., Mukhopadhyay, A., Potteiger, N., Serbinowska, S., Stojcsics, D., Zhang, Y., & Karsai, G. (in press). "Towards Assured Autonomy using Neuro-Symbolic Components and Systems." In Neuro-symbolic AI: Foundations and Applications (Chap. 4). Wiley.

Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems

Published in Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023), 2023

This paper proposes a dynamic simplex strategy with online controller switching logic for balancing safety and performance in autonomous cyber-physical systems.

Recommended citation: Luo, B., Ramakrishna, S., Pettet, A., Kuhn, C., Karsai, G., & Mukhopadhyay, A. (2023). "Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems." Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023). 177-186.
Paper | Code

ANTI-CARLA: An Adversarial Testing Framework for Autonomous Vehicles in CARLA

Published in 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), 2022

This paper presents ANTI-CARLA, an adversarial testing framework for autonomous vehicles using the CARLA simulator.

Recommended citation: Ramakrishna, S., Luo, B., Kuhn, C. B., Karsai, G., & Dubey, A. (2022). "ANTI-CARLA: An Adversarial Testing Framework for Autonomous Vehicles in CARLA." 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC). 2620-2627.
Paper | Code

Risk-Aware Scene Sampling for Dynamic Assurance of Autonomous Systems

Published in 2022 IEEE International Conference on Assured Autonomy (ICAA), 2022

This paper presents a risk-aware scene sampling approach for dynamic assurance of autonomous systems, addressing challenges in cyber-physical systems and uncertainty management.

Recommended citation: Ramakrishna, S., Luo, B., Barve, Y., Karsai, G., & Dubey, A. (2022). "Risk-Aware Scene Sampling for Dynamic Assurance of Autonomous Systems." 2022 IEEE International Conference on Assured Autonomy (ICAA). 107-116.
Paper | Code

Securing Connected and Autonomous Vehicles

Credibility Enhanced Temporal Graph Convolutional Network Based Sybil Attack Detection On Edge Computing Servers

Published in 2021 IEEE Intelligent Vehicles Symposium (IV), 2021

This paper presents a Credibility Enhanced Temporal Graph Convolutional Network for detecting Sybil attacks on edge computing servers in vehicular ad hoc networks.

Recommended citation: Luo, B., Liu, X., & Zhu, Q. (2021). "Credibility Enhanced Temporal Graph Convolutional Network Based Sybil Attack Detection On Edge Computing Servers." 2021 IEEE Intelligent Vehicles Symposium (IV). 524-531.
Paper

Securing Connected Vehicle Applications with an Efficient Dual Cyber-Physical Blockchain Framework

Published in 2021 IEEE Intelligent Vehicles Symposium (IV), 2021

This paper presents an efficient dual cyber-physical blockchain framework for securing connected vehicle applications, addressing challenges in road transportation and intelligent vehicle systems.

Recommended citation: Liu, X., Luo, B., Abdo, A., Abu-Ghazaleh, N., & Zhu, Q. (2021). "Securing Connected Vehicle Applications with an Efficient Dual Cyber-Physical Blockchain Framework." 2021 IEEE Intelligent Vehicles Symposium (IV). 393-400.
Paper