Liam Schramm and Abdeslam Boularias. Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization. Proceedings of the 41^st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [https://arxiv.org/html/2407.05511v1]

Haonan Chang, Kowndinya Boyalakuntla, Yuhan Liu, Xinyu Zhang, Liam Schramm, Abdeslam Boularias. DAP: Diffusion-based Affordance Prediction for Multi-modality Storage. Proceedings of the International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, UAE, 2024.

Schramm, Liam, Yunfu Deng, Edgar Granados, and Abdeslam Boularias. USHER: Unbiased Sampling for Hindsight Experience Replay. Proceedings of the Conference on Robotic Learning (CoRL), Aukland, New Zealand, 2022. [video: https://www.youtube.com/watch?v=s1J2x3cMxdI&ab_channel=AbdeslamBoularias%5D [https://proceedings.mlr.press/v205/schramm23a.html]

_____ and Abdeslam Boularias. Learning-Guided Exploration for Efficient Sampling-Based Motion Planning in High Dimensions. Proceedings of the 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, PA, 2022. [video: https://www.youtube.com/watch?v=lD70ZFHxwus&ab_channel=AbdeslamBoularias] [https://ieeexplore.ieee.org/document/9812184]

_____, Avishai Sintov, Abdeslam Boularias. Learning to Transfer Dynamic Models of Underactuated Soft Robotics Hands. Proceedings of the 2020 International Conference on Robotics and Automation (ICRA), Paris, France, 2020. [video: https://www.youtube.com/watch?v=ki88e8Yovgs&ab_channel=AbdeslamBoularias%5D [https://ieeexplore.ieee.org/document/9197300]

_____. Convolutional neural networks and the quantum many-body problem. Senior thesis. Bard College, Annandale on Hudson, NY. 2018.

_____. Improving Performance of Automatic Program Repair Using Learned Heuristics. Proceedings of 11th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering, Paderborn, Germany, 2017. Student Research Competition, 2nd place award. [https://dl.acm.org/doi/10.1145/3106237.3121281]

Current Work

Liam Schramm and Abdeslam Boularias. Diffusion Models as Convex Optimizers of Non-Convex Value Functions. Current research agenda. [https://arxiv.org/abs/2407.12163]